{
  "best_metric": 0.981892523364486,
  "best_model_checkpoint": "deit-base-patch16-224-finetuned-lora-medmnistv2/checkpoint-1870",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 3.587554693222046,
      "learning_rate": 0.004973262032085562,
      "loss": 1.6152,
      "step": 10
    },
    {
      "epoch": 0.11,
      "grad_norm": 2.7896249294281006,
      "learning_rate": 0.004946524064171123,
      "loss": 0.9293,
      "step": 20
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.900453805923462,
      "learning_rate": 0.004919786096256685,
      "loss": 0.7466,
      "step": 30
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1440342664718628,
      "learning_rate": 0.004893048128342246,
      "loss": 0.7922,
      "step": 40
    },
    {
      "epoch": 0.27,
      "grad_norm": 2.2305636405944824,
      "learning_rate": 0.004866310160427808,
      "loss": 0.7212,
      "step": 50
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.2825617790222168,
      "learning_rate": 0.004839572192513369,
      "loss": 0.6434,
      "step": 60
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.828630805015564,
      "learning_rate": 0.004812834224598931,
      "loss": 0.7316,
      "step": 70
    },
    {
      "epoch": 0.43,
      "grad_norm": 2.789102792739868,
      "learning_rate": 0.004786096256684492,
      "loss": 0.6947,
      "step": 80
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.9813400506973267,
      "learning_rate": 0.004759358288770054,
      "loss": 0.6042,
      "step": 90
    },
    {
      "epoch": 0.53,
      "grad_norm": 2.0925464630126953,
      "learning_rate": 0.004732620320855615,
      "loss": 0.5651,
      "step": 100
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.5666005611419678,
      "learning_rate": 0.004705882352941177,
      "loss": 0.6427,
      "step": 110
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.313793897628784,
      "learning_rate": 0.004679144385026738,
      "loss": 0.5964,
      "step": 120
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.3041290044784546,
      "learning_rate": 0.0046524064171123,
      "loss": 0.5604,
      "step": 130
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.781190276145935,
      "learning_rate": 0.0046256684491978615,
      "loss": 0.5539,
      "step": 140
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.0298523902893066,
      "learning_rate": 0.004598930481283423,
      "loss": 0.5521,
      "step": 150
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.687642216682434,
      "learning_rate": 0.004572192513368984,
      "loss": 0.6069,
      "step": 160
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.5597479343414307,
      "learning_rate": 0.004545454545454545,
      "loss": 0.5216,
      "step": 170
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.9967581033706665,
      "learning_rate": 0.004518716577540107,
      "loss": 0.4839,
      "step": 180
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8977803738317757,
      "eval_f1": 0.8762697412468743,
      "eval_loss": 0.2824207842350006,
      "eval_precision": 0.90567947974312,
      "eval_recall": 0.8661886777564033,
      "eval_runtime": 9.095,
      "eval_samples_per_second": 188.235,
      "eval_steps_per_second": 11.765,
      "step": 187
    },
    {
      "epoch": 1.02,
      "grad_norm": 1.7654634714126587,
      "learning_rate": 0.004491978609625669,
      "loss": 0.403,
      "step": 190
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.4351764917373657,
      "learning_rate": 0.00446524064171123,
      "loss": 0.5531,
      "step": 200
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.3419188261032104,
