{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4155,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007220216606498195,
      "grad_norm": 15.138864517211914,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9322,
      "step": 10
    },
    {
      "epoch": 0.01444043321299639,
      "grad_norm": 11.833885192871094,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7888,
      "step": 20
    },
    {
      "epoch": 0.021660649819494584,
      "grad_norm": 7.410687446594238,
      "learning_rate": 3e-06,
      "loss": 0.5394,
      "step": 30
    },
    {
      "epoch": 0.02888086642599278,
      "grad_norm": 3.045423746109009,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.3,
      "step": 40
    },
    {
      "epoch": 0.036101083032490974,
      "grad_norm": 0.5977299809455872,
      "learning_rate": 5e-06,
      "loss": 0.158,
      "step": 50
    },
    {
      "epoch": 0.04332129963898917,
      "grad_norm": 0.23663052916526794,
      "learning_rate": 6e-06,
      "loss": 0.1049,
      "step": 60
    },
    {
      "epoch": 0.05054151624548736,
      "grad_norm": 0.24775876104831696,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.0929,
      "step": 70
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": 0.250676691532135,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0818,
      "step": 80
    },
    {
      "epoch": 0.06498194945848375,
      "grad_norm": 0.2527087926864624,
      "learning_rate": 9e-06,
      "loss": 0.0812,
      "step": 90
    },
    {
      "epoch": 0.07220216606498195,
      "grad_norm": 0.24259184300899506,
      "learning_rate": 1e-05,
      "loss": 0.0726,
      "step": 100
    },
    {
      "epoch": 0.07942238267148015,
      "grad_norm": 0.19805486500263214,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0657,
      "step": 110
    },
    {
      "epoch": 0.08664259927797834,
      "grad_norm": 0.21339212357997894,
      "learning_rate": 1.2e-05,
      "loss": 0.0649,
      "step": 120
    },
    {
      "epoch": 0.09386281588447654,
      "grad_norm": 0.27472904324531555,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0608,
      "step": 130
    },
    {
      "epoch": 0.10108303249097472,
      "grad_norm": 0.3953518867492676,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.055,
      "step": 140
    },
    {
      "epoch": 0.10830324909747292,
      "grad_norm": 0.19267311692237854,
      "learning_rate": 1.5e-05,
      "loss": 0.0546,
      "step": 150
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 0.16826550662517548,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0519,
      "step": 160
    },
    {
      "epoch": 0.12274368231046931,
      "grad_norm": 0.2655981183052063,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.0521,
      "step": 170
    },
    {
      "epoch": 0.1299638989169675,
      "grad_norm": 0.25509196519851685,
      "learning_rate": 1.8e-05,
      "loss": 0.0535,
      "step": 180
    },
    {
      "epoch": 0.1371841155234657,
      "grad_norm": 0.38085201382637024,
      "learning_rate": 1.9e-05,
      "loss": 0.0502,
      "step": 190
    },
    {
      "epoch": 0.1444043321299639,
      "grad_norm": 0.2515423893928528,
      "learning_rate": 2e-05,
      "loss": 0.0502,
      "step": 200
    },
    {
      "epoch": 0.15162454873646208,
      "grad_norm": 0.2517891824245453,
      "learning_rate": 2.1e-05,
      "loss": 0.0514,
      "step": 210
    },
    {
      "epoch": 0.1588447653429603,
      "grad_norm": 0.21332941949367523,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0463,
      "step": 220
    },
    {
      "epoch": 0.16606498194945848,
      "grad_norm": 0.2846091687679291,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.0526,
      "step": 230
    },
    {
      "epoch": 0.17328519855595667,
      "grad_norm": 0.2511647045612335,
      "learning_rate": 2.4e-05,
      "loss": 0.0487,
      "step": 240
    },
    {
      "epoch": 0.18050541516245489,
      "grad_norm": 0.20305795967578888,
      "learning_rate": 2.5e-05,
      "loss": 0.0437,
      "step": 250
    },
    {
      "epoch": 0.18772563176895307,
      "grad_norm": 0.27594617009162903,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0455,
      "step": 260
    },
    {
      "epoch": 0.19494584837545126,
      "grad_norm": 0.4420526921749115,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.0507,
      "step": 270
    },
    {
      "epoch": 0.20216606498194944,
      "grad_norm": 0.3529132604598999,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0483,
      "step": 280
    },
    {
      "epoch": 0.20938628158844766,
      "grad_norm": 0.18353258073329926,
      "learning_rate": 2.9e-05,
      "loss": 0.0435,
      "step": 290
    },
    {
      "epoch": 0.21660649819494585,
      "grad_norm": 0.2105967402458191,
      "learning_rate": 3e-05,
      "loss": 0.0489,
      "step": 300
    },
    {
      "epoch": 0.22382671480144403,
      "grad_norm": 0.21252156794071198,
      "learning_rate": 3.1e-05,
      "loss": 0.0434,
      "step": 310
    },
    {
      "epoch": 0.23104693140794225,
      "grad_norm": 0.189384326338768,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0391,
      "step": 320
    },
    {
      "epoch": 0.23826714801444043,
      "grad_norm": 0.22159768640995026,
      "learning_rate": 3.3e-05,
      "loss": 0.0438,
      "step": 330
    },
    {
      "epoch": 0.24548736462093862,
      "grad_norm": 0.2974785268306732,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0421,
      "step": 340
    },
    {
      "epoch": 0.2527075812274368,
      "grad_norm": 0.21233530342578888,
      "learning_rate": 3.5e-05,
      "loss": 0.0419,
      "step": 350
    },
    {
      "epoch": 0.259927797833935,
      "grad_norm": 0.198137104511261,
      "learning_rate": 3.6e-05,
      "loss": 0.0411,
      "step": 360
    },
    {
      "epoch": 0.26714801444043323,
      "grad_norm": 0.29586824774742126,
      "learning_rate": 3.7e-05,
      "loss": 0.0451,
      "step": 370
    },
    {
      "epoch": 0.2743682310469314,
      "grad_norm": 0.1930268108844757,
      "learning_rate": 3.8e-05,
      "loss": 0.0401,
      "step": 380
    },
    {
      "epoch": 0.2815884476534296,
      "grad_norm": 0.21896091103553772,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.0393,
      "step": 390
    },
    {
      "epoch": 0.2888086642599278,
      "grad_norm": 0.21269367635250092,
      "learning_rate": 4e-05,
      "loss": 0.0415,
      "step": 400
    },
    {
      "epoch": 0.296028880866426,
      "grad_norm": 0.2300368845462799,
      "learning_rate": 4.1e-05,
      "loss": 0.0436,
      "step": 410
    },
    {
      "epoch": 0.30324909747292417,
      "grad_norm": 0.17586210370063782,
      "learning_rate": 4.2e-05,
      "loss": 0.0417,
      "step": 420
    },
    {
      "epoch": 0.3104693140794224,
      "grad_norm": 0.20255301892757416,
      "learning_rate": 4.3e-05,
      "loss": 0.0373,
      "step": 430
    },
    {
      "epoch": 0.3176895306859206,
      "grad_norm": 0.29133227467536926,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0427,
      "step": 440
    },
    {
      "epoch": 0.3249097472924188,
      "grad_norm": 0.14938658475875854,
      "learning_rate": 4.5e-05,
      "loss": 0.0402,
      "step": 450
    },
    {
      "epoch": 0.33212996389891697,
      "grad_norm": 0.20491056144237518,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0407,
      "step": 460
    },
    {
      "epoch": 0.33935018050541516,
      "grad_norm": 0.38727957010269165,
      "learning_rate": 4.7e-05,
      "loss": 0.0393,
      "step": 470
    },
    {
      "epoch": 0.34657039711191334,
      "grad_norm": 0.2549976408481598,
      "learning_rate": 4.8e-05,
      "loss": 0.0381,
      "step": 480
    },
    {
      "epoch": 0.35379061371841153,
      "grad_norm": 0.21853362023830414,
      "learning_rate": 4.9e-05,
      "loss": 0.0407,
      "step": 490
    },
    {
      "epoch": 0.36101083032490977,
      "grad_norm": 0.2548893094062805,
      "learning_rate": 5e-05,
      "loss": 0.0366,
      "step": 500
    },
    {
      "epoch": 0.36823104693140796,
      "grad_norm": 0.2966635525226593,
      "learning_rate": 4.986320109439125e-05,
      "loss": 0.0388,
      "step": 510
    },
    {
      "epoch": 0.37545126353790614,
      "grad_norm": 0.2587813436985016,
      "learning_rate": 4.9726402188782486e-05,
      "loss": 0.0422,
      "step": 520
    },
    {
      "epoch": 0.38267148014440433,
      "grad_norm": 0.20156943798065186,
      "learning_rate": 4.958960328317374e-05,
      "loss": 0.0379,
      "step": 530
    },
    {
      "epoch": 0.3898916967509025,
      "grad_norm": 0.23318979144096375,
      "learning_rate": 4.945280437756498e-05,
      "loss": 0.0387,
      "step": 540
    },
    {
      "epoch": 0.3971119133574007,
      "grad_norm": 0.21295292675495148,
      "learning_rate": 4.931600547195623e-05,
      "loss": 0.0363,
      "step": 550
    },
    {
      "epoch": 0.4043321299638989,
      "grad_norm": 0.23067612946033478,
      "learning_rate": 4.917920656634747e-05,