      "learning_rate": 0.004438502673796791,
      "loss": 0.4626,
      "step": 210
    },
    {
      "epoch": 1.18,
      "grad_norm": 1.2612953186035156,
      "learning_rate": 0.004411764705882353,
      "loss": 0.4752,
      "step": 220
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.9036948680877686,
      "learning_rate": 0.004385026737967914,
      "loss": 0.5154,
      "step": 230
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.5349265336990356,
      "learning_rate": 0.004358288770053476,
      "loss": 0.4288,
      "step": 240
    },
    {
      "epoch": 1.34,
      "grad_norm": 2.2249972820281982,
      "learning_rate": 0.0043315508021390375,
      "loss": 0.4383,
      "step": 250
    },
    {
      "epoch": 1.39,
      "grad_norm": 2.19148325920105,
      "learning_rate": 0.004304812834224599,
      "loss": 0.5313,
      "step": 260
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.2363046407699585,
      "learning_rate": 0.0042780748663101605,
      "loss": 0.4048,
      "step": 270
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.1985669136047363,
      "learning_rate": 0.004251336898395722,
      "loss": 0.5779,
      "step": 280
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.6020399332046509,
      "learning_rate": 0.004224598930481284,
      "loss": 0.5005,
      "step": 290
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.5544497966766357,
      "learning_rate": 0.004197860962566845,
      "loss": 0.4702,
      "step": 300
    },
    {
      "epoch": 1.66,
      "grad_norm": 1.830074429512024,
      "learning_rate": 0.004171122994652407,
      "loss": 0.4712,
      "step": 310
    },
    {
      "epoch": 1.71,
      "grad_norm": 1.7887426614761353,
      "learning_rate": 0.004144385026737968,
      "loss": 0.4806,
      "step": 320
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.9905050992965698,
      "learning_rate": 0.00411764705882353,
      "loss": 0.4353,
      "step": 330
    },
    {
      "epoch": 1.82,
      "grad_norm": 3.7927136421203613,
      "learning_rate": 0.004090909090909091,
      "loss": 0.4194,
      "step": 340
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.877655565738678,
      "learning_rate": 0.004064171122994653,
      "loss": 0.4592,
      "step": 350
    },
    {
      "epoch": 1.93,
      "grad_norm": 2.024024248123169,
      "learning_rate": 0.004037433155080214,
      "loss": 0.4472,
      "step": 360
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.5308970212936401,
      "learning_rate": 0.004010695187165776,
      "loss": 0.4762,
      "step": 370
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9281542056074766,
      "eval_f1": 0.9185809735494163,
      "eval_loss": 0.2145574986934662,
      "eval_precision": 0.9245598328831828,
      "eval_recall": 0.9160674573942845,
      "eval_runtime": 9.0756,
      "eval_samples_per_second": 188.637,
      "eval_steps_per_second": 11.79,
      "step": 374
    },
    {
      "epoch": 2.03,
      "grad_norm": 1.3481825590133667,
      "learning_rate": 0.0039839572192513365,
      "loss": 0.4369,
      "step": 380
    },
    {
      "epoch": 2.09,
      "grad_norm": 1.5832984447479248,
      "learning_rate": 0.003957219251336899,
      "loss": 0.4218,
      "step": 390
    },
    {
      "epoch": 2.14,
      "grad_norm": 1.2749643325805664,
      "learning_rate": 0.00393048128342246,
      "loss": 0.4345,
      "step": 400
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.725550651550293,
      "learning_rate": 0.0039037433155080215,
      "loss": 0.4145,
      "step": 410
    },
    {
      "epoch": 2.25,
      "grad_norm": 1.1786770820617676,
      "learning_rate": 0.003877005347593583,