      "loss": 0.0396,
      "step": 560
    },
    {
      "epoch": 0.41155234657039713,
      "grad_norm": 0.1751265823841095,
      "learning_rate": 4.904240766073871e-05,
      "loss": 0.0386,
      "step": 570
    },
    {
      "epoch": 0.4187725631768953,
      "grad_norm": 0.32408931851387024,
      "learning_rate": 4.8905608755129964e-05,
      "loss": 0.0369,
      "step": 580
    },
    {
      "epoch": 0.4259927797833935,
      "grad_norm": 0.1949748396873474,
      "learning_rate": 4.876880984952121e-05,
      "loss": 0.0387,
      "step": 590
    },
    {
      "epoch": 0.4332129963898917,
      "grad_norm": 0.21588054299354553,
      "learning_rate": 4.863201094391245e-05,
      "loss": 0.0365,
      "step": 600
    },
    {
      "epoch": 0.4404332129963899,
      "grad_norm": 0.19144290685653687,
      "learning_rate": 4.849521203830369e-05,
      "loss": 0.035,
      "step": 610
    },
    {
      "epoch": 0.44765342960288806,
      "grad_norm": 0.25373053550720215,
      "learning_rate": 4.835841313269494e-05,
      "loss": 0.0391,
      "step": 620
    },
    {
      "epoch": 0.4548736462093863,
      "grad_norm": 0.2404279261827469,
      "learning_rate": 4.822161422708619e-05,
      "loss": 0.0364,
      "step": 630
    },
    {
      "epoch": 0.4620938628158845,
      "grad_norm": 0.1697109341621399,
      "learning_rate": 4.808481532147743e-05,
      "loss": 0.0322,
      "step": 640
    },
    {
      "epoch": 0.4693140794223827,
      "grad_norm": 0.17318709194660187,
      "learning_rate": 4.7948016415868674e-05,
      "loss": 0.0365,
      "step": 650
    },
    {
      "epoch": 0.47653429602888087,
      "grad_norm": 0.18541967868804932,
      "learning_rate": 4.781121751025992e-05,
      "loss": 0.0394,
      "step": 660
    },
    {
      "epoch": 0.48375451263537905,
      "grad_norm": 0.21878574788570404,
      "learning_rate": 4.7674418604651164e-05,
      "loss": 0.0336,
      "step": 670
    },
    {
      "epoch": 0.49097472924187724,
      "grad_norm": 0.2381717413663864,
      "learning_rate": 4.753761969904241e-05,
      "loss": 0.0343,
      "step": 680
    },
    {
      "epoch": 0.4981949458483754,
      "grad_norm": 0.2559703290462494,
      "learning_rate": 4.7400820793433654e-05,
      "loss": 0.0356,
      "step": 690
    },
    {
      "epoch": 0.5054151624548736,
      "grad_norm": 0.25602829456329346,
      "learning_rate": 4.72640218878249e-05,
      "loss": 0.0341,
      "step": 700
    },
    {
      "epoch": 0.5126353790613718,
      "grad_norm": 0.30914345383644104,
      "learning_rate": 4.7127222982216145e-05,
      "loss": 0.0378,
      "step": 710
    },
    {
      "epoch": 0.51985559566787,
      "grad_norm": 0.24148257076740265,
      "learning_rate": 4.699042407660739e-05,
      "loss": 0.0329,
      "step": 720
    },
    {
      "epoch": 0.5270758122743683,
      "grad_norm": 0.16448011994361877,
      "learning_rate": 4.6853625170998635e-05,
      "loss": 0.0373,
      "step": 730
    },
    {
      "epoch": 0.5342960288808665,
      "grad_norm": 0.20992177724838257,
      "learning_rate": 4.671682626538988e-05,
      "loss": 0.0358,
      "step": 740
    },
    {
      "epoch": 0.5415162454873647,
      "grad_norm": 0.1955261081457138,
      "learning_rate": 4.6580027359781126e-05,
      "loss": 0.0373,
      "step": 750
    },
    {
      "epoch": 0.5487364620938628,
      "grad_norm": 0.1674635410308838,
      "learning_rate": 4.6443228454172364e-05,
      "loss": 0.0332,
      "step": 760
    },
    {
      "epoch": 0.555956678700361,
      "grad_norm": 0.22619013488292694,
      "learning_rate": 4.630642954856361e-05,
      "loss": 0.0375,
      "step": 770
    },
    {
      "epoch": 0.5631768953068592,
      "grad_norm": 0.20930354297161102,
      "learning_rate": 4.616963064295486e-05,
      "loss": 0.0385,
      "step": 780
    },
    {
      "epoch": 0.5703971119133574,
      "grad_norm": 0.23155862092971802,
      "learning_rate": 4.6032831737346106e-05,
      "loss": 0.0325,
      "step": 790
    },
    {
      "epoch": 0.5776173285198556,
      "grad_norm": 0.25036847591400146,
      "learning_rate": 4.5896032831737345e-05,
      "loss": 0.0326,
      "step": 800
    },
    {
      "epoch": 0.5848375451263538,
      "grad_norm": 0.17637784779071808,
      "learning_rate": 4.575923392612859e-05,
      "loss": 0.0352,
      "step": 810
    },
    {
      "epoch": 0.592057761732852,
      "grad_norm": 0.2410997748374939,
      "learning_rate": 4.5622435020519835e-05,
      "loss": 0.0343,
      "step": 820
    },
    {
      "epoch": 0.5992779783393501,
      "grad_norm": 0.18689364194869995,
      "learning_rate": 4.548563611491109e-05,
      "loss": 0.0337,
      "step": 830
    },
    {
      "epoch": 0.6064981949458483,
      "grad_norm": 0.1366495043039322,
      "learning_rate": 4.5348837209302326e-05,
      "loss": 0.0332,
      "step": 840
    },
    {
      "epoch": 0.6137184115523465,
      "grad_norm": 0.1845828890800476,
      "learning_rate": 4.521203830369357e-05,
      "loss": 0.0337,
      "step": 850
    },
    {
      "epoch": 0.6209386281588448,
      "grad_norm": 0.17139053344726562,
      "learning_rate": 4.5075239398084816e-05,
      "loss": 0.0373,
      "step": 860
    },
    {
      "epoch": 0.628158844765343,
      "grad_norm": 0.25084948539733887,
      "learning_rate": 4.493844049247606e-05,
      "loss": 0.0347,
      "step": 870
    },
    {
      "epoch": 0.6353790613718412,
      "grad_norm": 0.23243854939937592,
      "learning_rate": 4.4801641586867306e-05,
      "loss": 0.0298,
      "step": 880
    },
    {
      "epoch": 0.6425992779783394,
      "grad_norm": 0.16921032965183258,
      "learning_rate": 4.466484268125855e-05,
      "loss": 0.0335,
      "step": 890
    },
    {
      "epoch": 0.6498194945848376,
      "grad_norm": 0.21709440648555756,
      "learning_rate": 4.45280437756498e-05,
      "loss": 0.0294,
      "step": 900
    },
    {
      "epoch": 0.6570397111913358,
      "grad_norm": 0.25876304507255554,
      "learning_rate": 4.439124487004104e-05,
      "loss": 0.0355,
      "step": 910
    },
    {
      "epoch": 0.6642599277978339,
      "grad_norm": 0.23916779458522797,
      "learning_rate": 4.425444596443229e-05,
      "loss": 0.0301,
      "step": 920
    },
    {
      "epoch": 0.6714801444043321,
      "grad_norm": 0.19482851028442383,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.0331,
      "step": 930
    },
    {
      "epoch": 0.6787003610108303,
      "grad_norm": 0.1518426537513733,
      "learning_rate": 4.398084815321478e-05,
      "loss": 0.0313,
      "step": 940
    },
    {
      "epoch": 0.6859205776173285,
      "grad_norm": 0.17477025091648102,
      "learning_rate": 4.384404924760602e-05,
      "loss": 0.0284,
      "step": 950
    },
    {
      "epoch": 0.6931407942238267,
      "grad_norm": 0.2821789085865021,
      "learning_rate": 4.370725034199726e-05,
      "loss": 0.0294,
      "step": 960
    },
    {
      "epoch": 0.7003610108303249,
      "grad_norm": 0.19530260562896729,
      "learning_rate": 4.3570451436388506e-05,
      "loss": 0.0307,
      "step": 970
    },
    {
      "epoch": 0.7075812274368231,
      "grad_norm": 0.2189357876777649,
      "learning_rate": 4.343365253077976e-05,
      "loss": 0.0325,
      "step": 980
    },
    {
      "epoch": 0.7148014440433214,
      "grad_norm": 0.18680965900421143,
      "learning_rate": 4.3296853625171004e-05,
      "loss": 0.0298,
      "step": 990
    },
    {
      "epoch": 0.7220216606498195,
      "grad_norm": 0.20822104811668396,
      "learning_rate": 4.316005471956224e-05,
      "loss": 0.0318,
      "step": 1000
    },
    {
      "epoch": 0.7292418772563177,
      "grad_norm": 0.17637012898921967,
      "learning_rate": 4.302325581395349e-05,
      "loss": 0.0267,
      "step": 1010
    },
    {
      "epoch": 0.7364620938628159,
      "grad_norm": 0.16878972947597504,
      "learning_rate": 4.288645690834473e-05,
      "loss": 0.0285,
      "step": 1020
    },
    {
      "epoch": 0.7436823104693141,
      "grad_norm": 0.3033148944377899,
      "learning_rate": 4.2749658002735984e-05,
      "loss": 0.0315,
      "step": 1030
    },
    {
      "epoch": 0.7509025270758123,
      "grad_norm": 0.21088653802871704,
      "learning_rate": 4.261285909712722e-05,
      "loss": 0.0329,
      "step": 1040
    },
    {
      "epoch": 0.7581227436823105,
      "grad_norm": 0.20485380291938782,
      "learning_rate": 4.247606019151847e-05,
      "loss": 0.0321,
      "step": 1050
    },
    {
      "epoch": 0.7653429602888087,
      "grad_norm": 0.21797245740890503,
      "learning_rate": 4.233926128590971e-05,
      "loss": 0.0288,
      "step": 1060
    },
    {
      "epoch": 0.7725631768953068,
      "grad_norm": 0.1585124433040619,
      "learning_rate": 4.220246238030096e-05,
      "loss": 0.0332,
      "step": 1070
    },
    {
      "epoch": 0.779783393501805,
      "grad_norm": 0.18445636332035065,
      "learning_rate": 4.2065663474692204e-05,
      "loss": 0.0317,
      "step": 1080
    },
    {
      "epoch": 0.7870036101083032,
      "grad_norm": 0.2596589922904968,
      "learning_rate": 4.192886456908345e-05,
      "loss": 0.0283,
      "step": 1090
    },
    {
      "epoch": 0.7942238267148014,
      "grad_norm": 0.15991349518299103,
      "learning_rate": 4.1792065663474694e-05,
      "loss": 0.027,
      "step": 1100
    },
    {
      "epoch": 0.8014440433212996,
      "grad_norm": 0.2013750970363617,
      "learning_rate": 4.165526675786594e-05,
      "loss": 0.0285,
      "step": 1110
    },
    {
      "epoch": 0.8086642599277978,
      "grad_norm": 0.16817732155323029,
      "learning_rate": 4.1518467852257184e-05,
      "loss": 0.0304,
      "step": 1120
    },
    {
      "epoch": 0.8158844765342961,
      "grad_norm": 0.20662030577659607,
      "learning_rate": 4.138166894664843e-05,
      "loss": 0.0309,
      "step": 1130
    },
    {
      "epoch": 0.8231046931407943,
      "grad_norm": 0.24165768921375275,
      "learning_rate": 4.1244870041039675e-05,
      "loss": 0.0305,
      "step": 1140
    },
    {
      "epoch": 0.8303249097472925,
      "grad_norm": 0.15945856273174286,
      "learning_rate": 4.110807113543092e-05,
      "loss": 0.0331,
      "step": 1150
    },
    {
      "epoch": 0.8375451263537906,
      "grad_norm": 0.23878367245197296,
      "learning_rate": 4.097127222982216e-05,
      "loss": 0.0287,
      "step": 1160
    },
    {
      "epoch": 0.8447653429602888,
      "grad_norm": 0.20223484933376312,
      "learning_rate": 4.083447332421341e-05,
      "loss": 0.0283,
      "step": 1170
    },
    {
      "epoch": 0.851985559566787,
      "grad_norm": 0.23693232238292694,
      "learning_rate": 4.0697674418604655e-05,
      "loss": 0.0283,
      "step": 1180
    },
    {
      "epoch": 0.8592057761732852,
      "grad_norm": 0.21208103001117706,
      "learning_rate": 4.05608755129959e-05,
      "loss": 0.0291,
      "step": 1190
    },
    {
      "epoch": 0.8664259927797834,
      "grad_norm": 0.21978527307510376,
      "learning_rate": 4.042407660738714e-05,
      "loss": 0.031,
      "step": 1200
    },
    {
      "epoch": 0.8736462093862816,
      "grad_norm": 0.18041111528873444,
      "learning_rate": 4.0287277701778384e-05,
      "loss": 0.0266,
      "step": 1210
    },
    {
      "epoch": 0.8808664259927798,
      "grad_norm": 0.15536178648471832,
      "learning_rate": 4.015047879616963e-05,
      "loss": 0.0311,
      "step": 1220
    },
    {
      "epoch": 0.8880866425992779,
      "grad_norm": 0.17821329832077026,
      "learning_rate": 4.001367989056088e-05,
      "loss": 0.0303,
      "step": 1230
    },
    {
      "epoch": 0.8953068592057761,
      "grad_norm": 0.22445450723171234,
      "learning_rate": 3.987688098495212e-05,
      "loss": 0.0249,
      "step": 1240
    },
    {
      "epoch": 0.9025270758122743,
      "grad_norm": 0.22271278500556946,
      "learning_rate": 3.9740082079343365e-05,
      "loss": 0.0287,
      "step": 1250
    },
    {
      "epoch": 0.9097472924187726,
      "grad_norm": 0.23373781144618988,
      "learning_rate": 3.960328317373461e-05,
      "loss": 0.0301,
      "step": 1260
    },
    {
      "epoch": 0.9169675090252708,
      "grad_norm": 0.1760292649269104,
      "learning_rate": 3.9466484268125855e-05,
      "loss": 0.0266,
      "step": 1270
    },
    {
      "epoch": 0.924187725631769,
      "grad_norm": 0.19504322111606598,
      "learning_rate": 3.93296853625171e-05,
      "loss": 0.027,
      "step": 1280
    },
    {
      "epoch": 0.9314079422382672,
      "grad_norm": 0.23191095888614655,
      "learning_rate": 3.9192886456908346e-05,
      "loss": 0.0275,
      "step": 1290
    },
    {
      "epoch": 0.9386281588447654,
      "grad_norm": 0.28094080090522766,
      "learning_rate": 3.905608755129959e-05,
      "loss": 0.0299,
      "step": 1300
    },
    {
      "epoch": 0.9458483754512635,
      "grad_norm": 0.15457668900489807,
      "learning_rate": 3.8919288645690836e-05,
      "loss": 0.0281,
      "step": 1310
    },
    {
      "epoch": 0.9530685920577617,
      "grad_norm": 0.20441775023937225,
      "learning_rate": 3.878248974008208e-05,
      "loss": 0.0314,
      "step": 1320
    },
    {
      "epoch": 0.9602888086642599,
      "grad_norm": 0.2961263954639435,
      "learning_rate": 3.864569083447333e-05,
      "loss": 0.0285,
      "step": 1330
    },
    {
      "epoch": 0.9675090252707581,
      "grad_norm": 0.16792945563793182,
      "learning_rate": 3.850889192886457e-05,
      "loss": 0.0277,
      "step": 1340
    },
    {
      "epoch": 0.9747292418772563,
      "grad_norm": 0.3934960961341858,
      "learning_rate": 3.837209302325582e-05,
      "loss": 0.0303,
      "step": 1350
    },
    {
      "epoch": 0.9819494584837545,
      "grad_norm": 0.24637605249881744,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.0272,
      "step": 1360
    },
    {
      "epoch": 0.9891696750902527,
      "grad_norm": 0.21808254718780518,
      "learning_rate": 3.809849521203831e-05,
      "loss": 0.0266,
      "step": 1370
    },
    {
      "epoch": 0.9963898916967509,
      "grad_norm": 0.2921408712863922,
      "learning_rate": 3.796169630642955e-05,
      "loss": 0.0274,
      "step": 1380
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9881444816395965,
      "eval_f1": 0.8667477505754343,
      "eval_loss": 0.030792543664574623,
      "eval_precision": 0.8156923076923077,
      "eval_recall": 0.9246212226903653,
      "eval_runtime": 271.409,
      "eval_samples_per_second": 81.464,
      "eval_steps_per_second": 1.275,
      "step": 1385
    },
    {
      "epoch": 1.0036101083032491,
      "grad_norm": 0.18204669654369354,
      "learning_rate": 3.78248974008208e-05,
      "loss": 0.0265,
      "step": 1390
    },
    {
      "epoch": 1.0108303249097472,
      "grad_norm": 0.13540150225162506,
      "learning_rate": 3.7688098495212036e-05,
      "loss": 0.0239,
      "step": 1400
    },
    {
      "epoch": 1.0180505415162455,
      "grad_norm": 0.2114001214504242,
      "learning_rate": 3.755129958960328e-05,
      "loss": 0.0208,
      "step": 1410
    },
    {
      "epoch": 1.0252707581227436,
      "grad_norm": 0.20667189359664917,
      "learning_rate": 3.741450068399453e-05,
      "loss": 0.0282,
      "step": 1420
    },
    {
      "epoch": 1.032490974729242,
      "grad_norm": 0.16794054210186005,
      "learning_rate": 3.727770177838578e-05,
      "loss": 0.0216,
      "step": 1430
    },
    {
      "epoch": 1.03971119133574,
      "grad_norm": 0.19682972133159637,
      "learning_rate": 3.714090287277702e-05,
      "loss": 0.0209,
      "step": 1440
    },
    {
      "epoch": 1.0469314079422383,
      "grad_norm": 0.18295951187610626,
      "learning_rate": 3.700410396716826e-05,
      "loss": 0.0251,
      "step": 1450
    },
    {
      "epoch": 1.0541516245487366,
      "grad_norm": 0.1491762399673462,
      "learning_rate": 3.686730506155951e-05,
      "loss": 0.0215,
      "step": 1460
    },
    {
      "epoch": 1.0613718411552346,
      "grad_norm": 0.3141365647315979,
      "learning_rate": 3.673050615595075e-05,
      "loss": 0.0235,
      "step": 1470
    },
    {
      "epoch": 1.068592057761733,
      "grad_norm": 0.18586914241313934,
      "learning_rate": 3.6593707250342e-05,
      "loss": 0.0226,
      "step": 1480
    },
    {
      "epoch": 1.075812274368231,
      "grad_norm": 0.26788514852523804,
      "learning_rate": 3.645690834473324e-05,
      "loss": 0.0214,
      "step": 1490
    },
    {
      "epoch": 1.0830324909747293,
      "grad_norm": 0.18625912070274353,
      "learning_rate": 3.632010943912449e-05,
      "loss": 0.0223,
      "step": 1500
    },
    {
      "epoch": 1.0902527075812274,
      "grad_norm": 0.23848237097263336,
      "learning_rate": 3.6183310533515733e-05,
      "loss": 0.0222,
      "step": 1510
    },
    {
      "epoch": 1.0974729241877257,
      "grad_norm": 0.24550049006938934,
      "learning_rate": 3.604651162790698e-05,
      "loss": 0.0223,
      "step": 1520
    },
    {
      "epoch": 1.1046931407942238,
      "grad_norm": 0.33519259095191956,
      "learning_rate": 3.5909712722298224e-05,
      "loss": 0.0207,
      "step": 1530
    },
    {
      "epoch": 1.111913357400722,
      "grad_norm": 0.19318382441997528,
      "learning_rate": 3.577291381668947e-05,
      "loss": 0.0255,
      "step": 1540
    },
    {
      "epoch": 1.1191335740072201,
      "grad_norm": 0.23220829665660858,
      "learning_rate": 3.5636114911080714e-05,
      "loss": 0.0218,
      "step": 1550
    },
    {
      "epoch": 1.1263537906137184,
      "grad_norm": 0.1848268061876297,
      "learning_rate": 3.549931600547195e-05,
      "loss": 0.0252,
      "step": 1560
    },
    {
      "epoch": 1.1335740072202167,
      "grad_norm": 0.20493029057979584,
      "learning_rate": 3.5362517099863205e-05,
      "loss": 0.0233,
      "step": 1570
    },
    {
      "epoch": 1.1407942238267148,
      "grad_norm": 0.19206510484218597,
      "learning_rate": 3.522571819425445e-05,
      "loss": 0.0227,
      "step": 1580
    },
    {
      "epoch": 1.1480144404332129,
      "grad_norm": 0.25989973545074463,