      "loss": 0.4393,
      "step": 420
    },
    {
      "epoch": 2.3,
      "grad_norm": 1.432307243347168,
      "learning_rate": 0.003850267379679144,
      "loss": 0.3709,
      "step": 430
    },
    {
      "epoch": 2.35,
      "grad_norm": 2.1418895721435547,
      "learning_rate": 0.0038235294117647057,
      "loss": 0.4356,
      "step": 440
    },
    {
      "epoch": 2.41,
      "grad_norm": 2.0751211643218994,
      "learning_rate": 0.0037967914438502676,
      "loss": 0.4003,
      "step": 450
    },
    {
      "epoch": 2.46,
      "grad_norm": 1.2488188743591309,
      "learning_rate": 0.003770053475935829,
      "loss": 0.5263,
      "step": 460
    },
    {
      "epoch": 2.51,
      "grad_norm": 1.2528233528137207,
      "learning_rate": 0.0037433155080213902,
      "loss": 0.4224,
      "step": 470
    },
    {
      "epoch": 2.57,
      "grad_norm": 1.3320534229278564,
      "learning_rate": 0.0037165775401069518,
      "loss": 0.3868,
      "step": 480
    },
    {
      "epoch": 2.62,
      "grad_norm": 1.1116540431976318,
      "learning_rate": 0.0036898395721925133,
      "loss": 0.428,
      "step": 490
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.698747992515564,
      "learning_rate": 0.0036631016042780753,
      "loss": 0.4034,
      "step": 500
    },
    {
      "epoch": 2.73,
      "grad_norm": 0.9850418567657471,
      "learning_rate": 0.0036363636363636364,
      "loss": 0.3433,
      "step": 510
    },
    {
      "epoch": 2.78,
      "grad_norm": 1.1448285579681396,
      "learning_rate": 0.003609625668449198,
      "loss": 0.4379,
      "step": 520
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.8283530473709106,
      "learning_rate": 0.0035828877005347594,
      "loss": 0.3691,
      "step": 530
    },
    {
      "epoch": 2.89,
      "grad_norm": 1.0462627410888672,
      "learning_rate": 0.0035561497326203205,
      "loss": 0.3956,
      "step": 540
    },
    {
      "epoch": 2.94,
      "grad_norm": 2.427431583404541,
      "learning_rate": 0.0035294117647058825,
      "loss": 0.3877,
      "step": 550
    },
    {
      "epoch": 2.99,
      "grad_norm": 0.9325568079948425,
      "learning_rate": 0.003502673796791444,
      "loss": 0.3445,
      "step": 560
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.923481308411215,
      "eval_f1": 0.9167621051952115,
      "eval_loss": 0.21345409750938416,
      "eval_precision": 0.9243706129462914,
      "eval_recall": 0.9158821384305301,
      "eval_runtime": 9.0543,
      "eval_samples_per_second": 189.081,
      "eval_steps_per_second": 11.818,
      "step": 561
    },
    {
      "epoch": 3.05,
      "grad_norm": 1.159042239189148,
      "learning_rate": 0.0034759358288770055,
      "loss": 0.3665,
      "step": 570
    },
    {
      "epoch": 3.1,
      "grad_norm": 1.1578980684280396,
      "learning_rate": 0.0034491978609625666,
      "loss": 0.3696,
      "step": 580
    },
    {
      "epoch": 3.16,
      "grad_norm": 1.49112069606781,
      "learning_rate": 0.003422459893048128,
      "loss": 0.4138,
      "step": 590
    },
    {
      "epoch": 3.21,
      "grad_norm": 1.3102260828018188,
      "learning_rate": 0.00339572192513369,
      "loss": 0.4534,
      "step": 600
    },
    {
      "epoch": 3.26,
      "grad_norm": 1.571768045425415,
      "learning_rate": 0.0033689839572192517,
      "loss": 0.3879,
      "step": 610
    },
    {
      "epoch": 3.32,
      "grad_norm": 1.4697015285491943,
      "learning_rate": 0.0033422459893048127,
      "loss": 0.3276,
      "step": 620
    },
    {
      "epoch": 3.37,
      "grad_norm": 1.3779832124710083,
      "learning_rate": 0.0033155080213903743,