      "learning_rate": 3.5088919288645695e-05,
      "loss": 0.0205,
      "step": 1590
    },
    {
      "epoch": 1.1552346570397112,
      "grad_norm": 0.20777900516986847,
      "learning_rate": 3.4952120383036933e-05,
      "loss": 0.026,
      "step": 1600
    },
    {
      "epoch": 1.1624548736462095,
      "grad_norm": 0.25129932165145874,
      "learning_rate": 3.481532147742818e-05,
      "loss": 0.0246,
      "step": 1610
    },
    {
      "epoch": 1.1696750902527075,
      "grad_norm": 0.245501309633255,
      "learning_rate": 3.467852257181943e-05,
      "loss": 0.0232,
      "step": 1620
    },
    {
      "epoch": 1.1768953068592058,
      "grad_norm": 0.19470812380313873,
      "learning_rate": 3.4541723666210676e-05,
      "loss": 0.02,
      "step": 1630
    },
    {
      "epoch": 1.184115523465704,
      "grad_norm": 0.23183578252792358,
      "learning_rate": 3.4404924760601914e-05,
      "loss": 0.0257,
      "step": 1640
    },
    {
      "epoch": 1.1913357400722022,
      "grad_norm": 0.2162778079509735,
      "learning_rate": 3.426812585499316e-05,
      "loss": 0.0242,
      "step": 1650
    },
    {
      "epoch": 1.1985559566787003,
      "grad_norm": 0.15980581939220428,
      "learning_rate": 3.4131326949384405e-05,
      "loss": 0.0242,
      "step": 1660
    },
    {
      "epoch": 1.2057761732851986,
      "grad_norm": 0.1984899491071701,
      "learning_rate": 3.399452804377565e-05,
      "loss": 0.0235,
      "step": 1670
    },
    {
      "epoch": 1.2129963898916967,
      "grad_norm": 0.19146302342414856,
      "learning_rate": 3.3857729138166895e-05,
      "loss": 0.0212,
      "step": 1680
    },
    {
      "epoch": 1.220216606498195,
      "grad_norm": 0.19686651229858398,
      "learning_rate": 3.372093023255814e-05,
      "loss": 0.0242,
      "step": 1690
    },
    {
      "epoch": 1.2274368231046933,
      "grad_norm": 0.17915378510951996,
      "learning_rate": 3.3584131326949385e-05,
      "loss": 0.0264,
      "step": 1700
    },
    {
      "epoch": 1.2346570397111913,
      "grad_norm": 0.18991689383983612,
      "learning_rate": 3.344733242134063e-05,
      "loss": 0.0227,
      "step": 1710
    },
    {
      "epoch": 1.2418772563176894,
      "grad_norm": 0.16964809596538544,
      "learning_rate": 3.3310533515731876e-05,
      "loss": 0.0229,
      "step": 1720
    },
    {
      "epoch": 1.2490974729241877,
      "grad_norm": 0.33044272661209106,
      "learning_rate": 3.317373461012312e-05,
      "loss": 0.0233,
      "step": 1730
    },
    {
      "epoch": 1.256317689530686,
      "grad_norm": 0.27375954389572144,
      "learning_rate": 3.3036935704514366e-05,
      "loss": 0.023,
      "step": 1740
    },
    {
      "epoch": 1.263537906137184,
      "grad_norm": 0.19099849462509155,
      "learning_rate": 3.290013679890561e-05,
      "loss": 0.0199,
      "step": 1750
    },
    {
      "epoch": 1.2707581227436824,
      "grad_norm": 0.21204090118408203,
      "learning_rate": 3.276333789329685e-05,
      "loss": 0.0228,
      "step": 1760
    },
    {
      "epoch": 1.2779783393501805,
      "grad_norm": 0.17759856581687927,
      "learning_rate": 3.26265389876881e-05,
      "loss": 0.0209,
      "step": 1770
    },
    {
      "epoch": 1.2851985559566788,
      "grad_norm": 0.19070599973201752,
      "learning_rate": 3.248974008207935e-05,
      "loss": 0.0223,
      "step": 1780
    },
    {
      "epoch": 1.2924187725631768,
      "grad_norm": 0.18185602128505707,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.0201,
      "step": 1790
    },
    {
      "epoch": 1.2996389891696751,
      "grad_norm": 0.20534738898277283,
      "learning_rate": 3.221614227086183e-05,
      "loss": 0.0202,
      "step": 1800
    },
    {
      "epoch": 1.3068592057761732,
      "grad_norm": 0.2479701191186905,
      "learning_rate": 3.2079343365253076e-05,
      "loss": 0.019,
      "step": 1810
    },
    {
      "epoch": 1.3140794223826715,
      "grad_norm": 0.2699389159679413,
      "learning_rate": 3.194254445964433e-05,
      "loss": 0.023,
      "step": 1820
    },
    {
      "epoch": 1.3212996389891698,
      "grad_norm": 0.22228173911571503,
      "learning_rate": 3.180574555403557e-05,
      "loss": 0.0199,
      "step": 1830
    },
    {
      "epoch": 1.3285198555956679,
      "grad_norm": 0.1938995122909546,
      "learning_rate": 3.166894664842681e-05,
      "loss": 0.0235,
      "step": 1840
    },
    {
      "epoch": 1.335740072202166,
      "grad_norm": 0.17550387978553772,
      "learning_rate": 3.1532147742818057e-05,
      "loss": 0.02,
      "step": 1850
    },
    {
      "epoch": 1.3429602888086642,
      "grad_norm": 0.13713954389095306,
      "learning_rate": 3.13953488372093e-05,
      "loss": 0.0239,
      "step": 1860
    },
    {
      "epoch": 1.3501805054151625,
      "grad_norm": 0.19476300477981567,
      "learning_rate": 3.125854993160055e-05,
      "loss": 0.0197,
      "step": 1870
    },
    {
      "epoch": 1.3574007220216606,
      "grad_norm": 0.23414915800094604,
      "learning_rate": 3.112175102599179e-05,
      "loss": 0.0179,
      "step": 1880
    },
    {
      "epoch": 1.364620938628159,
      "grad_norm": 0.20327487587928772,
      "learning_rate": 3.098495212038304e-05,
      "loss": 0.0215,
      "step": 1890
    },
    {
      "epoch": 1.371841155234657,
      "grad_norm": 0.2250749170780182,
      "learning_rate": 3.084815321477428e-05,
      "loss": 0.0213,
      "step": 1900
    },
    {
      "epoch": 1.3790613718411553,
      "grad_norm": 0.17825260758399963,
      "learning_rate": 3.071135430916553e-05,
      "loss": 0.0199,
      "step": 1910
    },
    {
      "epoch": 1.3862815884476534,
      "grad_norm": 0.22727660834789276,
      "learning_rate": 3.057455540355677e-05,
      "loss": 0.0223,
      "step": 1920
    },
    {
      "epoch": 1.3935018050541517,
      "grad_norm": 0.18458124995231628,
      "learning_rate": 3.0437756497948018e-05,
      "loss": 0.0223,
      "step": 1930
    },
    {
      "epoch": 1.4007220216606497,
      "grad_norm": 0.2251572608947754,
      "learning_rate": 3.0300957592339263e-05,
      "loss": 0.0227,
      "step": 1940
    },
    {
      "epoch": 1.407942238267148,
      "grad_norm": 0.2070099413394928,
      "learning_rate": 3.016415868673051e-05,
      "loss": 0.023,
      "step": 1950
    },
    {
      "epoch": 1.4151624548736463,
      "grad_norm": 0.1247980073094368,
      "learning_rate": 3.002735978112175e-05,
      "loss": 0.0201,
      "step": 1960
    },
    {
      "epoch": 1.4223826714801444,
      "grad_norm": 0.19043412804603577,
      "learning_rate": 2.9890560875512996e-05,
      "loss": 0.0186,
      "step": 1970
    },
    {
      "epoch": 1.4296028880866425,
      "grad_norm": 0.22574257850646973,
      "learning_rate": 2.9753761969904244e-05,
      "loss": 0.0189,
      "step": 1980
    },
    {
      "epoch": 1.4368231046931408,
      "grad_norm": 0.17224276065826416,
      "learning_rate": 2.961696306429549e-05,
      "loss": 0.0205,
      "step": 1990
    },
    {
      "epoch": 1.444043321299639,
      "grad_norm": 0.18050329387187958,
      "learning_rate": 2.9480164158686728e-05,
      "loss": 0.0215,
      "step": 2000
    },
    {
      "epoch": 1.4512635379061372,
      "grad_norm": 0.23059330880641937,
      "learning_rate": 2.9343365253077976e-05,
      "loss": 0.0225,
      "step": 2010
    },
    {
      "epoch": 1.4584837545126355,
      "grad_norm": 0.24907854199409485,
      "learning_rate": 2.920656634746922e-05,
      "loss": 0.0204,
      "step": 2020
    },
    {
      "epoch": 1.4657039711191335,
      "grad_norm": 0.1699414849281311,
      "learning_rate": 2.9069767441860467e-05,
      "loss": 0.024,
      "step": 2030
    },
    {
      "epoch": 1.4729241877256318,
      "grad_norm": 0.16529108583927155,
      "learning_rate": 2.893296853625171e-05,
      "loss": 0.0196,
      "step": 2040
    },
    {
      "epoch": 1.48014440433213,
      "grad_norm": 0.18618591129779816,
      "learning_rate": 2.8796169630642954e-05,
      "loss": 0.0235,
      "step": 2050
    },
    {
      "epoch": 1.4873646209386282,
      "grad_norm": 0.15030409395694733,
      "learning_rate": 2.8659370725034202e-05,
      "loss": 0.0217,
      "step": 2060
    },
    {
      "epoch": 1.4945848375451263,
      "grad_norm": 0.28873658180236816,
      "learning_rate": 2.8522571819425448e-05,
      "loss": 0.0249,
      "step": 2070
    },
    {
      "epoch": 1.5018050541516246,
      "grad_norm": 0.19894906878471375,
      "learning_rate": 2.838577291381669e-05,
      "loss": 0.0217,
      "step": 2080
    },
    {
      "epoch": 1.5090252707581229,
      "grad_norm": 0.20735248923301697,
      "learning_rate": 2.8248974008207935e-05,
      "loss": 0.0223,
      "step": 2090
    },
    {
      "epoch": 1.516245487364621,
      "grad_norm": 0.13647274672985077,
      "learning_rate": 2.811217510259918e-05,
      "loss": 0.02,
      "step": 2100
    },
    {
      "epoch": 1.523465703971119,
      "grad_norm": 0.16693101823329926,
      "learning_rate": 2.797537619699043e-05,
      "loss": 0.0243,
      "step": 2110
    },
    {
      "epoch": 1.5306859205776173,
      "grad_norm": 0.21320907771587372,
      "learning_rate": 2.7838577291381667e-05,
      "loss": 0.0222,
      "step": 2120
    },
    {
      "epoch": 1.5379061371841156,
      "grad_norm": 0.2132214903831482,
      "learning_rate": 2.7701778385772915e-05,
      "loss": 0.0219,
      "step": 2130
    },
    {
      "epoch": 1.5451263537906137,
      "grad_norm": 0.1506602168083191,
      "learning_rate": 2.756497948016416e-05,
      "loss": 0.0224,
      "step": 2140
    },
    {
      "epoch": 1.5523465703971118,
      "grad_norm": 0.18722060322761536,
      "learning_rate": 2.7428180574555406e-05,
      "loss": 0.0222,
      "step": 2150
    },
    {
      "epoch": 1.55956678700361,
      "grad_norm": 0.22277644276618958,
      "learning_rate": 2.7291381668946648e-05,
      "loss": 0.0248,
      "step": 2160
    },
    {
      "epoch": 1.5667870036101084,
      "grad_norm": 0.16420182585716248,
      "learning_rate": 2.7154582763337893e-05,
      "loss": 0.0197,
      "step": 2170
    },
    {
      "epoch": 1.5740072202166067,
      "grad_norm": 0.23195837438106537,
      "learning_rate": 2.701778385772914e-05,
      "loss": 0.0213,
      "step": 2180
    },
    {
      "epoch": 1.5812274368231047,
      "grad_norm": 0.19835099577903748,
      "learning_rate": 2.6880984952120387e-05,
      "loss": 0.0224,
      "step": 2190
    },
    {
      "epoch": 1.5884476534296028,
      "grad_norm": 0.1974717378616333,
      "learning_rate": 2.674418604651163e-05,
      "loss": 0.0248,
      "step": 2200
    },
    {
      "epoch": 1.595667870036101,
      "grad_norm": 0.23695822060108185,
      "learning_rate": 2.6607387140902874e-05,
      "loss": 0.0199,
      "step": 2210
    },
    {
      "epoch": 1.6028880866425994,
      "grad_norm": 0.2396339625120163,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.0224,
      "step": 2220
    },
    {
      "epoch": 1.6101083032490975,
      "grad_norm": 0.20308814942836761,
      "learning_rate": 2.6333789329685364e-05,
      "loss": 0.0224,
      "step": 2230
    },
    {
      "epoch": 1.6173285198555956,
      "grad_norm": 0.2676025927066803,
      "learning_rate": 2.6196990424076606e-05,
      "loss": 0.0192,
      "step": 2240
    },
    {
      "epoch": 1.6245487364620939,
      "grad_norm": 0.1903916597366333,
      "learning_rate": 2.606019151846785e-05,
      "loss": 0.0234,
      "step": 2250
    },
    {
      "epoch": 1.6317689530685922,
      "grad_norm": 0.194184347987175,
      "learning_rate": 2.59233926128591e-05,
      "loss": 0.021,
      "step": 2260
    },
    {
      "epoch": 1.6389891696750902,
      "grad_norm": 0.22250430285930634,
      "learning_rate": 2.5786593707250345e-05,
      "loss": 0.0211,
      "step": 2270
    },
    {
      "epoch": 1.6462093862815883,
      "grad_norm": 0.18064111471176147,
      "learning_rate": 2.5649794801641587e-05,
      "loss": 0.0176,
      "step": 2280
    },
    {
      "epoch": 1.6534296028880866,
      "grad_norm": 0.22021658718585968,
      "learning_rate": 2.5512995896032832e-05,
      "loss": 0.0205,
      "step": 2290
    },
    {
      "epoch": 1.660649819494585,
      "grad_norm": 0.18112881481647491,
      "learning_rate": 2.5376196990424077e-05,
      "loss": 0.0198,
      "step": 2300
    },
    {
      "epoch": 1.6678700361010832,
      "grad_norm": 0.25381046533584595,
      "learning_rate": 2.5239398084815325e-05,
      "loss": 0.0209,
      "step": 2310
    },
    {
      "epoch": 1.6750902527075813,
      "grad_norm": 0.19742076098918915,
      "learning_rate": 2.5102599179206564e-05,
      "loss": 0.0214,
      "step": 2320
    },
    {
      "epoch": 1.6823104693140793,
      "grad_norm": 0.20728257298469543,
      "learning_rate": 2.4965800273597812e-05,
      "loss": 0.0218,
      "step": 2330
    },
    {
      "epoch": 1.6895306859205776,
      "grad_norm": 0.14151689410209656,
      "learning_rate": 2.4829001367989058e-05,
      "loss": 0.0211,
      "step": 2340
    },
    {
      "epoch": 1.696750902527076,
      "grad_norm": 0.2515600621700287,
      "learning_rate": 2.46922024623803e-05,
      "loss": 0.0215,
      "step": 2350
    },
    {
      "epoch": 1.703971119133574,
      "grad_norm": 0.21007981896400452,
      "learning_rate": 2.4555403556771548e-05,
      "loss": 0.0207,
      "step": 2360
    },
    {
      "epoch": 1.711191335740072,
      "grad_norm": 0.20441214740276337,
      "learning_rate": 2.441860465116279e-05,
      "loss": 0.0204,
      "step": 2370
    },
    {
      "epoch": 1.7184115523465704,
      "grad_norm": 0.21464481949806213,
      "learning_rate": 2.428180574555404e-05,
      "loss": 0.0187,
      "step": 2380
    },
    {
      "epoch": 1.7256317689530687,
      "grad_norm": 0.18914371728897095,
      "learning_rate": 2.414500683994528e-05,
      "loss": 0.0214,
      "step": 2390
    },
    {
      "epoch": 1.7328519855595668,
      "grad_norm": 0.16250531375408173,
      "learning_rate": 2.4008207934336525e-05,
      "loss": 0.0229,
      "step": 2400
    },
    {
      "epoch": 1.7400722021660648,
      "grad_norm": 0.14336325228214264,
      "learning_rate": 2.387140902872777e-05,
      "loss": 0.0211,
      "step": 2410
    },
    {
      "epoch": 1.7472924187725631,
      "grad_norm": 0.2290533185005188,
      "learning_rate": 2.3734610123119016e-05,
      "loss": 0.0216,
      "step": 2420
    },
    {
      "epoch": 1.7545126353790614,
      "grad_norm": 0.21229666471481323,
      "learning_rate": 2.359781121751026e-05,
      "loss": 0.023,
      "step": 2430
    },
    {
      "epoch": 1.7617328519855595,
      "grad_norm": 0.17029692232608795,
      "learning_rate": 2.3461012311901506e-05,
      "loss": 0.0226,
      "step": 2440
    },
    {
      "epoch": 1.7689530685920578,
      "grad_norm": 0.1786644607782364,
      "learning_rate": 2.3324213406292748e-05,
      "loss": 0.0201,
      "step": 2450
    },
    {
      "epoch": 1.7761732851985559,
      "grad_norm": 0.1429545283317566,
      "learning_rate": 2.3187414500683997e-05,
      "loss": 0.0201,
      "step": 2460
    },
    {
      "epoch": 1.7833935018050542,
      "grad_norm": 0.18863752484321594,
      "learning_rate": 2.305061559507524e-05,
      "loss": 0.0205,
      "step": 2470
    },
    {
      "epoch": 1.7906137184115525,
      "grad_norm": 0.16493657231330872,
      "learning_rate": 2.2913816689466487e-05,
      "loss": 0.0214,
      "step": 2480
    },
    {
      "epoch": 1.7978339350180506,
      "grad_norm": 0.23174484074115753,
      "learning_rate": 2.277701778385773e-05,
      "loss": 0.0178,
      "step": 2490
    },
    {
      "epoch": 1.8050541516245486,
      "grad_norm": 0.2224528193473816,
      "learning_rate": 2.2640218878248974e-05,
      "loss": 0.0217,
      "step": 2500
    },
    {
      "epoch": 1.812274368231047,
      "grad_norm": 0.19585539400577545,
      "learning_rate": 2.250341997264022e-05,
      "loss": 0.0218,
      "step": 2510
    },
    {
      "epoch": 1.8194945848375452,
      "grad_norm": 0.18590857088565826,
      "learning_rate": 2.2366621067031464e-05,
      "loss": 0.0211,
      "step": 2520
    },
    {
      "epoch": 1.8267148014440433,
      "grad_norm": 0.17392487823963165,
      "learning_rate": 2.222982216142271e-05,
      "loss": 0.0208,
      "step": 2530
    },
    {
      "epoch": 1.8339350180505414,
      "grad_norm": 0.33551010489463806,
      "learning_rate": 2.2093023255813955e-05,
      "loss": 0.0213,
      "step": 2540
    },
    {
      "epoch": 1.8411552346570397,
      "grad_norm": 0.16854000091552734,
      "learning_rate": 2.19562243502052e-05,
      "loss": 0.0189,
      "step": 2550
    },
    {
      "epoch": 1.848375451263538,
      "grad_norm": 0.20123836398124695,
      "learning_rate": 2.1819425444596445e-05,
      "loss": 0.0216,
      "step": 2560
    },
    {
      "epoch": 1.855595667870036,
      "grad_norm": 0.1919688880443573,
      "learning_rate": 2.1682626538987687e-05,
      "loss": 0.0208,
      "step": 2570
    },
    {
      "epoch": 1.8628158844765343,
      "grad_norm": 0.20486849546432495,
      "learning_rate": 2.1545827633378936e-05,
      "loss": 0.0204,
      "step": 2580
    },
    {
      "epoch": 1.8700361010830324,
      "grad_norm": 0.15359218418598175,
      "learning_rate": 2.1409028727770177e-05,
      "loss": 0.0187,
      "step": 2590
    },
    {
      "epoch": 1.8772563176895307,
      "grad_norm": 0.17525233328342438,
      "learning_rate": 2.1272229822161423e-05,
      "loss": 0.0256,
      "step": 2600
    },
    {
      "epoch": 1.884476534296029,
      "grad_norm": 0.2669832408428192,
      "learning_rate": 2.1135430916552668e-05,
      "loss": 0.02,
      "step": 2610
    },
    {
      "epoch": 1.891696750902527,
      "grad_norm": 0.2607351839542389,
      "learning_rate": 2.0998632010943913e-05,
      "loss": 0.021,
      "step": 2620
    },
    {
      "epoch": 1.8989169675090252,
      "grad_norm": 0.1423048973083496,
      "learning_rate": 2.0861833105335158e-05,
      "loss": 0.0186,
      "step": 2630
    },