      "loss": 0.4291,
      "step": 630
    },
    {
      "epoch": 3.42,
      "grad_norm": 1.576749563217163,
      "learning_rate": 0.003288770053475936,
      "loss": 0.3085,
      "step": 640
    },
    {
      "epoch": 3.48,
      "grad_norm": 1.58197820186615,
      "learning_rate": 0.0032620320855614978,
      "loss": 0.4367,
      "step": 650
    },
    {
      "epoch": 3.53,
      "grad_norm": 0.894018292427063,
      "learning_rate": 0.003235294117647059,
      "loss": 0.3267,
      "step": 660
    },
    {
      "epoch": 3.58,
      "grad_norm": 1.0838289260864258,
      "learning_rate": 0.0032085561497326204,
      "loss": 0.4036,
      "step": 670
    },
    {
      "epoch": 3.64,
      "grad_norm": 0.9624530076980591,
      "learning_rate": 0.003181818181818182,
      "loss": 0.3892,
      "step": 680
    },
    {
      "epoch": 3.69,
      "grad_norm": 1.1710550785064697,
      "learning_rate": 0.003155080213903743,
      "loss": 0.3569,
      "step": 690
    },
    {
      "epoch": 3.74,
      "grad_norm": 1.3219703435897827,
      "learning_rate": 0.0031283422459893045,
      "loss": 0.3127,
      "step": 700
    },
    {
      "epoch": 3.8,
      "grad_norm": 1.4994938373565674,
      "learning_rate": 0.0031016042780748665,
      "loss": 0.3152,
      "step": 710
    },
    {
      "epoch": 3.85,
      "grad_norm": 2.016817331314087,
      "learning_rate": 0.003074866310160428,
      "loss": 0.3041,
      "step": 720
    },
    {
      "epoch": 3.9,
      "grad_norm": 1.1754976511001587,
      "learning_rate": 0.003048128342245989,
      "loss": 0.361,
      "step": 730
    },
    {
      "epoch": 3.96,
      "grad_norm": 1.263210654258728,
      "learning_rate": 0.0030213903743315507,
      "loss": 0.2963,
      "step": 740
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9415887850467289,
      "eval_f1": 0.934561225992784,
      "eval_loss": 0.16466087102890015,
      "eval_precision": 0.9322896664365989,
      "eval_recall": 0.9426571976128333,
      "eval_runtime": 9.0577,
      "eval_samples_per_second": 189.01,
      "eval_steps_per_second": 11.813,
      "step": 748
    },
    {
      "epoch": 4.01,
      "grad_norm": 1.6111160516738892,
      "learning_rate": 0.002994652406417112,
      "loss": 0.3683,
      "step": 750
    },
    {
      "epoch": 4.06,
      "grad_norm": 1.29823637008667,
      "learning_rate": 0.002967914438502674,
      "loss": 0.354,
      "step": 760
    },
    {
      "epoch": 4.12,
      "grad_norm": 0.9260041117668152,
      "learning_rate": 0.0029411764705882353,
      "loss": 0.3839,
      "step": 770
    },
    {
      "epoch": 4.17,
      "grad_norm": 1.0567574501037598,
      "learning_rate": 0.0029144385026737968,
      "loss": 0.3461,
      "step": 780
    },
    {
      "epoch": 4.22,
      "grad_norm": 0.9306647777557373,
      "learning_rate": 0.0028877005347593583,
      "loss": 0.344,
      "step": 790
    },
    {
      "epoch": 4.28,
      "grad_norm": 0.9743908643722534,
      "learning_rate": 0.0028609625668449194,
      "loss": 0.2981,
      "step": 800
    },
    {
      "epoch": 4.33,
      "grad_norm": 0.7713109254837036,
      "learning_rate": 0.0028342245989304814,
      "loss": 0.3017,
      "step": 810
    },
    {
      "epoch": 4.39,
      "grad_norm": 1.3103464841842651,
      "learning_rate": 0.002807486631016043,
      "loss": 0.3411,
      "step": 820
    },
    {
      "epoch": 4.44,
      "grad_norm": 0.7277514934539795,
      "learning_rate": 0.0027807486631016044,
      "loss": 0.2546,
      "step": 830
    },
    {
      "epoch": 4.49,
      "grad_norm": 0.9697772264480591,
      "learning_rate": 0.0027540106951871655,