    {
      "epoch": 1.9061371841155235,
      "grad_norm": 0.2874491810798645,
      "learning_rate": 2.0725034199726403e-05,
      "loss": 0.0225,
      "step": 2640
    },
    {
      "epoch": 1.9133574007220218,
      "grad_norm": 0.19905777275562286,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.0205,
      "step": 2650
    },
    {
      "epoch": 1.9205776173285198,
      "grad_norm": 0.18077979981899261,
      "learning_rate": 2.0451436388508894e-05,
      "loss": 0.0172,
      "step": 2660
    },
    {
      "epoch": 1.927797833935018,
      "grad_norm": 0.21182967722415924,
      "learning_rate": 2.0314637482900136e-05,
      "loss": 0.0208,
      "step": 2670
    },
    {
      "epoch": 1.9350180505415162,
      "grad_norm": 0.23693156242370605,
      "learning_rate": 2.0177838577291384e-05,
      "loss": 0.0208,
      "step": 2680
    },
    {
      "epoch": 1.9422382671480145,
      "grad_norm": 0.1655312329530716,
      "learning_rate": 2.0041039671682626e-05,
      "loss": 0.0194,
      "step": 2690
    },
    {
      "epoch": 1.9494584837545126,
      "grad_norm": 0.18168915808200836,
      "learning_rate": 1.990424076607387e-05,
      "loss": 0.0202,
      "step": 2700
    },
    {
      "epoch": 1.9566787003610109,
      "grad_norm": 0.16807179152965546,
      "learning_rate": 1.9767441860465116e-05,
      "loss": 0.0225,
      "step": 2710
    },
    {
      "epoch": 1.963898916967509,
      "grad_norm": 0.15267817676067352,
      "learning_rate": 1.963064295485636e-05,
      "loss": 0.0189,
      "step": 2720
    },
    {
      "epoch": 1.9711191335740073,
      "grad_norm": 0.35743266344070435,
      "learning_rate": 1.9493844049247607e-05,
      "loss": 0.0172,
      "step": 2730
    },
    {
      "epoch": 1.9783393501805056,
      "grad_norm": 0.14603158831596375,
      "learning_rate": 1.9357045143638852e-05,
      "loss": 0.0175,
      "step": 2740
    },
    {
      "epoch": 1.9855595667870036,
      "grad_norm": 0.1915268450975418,
      "learning_rate": 1.9220246238030097e-05,
      "loss": 0.0202,
      "step": 2750
    },
    {
      "epoch": 1.9927797833935017,
      "grad_norm": 0.2167324721813202,
      "learning_rate": 1.9083447332421342e-05,
      "loss": 0.0191,
      "step": 2760
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.22105805575847626,
      "learning_rate": 1.8946648426812584e-05,
      "loss": 0.0206,
      "step": 2770
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9911191241647089,
      "eval_f1": 0.8963686600905629,
      "eval_loss": 0.024568406865000725,
      "eval_precision": 0.8729883765521071,
      "eval_recall": 0.9210357431847986,
      "eval_runtime": 271.5143,
      "eval_samples_per_second": 81.432,
      "eval_steps_per_second": 1.274,
      "step": 2770
    },
    {
      "epoch": 2.0072202166064983,
      "grad_norm": 0.15133358538150787,
      "learning_rate": 1.8809849521203833e-05,
      "loss": 0.0135,
      "step": 2780
    },
    {
      "epoch": 2.0144404332129966,
      "grad_norm": 0.23863369226455688,
      "learning_rate": 1.8673050615595075e-05,
      "loss": 0.0153,
      "step": 2790
    },
    {
      "epoch": 2.0216606498194944,
      "grad_norm": 0.16403010487556458,
      "learning_rate": 1.853625170998632e-05,
      "loss": 0.0161,
      "step": 2800
    },
    {
      "epoch": 2.0288808664259927,
      "grad_norm": 0.19030123949050903,
      "learning_rate": 1.8399452804377565e-05,
      "loss": 0.0137,
      "step": 2810
    },
    {
      "epoch": 2.036101083032491,
      "grad_norm": 0.17739665508270264,
      "learning_rate": 1.826265389876881e-05,
      "loss": 0.0149,
      "step": 2820
    },
    {
      "epoch": 2.0433212996389893,
      "grad_norm": 0.18450963497161865,
      "learning_rate": 1.8125854993160055e-05,
      "loss": 0.0151,
      "step": 2830
    },
    {
      "epoch": 2.050541516245487,
      "grad_norm": 0.1654953956604004,
      "learning_rate": 1.79890560875513e-05,
      "loss": 0.0152,
      "step": 2840
    },
    {
      "epoch": 2.0577617328519855,
      "grad_norm": 0.18726739287376404,
      "learning_rate": 1.7852257181942546e-05,
      "loss": 0.0136,
      "step": 2850
    },
    {
      "epoch": 2.064981949458484,
      "grad_norm": 0.15999707579612732,
      "learning_rate": 1.771545827633379e-05,
      "loss": 0.0167,
      "step": 2860
    },
    {
      "epoch": 2.072202166064982,
      "grad_norm": 0.20449534058570862,
      "learning_rate": 1.7578659370725033e-05,
      "loss": 0.0138,
      "step": 2870
    },
    {
      "epoch": 2.07942238267148,
      "grad_norm": 0.18105897307395935,
      "learning_rate": 1.744186046511628e-05,
      "loss": 0.0137,
      "step": 2880
    },
    {
      "epoch": 2.0866425992779782,
      "grad_norm": 0.2451828122138977,
      "learning_rate": 1.7305061559507523e-05,
      "loss": 0.0183,
      "step": 2890
    },
    {
      "epoch": 2.0938628158844765,
      "grad_norm": 0.24325129389762878,
      "learning_rate": 1.716826265389877e-05,
      "loss": 0.0142,
      "step": 2900
    },
    {
      "epoch": 2.101083032490975,
      "grad_norm": 0.21412310004234314,
      "learning_rate": 1.7031463748290014e-05,
      "loss": 0.0158,
      "step": 2910
    },
    {
      "epoch": 2.108303249097473,
      "grad_norm": 0.2084820568561554,
      "learning_rate": 1.689466484268126e-05,
      "loss": 0.0146,
      "step": 2920
    },
    {
      "epoch": 2.115523465703971,
      "grad_norm": 0.1751072257757187,
      "learning_rate": 1.6757865937072504e-05,
      "loss": 0.0153,
      "step": 2930
    },
    {
      "epoch": 2.1227436823104693,
      "grad_norm": 0.1661452054977417,
      "learning_rate": 1.662106703146375e-05,
      "loss": 0.0142,
      "step": 2940
    },
    {
      "epoch": 2.1299638989169676,
      "grad_norm": 0.15145418047904968,
      "learning_rate": 1.6484268125854994e-05,
      "loss": 0.0163,
      "step": 2950
    },
    {
      "epoch": 2.137184115523466,
      "grad_norm": 0.22948749363422394,
      "learning_rate": 1.634746922024624e-05,
      "loss": 0.0154,
      "step": 2960
    },
    {
      "epoch": 2.1444043321299637,
      "grad_norm": 0.20568566024303436,
      "learning_rate": 1.621067031463748e-05,
      "loss": 0.0152,
      "step": 2970
    },
    {
      "epoch": 2.151624548736462,
      "grad_norm": 0.1933920830488205,
      "learning_rate": 1.607387140902873e-05,
      "loss": 0.0163,
      "step": 2980
    },
    {
      "epoch": 2.1588447653429603,
      "grad_norm": 0.25813716650009155,
      "learning_rate": 1.5937072503419972e-05,
      "loss": 0.0128,
      "step": 2990
    },
    {
      "epoch": 2.1660649819494586,
      "grad_norm": 0.17636476457118988,
      "learning_rate": 1.580027359781122e-05,
      "loss": 0.0142,
      "step": 3000
    },
    {
      "epoch": 2.1732851985559565,
      "grad_norm": 0.2212180197238922,
      "learning_rate": 1.5663474692202462e-05,
      "loss": 0.0133,
      "step": 3010
    },
    {
      "epoch": 2.1805054151624548,
      "grad_norm": 0.23074433207511902,
      "learning_rate": 1.5526675786593707e-05,
      "loss": 0.0151,
      "step": 3020
    },
    {
      "epoch": 2.187725631768953,
      "grad_norm": 0.2936890423297882,
      "learning_rate": 1.5389876880984953e-05,
      "loss": 0.0132,
      "step": 3030
    },
    {
      "epoch": 2.1949458483754514,
      "grad_norm": 0.10483139753341675,
      "learning_rate": 1.5253077975376198e-05,
      "loss": 0.0146,
      "step": 3040
    },
    {
      "epoch": 2.2021660649819497,
      "grad_norm": 0.13914550840854645,
      "learning_rate": 1.5116279069767441e-05,
      "loss": 0.0178,
      "step": 3050
    },
    {
      "epoch": 2.2093862815884475,
      "grad_norm": 0.15463340282440186,
      "learning_rate": 1.4979480164158688e-05,
      "loss": 0.0126,
      "step": 3060
    },
    {
      "epoch": 2.216606498194946,
      "grad_norm": 0.18321174383163452,
      "learning_rate": 1.4842681258549932e-05,
      "loss": 0.0144,
      "step": 3070
    },
    {
      "epoch": 2.223826714801444,
      "grad_norm": 0.2047768235206604,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.0149,
      "step": 3080
    },
    {
      "epoch": 2.2310469314079424,
      "grad_norm": 0.15067626535892487,
      "learning_rate": 1.456908344733242e-05,
      "loss": 0.0134,
      "step": 3090
    },
    {
      "epoch": 2.2382671480144403,
      "grad_norm": 0.1758282482624054,
      "learning_rate": 1.4432284541723667e-05,
      "loss": 0.0133,
      "step": 3100
    },
    {
      "epoch": 2.2454873646209386,
      "grad_norm": 0.20649059116840363,
      "learning_rate": 1.429548563611491e-05,
      "loss": 0.0161,
      "step": 3110
    },
    {
      "epoch": 2.252707581227437,
      "grad_norm": 0.17980459332466125,
      "learning_rate": 1.4158686730506158e-05,
      "loss": 0.0135,
      "step": 3120
    },
    {
      "epoch": 2.259927797833935,
      "grad_norm": 0.22073961794376373,
      "learning_rate": 1.4021887824897401e-05,
      "loss": 0.0146,
      "step": 3130
    },
    {
      "epoch": 2.2671480144404335,
      "grad_norm": 0.20626509189605713,
      "learning_rate": 1.3885088919288646e-05,
      "loss": 0.0138,
      "step": 3140
    },
    {
      "epoch": 2.2743682310469313,
      "grad_norm": 0.16285601258277893,
      "learning_rate": 1.374829001367989e-05,
      "loss": 0.0136,
      "step": 3150
    },
    {
      "epoch": 2.2815884476534296,
      "grad_norm": 0.17455926537513733,
      "learning_rate": 1.3611491108071137e-05,
      "loss": 0.0138,
      "step": 3160
    },
    {
      "epoch": 2.288808664259928,
      "grad_norm": 0.18891878426074982,
      "learning_rate": 1.347469220246238e-05,
      "loss": 0.0151,
      "step": 3170
    },
    {
      "epoch": 2.2960288808664258,
      "grad_norm": 0.13757237792015076,
      "learning_rate": 1.3337893296853627e-05,
      "loss": 0.017,
      "step": 3180
    },
    {
      "epoch": 2.303249097472924,
      "grad_norm": 0.18987725675106049,
      "learning_rate": 1.3201094391244869e-05,
      "loss": 0.0147,
      "step": 3190
    },
    {
      "epoch": 2.3104693140794224,
      "grad_norm": 0.13427282869815826,
      "learning_rate": 1.3064295485636116e-05,
      "loss": 0.0142,
      "step": 3200
    },
    {
      "epoch": 2.3176895306859207,
      "grad_norm": 0.2868107557296753,
      "learning_rate": 1.292749658002736e-05,
      "loss": 0.0141,
      "step": 3210
    },
    {
      "epoch": 2.324909747292419,
      "grad_norm": 0.19995689392089844,
      "learning_rate": 1.2790697674418606e-05,
      "loss": 0.0145,
      "step": 3220
    },
    {
      "epoch": 2.332129963898917,
      "grad_norm": 0.15799254179000854,
      "learning_rate": 1.265389876880985e-05,
      "loss": 0.0149,
      "step": 3230
    },
    {
      "epoch": 2.339350180505415,
      "grad_norm": 0.2354062795639038,
      "learning_rate": 1.2517099863201095e-05,
      "loss": 0.0173,
      "step": 3240
    },
    {
      "epoch": 2.3465703971119134,
      "grad_norm": 0.2461709827184677,
      "learning_rate": 1.238030095759234e-05,
      "loss": 0.0165,
      "step": 3250
    },
    {
      "epoch": 2.3537906137184117,
      "grad_norm": 0.17912667989730835,
      "learning_rate": 1.2243502051983585e-05,
      "loss": 0.0168,
      "step": 3260
    },
    {
      "epoch": 2.3610108303249095,
      "grad_norm": 0.2090194672346115,
      "learning_rate": 1.210670314637483e-05,
      "loss": 0.0133,
      "step": 3270
    },
    {
      "epoch": 2.368231046931408,
      "grad_norm": 0.16298013925552368,
      "learning_rate": 1.1969904240766076e-05,
      "loss": 0.0164,
      "step": 3280
    },
    {
      "epoch": 2.375451263537906,
      "grad_norm": 0.14699536561965942,
      "learning_rate": 1.183310533515732e-05,
      "loss": 0.0165,
      "step": 3290
    },
    {
      "epoch": 2.3826714801444044,
      "grad_norm": 0.1909872591495514,
      "learning_rate": 1.1696306429548564e-05,
      "loss": 0.0146,
      "step": 3300
    },
    {
      "epoch": 2.3898916967509027,
      "grad_norm": 0.149457648396492,
      "learning_rate": 1.155950752393981e-05,
      "loss": 0.0154,
      "step": 3310
    },
    {
      "epoch": 2.3971119133574006,
      "grad_norm": 0.18534165620803833,
      "learning_rate": 1.1422708618331055e-05,
      "loss": 0.0147,
      "step": 3320
    },
    {
      "epoch": 2.404332129963899,
      "grad_norm": 0.17388072609901428,
      "learning_rate": 1.12859097127223e-05,
      "loss": 0.0132,
      "step": 3330
    },
    {
      "epoch": 2.411552346570397,
      "grad_norm": 0.2680976390838623,
      "learning_rate": 1.1149110807113544e-05,
      "loss": 0.0148,
      "step": 3340
    },
    {
      "epoch": 2.4187725631768955,
      "grad_norm": 0.2023518681526184,
      "learning_rate": 1.1012311901504789e-05,
      "loss": 0.0133,
      "step": 3350
    },
    {
      "epoch": 2.4259927797833933,
      "grad_norm": 0.19814668595790863,
      "learning_rate": 1.0875512995896034e-05,
      "loss": 0.0139,
      "step": 3360
    },
    {
      "epoch": 2.4332129963898916,
      "grad_norm": 0.1586819589138031,
      "learning_rate": 1.0738714090287279e-05,
      "loss": 0.0139,
      "step": 3370
    },
    {
      "epoch": 2.44043321299639,
      "grad_norm": 0.12945076823234558,
      "learning_rate": 1.0601915184678524e-05,
      "loss": 0.0136,
      "step": 3380
    },
    {
      "epoch": 2.4476534296028882,
      "grad_norm": 0.22156469523906708,
      "learning_rate": 1.0465116279069768e-05,
      "loss": 0.017,
      "step": 3390
    },
    {
      "epoch": 2.4548736462093865,
      "grad_norm": 0.24720166623592377,
      "learning_rate": 1.0328317373461013e-05,
      "loss": 0.0131,
      "step": 3400
    },
    {
      "epoch": 2.4620938628158844,
      "grad_norm": 0.15608453750610352,
      "learning_rate": 1.0191518467852258e-05,
      "loss": 0.0155,
      "step": 3410
    },
    {
      "epoch": 2.4693140794223827,
      "grad_norm": 0.34953010082244873,
      "learning_rate": 1.0054719562243503e-05,
      "loss": 0.017,
      "step": 3420
    },
    {
      "epoch": 2.476534296028881,
      "grad_norm": 0.20051924884319305,
      "learning_rate": 9.917920656634749e-06,
      "loss": 0.0136,
      "step": 3430
    },
    {
      "epoch": 2.483754512635379,
      "grad_norm": 0.20402652025222778,
      "learning_rate": 9.781121751025992e-06,
      "loss": 0.0133,
      "step": 3440
    },
    {
      "epoch": 2.490974729241877,
      "grad_norm": 0.1991117298603058,
      "learning_rate": 9.644322845417237e-06,
      "loss": 0.0153,
      "step": 3450
    },
    {
      "epoch": 2.4981949458483754,
      "grad_norm": 0.1154688373208046,
      "learning_rate": 9.507523939808483e-06,
      "loss": 0.0126,
      "step": 3460
    },
    {
      "epoch": 2.5054151624548737,
      "grad_norm": 0.1297905594110489,
      "learning_rate": 9.370725034199728e-06,
      "loss": 0.0146,
      "step": 3470
    },
    {
      "epoch": 2.512635379061372,
      "grad_norm": 0.23860248923301697,
      "learning_rate": 9.233926128590973e-06,
      "loss": 0.0159,
      "step": 3480
    },
    {
      "epoch": 2.51985559566787,
      "grad_norm": 0.20767924189567566,
      "learning_rate": 9.097127222982216e-06,
      "loss": 0.0133,
      "step": 3490
    },
    {
      "epoch": 2.527075812274368,
      "grad_norm": 0.22992978990077972,
      "learning_rate": 8.960328317373462e-06,
      "loss": 0.016,
      "step": 3500
    },
    {
      "epoch": 2.5342960288808665,
      "grad_norm": 0.13888780772686005,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.0129,
      "step": 3510
    },
    {
      "epoch": 2.5415162454873648,
      "grad_norm": 0.17588818073272705,
      "learning_rate": 8.686730506155952e-06,
      "loss": 0.0155,
      "step": 3520
    },
    {
      "epoch": 2.5487364620938626,
      "grad_norm": 0.17710047960281372,
      "learning_rate": 8.549931600547197e-06,
      "loss": 0.0147,
      "step": 3530
    },
    {
      "epoch": 2.555956678700361,
      "grad_norm": 0.2465488165616989,
      "learning_rate": 8.41313269493844e-06,
      "loss": 0.0159,
      "step": 3540
    },
    {
      "epoch": 2.563176895306859,
      "grad_norm": 0.211311474442482,
      "learning_rate": 8.276333789329686e-06,
      "loss": 0.0142,
      "step": 3550
    },
    {
      "epoch": 2.5703971119133575,
      "grad_norm": 0.19003704190254211,
      "learning_rate": 8.139534883720931e-06,
      "loss": 0.0156,
      "step": 3560
    },
    {
      "epoch": 2.577617328519856,
      "grad_norm": 0.20325423777103424,
      "learning_rate": 8.002735978112176e-06,
      "loss": 0.0138,
      "step": 3570
    },
    {
      "epoch": 2.5848375451263537,
      "grad_norm": 0.20516729354858398,
      "learning_rate": 7.865937072503421e-06,
      "loss": 0.0146,
      "step": 3580
    },
    {
      "epoch": 2.592057761732852,
      "grad_norm": 0.15101560950279236,
      "learning_rate": 7.729138166894665e-06,
      "loss": 0.0144,
      "step": 3590
    },
    {
      "epoch": 2.5992779783393503,
      "grad_norm": 0.20914088189601898,
      "learning_rate": 7.592339261285911e-06,
      "loss": 0.0147,
      "step": 3600
    },
    {
      "epoch": 2.606498194945848,
      "grad_norm": 0.21813435852527618,
      "learning_rate": 7.455540355677155e-06,
      "loss": 0.0148,
      "step": 3610
    },
    {
      "epoch": 2.6137184115523464,
      "grad_norm": 0.23971576988697052,
      "learning_rate": 7.318741450068401e-06,
      "loss": 0.0131,
      "step": 3620
    },
    {
      "epoch": 2.6209386281588447,
      "grad_norm": 0.17804710566997528,
      "learning_rate": 7.181942544459645e-06,
      "loss": 0.0136,
      "step": 3630
    },
    {
      "epoch": 2.628158844765343,
      "grad_norm": 0.15980184078216553,
      "learning_rate": 7.04514363885089e-06,
      "loss": 0.0118,
      "step": 3640
    },
    {
      "epoch": 2.6353790613718413,
      "grad_norm": 0.23447448015213013,
      "learning_rate": 6.908344733242135e-06,
      "loss": 0.0119,
      "step": 3650
    },
    {
      "epoch": 2.6425992779783396,
      "grad_norm": 0.2265952080488205,
      "learning_rate": 6.77154582763338e-06,
      "loss": 0.0135,
      "step": 3660
    },
    {
      "epoch": 2.6498194945848375,
      "grad_norm": 0.27709242701530457,
      "learning_rate": 6.634746922024625e-06,
      "loss": 0.0139,
      "step": 3670
    },
    {
      "epoch": 2.6570397111913358,
      "grad_norm": 0.189510315656662,
      "learning_rate": 6.497948016415869e-06,
      "loss": 0.0128,
      "step": 3680
    },
    {
      "epoch": 2.664259927797834,
      "grad_norm": 0.09412135928869247,
      "learning_rate": 6.3611491108071144e-06,
      "loss": 0.0155,
      "step": 3690
    },
    {
      "epoch": 2.671480144404332,
      "grad_norm": 0.21313029527664185,
      "learning_rate": 6.224350205198359e-06,
      "loss": 0.0144,
      "step": 3700
    },
    {
      "epoch": 2.67870036101083,
      "grad_norm": 0.35182449221611023,
      "learning_rate": 6.087551299589603e-06,
      "loss": 0.0158,
      "step": 3710
    },
    {
      "epoch": 2.6859205776173285,
      "grad_norm": 0.20150898396968842,
      "learning_rate": 5.950752393980848e-06,
      "loss": 0.0139,
      "step": 3720
    },
    {
      "epoch": 2.693140794223827,
      "grad_norm": 0.1621181070804596,
      "learning_rate": 5.8139534883720935e-06,
      "loss": 0.0131,
      "step": 3730
    },
    {
      "epoch": 2.700361010830325,
      "grad_norm": 0.20502717792987823,
      "learning_rate": 5.677154582763338e-06,
      "loss": 0.0132,
      "step": 3740
    },
    {
      "epoch": 2.707581227436823,
      "grad_norm": 0.14961372315883636,
      "learning_rate": 5.540355677154583e-06,
      "loss": 0.013,
      "step": 3750
    },
    {
      "epoch": 2.7148014440433212,
      "grad_norm": 0.2430783361196518,
      "learning_rate": 5.403556771545827e-06,
      "loss": 0.014,
      "step": 3760
    },
    {
      "epoch": 2.7220216606498195,
      "grad_norm": 0.2312983125448227,
      "learning_rate": 5.266757865937073e-06,
      "loss": 0.0151,
      "step": 3770
    },
    {
      "epoch": 2.729241877256318,
      "grad_norm": 0.23572318255901337,
      "learning_rate": 5.129958960328318e-06,
      "loss": 0.0146,
      "step": 3780
    },
    {
      "epoch": 2.7364620938628157,
      "grad_norm": 0.16730424761772156,
      "learning_rate": 4.993160054719562e-06,
      "loss": 0.014,
      "step": 3790
    },
    {
      "epoch": 2.743682310469314,
      "grad_norm": 0.26095303893089294,
      "learning_rate": 4.856361149110807e-06,
      "loss": 0.0153,
      "step": 3800
    },
    {
      "epoch": 2.7509025270758123,
      "grad_norm": 0.18118229508399963,
      "learning_rate": 4.7195622435020526e-06,
      "loss": 0.0148,
      "step": 3810
    },
    {
      "epoch": 2.7581227436823106,
      "grad_norm": 0.19273220002651215,
      "learning_rate": 4.582763337893297e-06,
      "loss": 0.0132,
      "step": 3820
    },
    {
      "epoch": 2.765342960288809,
      "grad_norm": 0.17820940911769867,
      "learning_rate": 4.445964432284542e-06,
      "loss": 0.0129,
      "step": 3830
    },
    {
      "epoch": 2.7725631768953067,
      "grad_norm": 0.255801260471344,
      "learning_rate": 4.3091655266757865e-06,
      "loss": 0.0138,
      "step": 3840
    },
    {
      "epoch": 2.779783393501805,
      "grad_norm": 0.2841118276119232,
      "learning_rate": 4.172366621067032e-06,
      "loss": 0.0165,
      "step": 3850
    },
    {
      "epoch": 2.7870036101083033,
      "grad_norm": 0.19371943175792694,
      "learning_rate": 4.035567715458277e-06,
      "loss": 0.0121,
      "step": 3860
    },
    {
      "epoch": 2.794223826714801,
      "grad_norm": 0.2262773960828781,
      "learning_rate": 3.898768809849521e-06,
      "loss": 0.0136,
      "step": 3870
    },
    {
      "epoch": 2.8014440433212995,
      "grad_norm": 0.17181913554668427,
      "learning_rate": 3.7619699042407664e-06,
      "loss": 0.0133,
      "step": 3880
    },
    {
      "epoch": 2.808664259927798,
      "grad_norm": 0.1269243359565735,
      "learning_rate": 3.625170998632011e-06,
      "loss": 0.0129,
      "step": 3890
    },
    {
      "epoch": 2.815884476534296,
      "grad_norm": 0.24962696433067322,
      "learning_rate": 3.488372093023256e-06,
      "loss": 0.0156,
      "step": 3900
    },
    {
      "epoch": 2.8231046931407944,
      "grad_norm": 0.21303677558898926,
      "learning_rate": 3.3515731874145007e-06,
      "loss": 0.016,
      "step": 3910
    },
    {
      "epoch": 2.8303249097472927,
      "grad_norm": 0.2242385894060135,
      "learning_rate": 3.2147742818057455e-06,
      "loss": 0.0147,
      "step": 3920
    },
    {
      "epoch": 2.8375451263537905,
      "grad_norm": 0.1730586290359497,
      "learning_rate": 3.0779753761969907e-06,
      "loss": 0.0125,
      "step": 3930
    },
    {
      "epoch": 2.844765342960289,
      "grad_norm": 0.17158852517604828,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0141,
      "step": 3940
    },
    {
      "epoch": 2.851985559566787,
      "grad_norm": 0.21147002279758453,
      "learning_rate": 2.8043775649794802e-06,
      "loss": 0.0142,
      "step": 3950
    },
    {
      "epoch": 2.859205776173285,
      "grad_norm": 0.22795933485031128,
      "learning_rate": 2.667578659370725e-06,
      "loss": 0.0133,
      "step": 3960
    },
    {
      "epoch": 2.8664259927797833,
      "grad_norm": 0.19155286252498627,
      "learning_rate": 2.5307797537619698e-06,
      "loss": 0.014,
      "step": 3970
    },
    {
      "epoch": 2.8736462093862816,
      "grad_norm": 0.1995808482170105,
      "learning_rate": 2.393980848153215e-06,
      "loss": 0.0131,
      "step": 3980
    },
    {
      "epoch": 2.88086642599278,
      "grad_norm": 0.20883041620254517,
      "learning_rate": 2.2571819425444598e-06,
      "loss": 0.0125,
      "step": 3990
    },
    {
      "epoch": 2.888086642599278,
      "grad_norm": 0.22262053191661835,
      "learning_rate": 2.1203830369357045e-06,
      "loss": 0.0151,
      "step": 4000
    },
    {
      "epoch": 2.895306859205776,
      "grad_norm": 0.17650048434734344,
      "learning_rate": 1.9835841313269493e-06,
      "loss": 0.0116,
      "step": 4010
    },
    {
      "epoch": 2.9025270758122743,
      "grad_norm": 0.2514309883117676,
      "learning_rate": 1.8467852257181943e-06,
      "loss": 0.0149,
      "step": 4020
    },
    {
      "epoch": 2.9097472924187726,
      "grad_norm": 0.13858270645141602,
      "learning_rate": 1.7099863201094393e-06,
      "loss": 0.0122,
      "step": 4030
    },
    {
      "epoch": 2.916967509025271,
      "grad_norm": 0.20119492709636688,
      "learning_rate": 1.573187414500684e-06,
      "loss": 0.0148,
      "step": 4040
    },
    {
      "epoch": 2.9241877256317688,
      "grad_norm": 0.2429434359073639,
      "learning_rate": 1.4363885088919288e-06,
      "loss": 0.0138,
      "step": 4050
    },
    {
      "epoch": 2.931407942238267,
      "grad_norm": 0.158556267619133,
      "learning_rate": 1.2995896032831738e-06,
      "loss": 0.0131,
      "step": 4060
    },
    {
      "epoch": 2.9386281588447654,
      "grad_norm": 0.15908589959144592,
      "learning_rate": 1.1627906976744186e-06,
      "loss": 0.0122,
      "step": 4070
    },
    {
      "epoch": 2.9458483754512637,
      "grad_norm": 0.20639561116695404,
      "learning_rate": 1.0259917920656636e-06,
      "loss": 0.0145,
      "step": 4080
    },
    {
      "epoch": 2.953068592057762,
      "grad_norm": 0.18711957335472107,
      "learning_rate": 8.891928864569083e-07,
      "loss": 0.0138,
      "step": 4090
    },
    {
      "epoch": 2.96028880866426,
      "grad_norm": 0.2037838101387024,
      "learning_rate": 7.523939808481532e-07,
      "loss": 0.0133,
      "step": 4100
    },
    {
      "epoch": 2.967509025270758,
      "grad_norm": 0.18255527317523956,
      "learning_rate": 6.155950752393981e-07,
      "loss": 0.0119,
      "step": 4110
    },
    {
      "epoch": 2.9747292418772564,
      "grad_norm": 0.21082955598831177,
      "learning_rate": 4.78796169630643e-07,
      "loss": 0.0145,
      "step": 4120
    },
    {
      "epoch": 2.9819494584837543,
      "grad_norm": 0.16639681160449982,
      "learning_rate": 3.4199726402188785e-07,
      "loss": 0.0116,
      "step": 4130
    },
    {
      "epoch": 2.9891696750902526,
      "grad_norm": 0.19572538137435913,
      "learning_rate": 2.051983584131327e-07,
      "loss": 0.0137,
      "step": 4140
    },
    {
      "epoch": 2.996389891696751,
      "grad_norm": 0.2220822423696518,
      "learning_rate": 6.839945280437757e-08,
      "loss": 0.0129,
      "step": 4150
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9919225627188221,
      "eval_f1": 0.9047710499602184,
      "eval_loss": 0.024072397500276566,
      "eval_precision": 0.8898783021668151,
      "eval_recall": 0.9201707636931834,
      "eval_runtime": 271.2138,
      "eval_samples_per_second": 81.522,
      "eval_steps_per_second": 1.276,
      "step": 4155
    }
  ],
  "logging_steps": 10,
  "max_steps": 4155,
  "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": 4.9767875544127224e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}