      "loss": 0.339,
      "step": 840
    },
    {
      "epoch": 4.55,
      "grad_norm": 0.885215163230896,
      "learning_rate": 0.002727272727272727,
      "loss": 0.2738,
      "step": 850
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.8923905491828918,
      "learning_rate": 0.002700534759358289,
      "loss": 0.2996,
      "step": 860
    },
    {
      "epoch": 4.65,
      "grad_norm": 1.0155311822891235,
      "learning_rate": 0.0026737967914438505,
      "loss": 0.3621,
      "step": 870
    },
    {
      "epoch": 4.71,
      "grad_norm": 0.6661949157714844,
      "learning_rate": 0.0026470588235294116,
      "loss": 0.2636,
      "step": 880
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.1502758264541626,
      "learning_rate": 0.002620320855614973,
      "loss": 0.3281,
      "step": 890
    },
    {
      "epoch": 4.81,
      "grad_norm": 0.9213528037071228,
      "learning_rate": 0.0025935828877005347,
      "loss": 0.3139,
      "step": 900
    },
    {
      "epoch": 4.87,
      "grad_norm": 0.9923821687698364,
      "learning_rate": 0.0025668449197860967,
      "loss": 0.2954,
      "step": 910
    },
    {
      "epoch": 4.92,
      "grad_norm": 0.8214481472969055,
      "learning_rate": 0.0025401069518716578,
      "loss": 0.3311,
      "step": 920
    },
    {
      "epoch": 4.97,
      "grad_norm": 1.2385145425796509,
      "learning_rate": 0.0025133689839572193,
      "loss": 0.3328,
      "step": 930
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9386682242990654,
      "eval_f1": 0.9316281329929348,
      "eval_loss": 0.17617273330688477,
      "eval_precision": 0.9322615361668551,
      "eval_recall": 0.9371856011394022,
      "eval_runtime": 9.0288,
      "eval_samples_per_second": 189.616,
      "eval_steps_per_second": 11.851,
      "step": 935
    },
    {
      "epoch": 5.03,
      "grad_norm": 0.7902320623397827,
      "learning_rate": 0.002486631016042781,
      "loss": 0.257,
      "step": 940
    },
    {
      "epoch": 5.08,
      "grad_norm": 1.2443559169769287,
      "learning_rate": 0.0024598930481283423,
      "loss": 0.314,
      "step": 950
    },
    {
      "epoch": 5.13,
      "grad_norm": 0.753470778465271,
      "learning_rate": 0.002433155080213904,
      "loss": 0.2539,
      "step": 960
    },
    {
      "epoch": 5.19,
      "grad_norm": 0.9723307490348816,
      "learning_rate": 0.0024064171122994654,
      "loss": 0.2922,
      "step": 970
    },
    {
      "epoch": 5.24,
      "grad_norm": 1.0655038356781006,
      "learning_rate": 0.002379679144385027,
      "loss": 0.2791,
      "step": 980
    },
    {
      "epoch": 5.29,
      "grad_norm": 0.8649442791938782,
      "learning_rate": 0.0023529411764705885,
      "loss": 0.298,
      "step": 990
    },
    {
      "epoch": 5.35,
      "grad_norm": 0.9552505612373352,
      "learning_rate": 0.00232620320855615,
      "loss": 0.2861,
      "step": 1000
    },
    {
      "epoch": 5.4,
      "grad_norm": 0.8958008885383606,
      "learning_rate": 0.0022994652406417115,
      "loss": 0.3015,
      "step": 1010
    },
    {
      "epoch": 5.45,
      "grad_norm": 1.3321876525878906,
      "learning_rate": 0.0022727272727272726,
      "loss": 0.3289,
      "step": 1020
    },
    {
      "epoch": 5.51,
      "grad_norm": 0.8562110066413879,
      "learning_rate": 0.0022459893048128346,
      "loss": 0.3088,
      "step": 1030
    },
    {
      "epoch": 5.56,
      "grad_norm": 1.5215970277786255,
      "learning_rate": 0.0022192513368983957,
      "loss": 0.2998,
      "step": 1040
    },
    {
      "epoch": 5.61,
      "grad_norm": 0.8548377752304077,
      "learning_rate": 0.002192513368983957,
      "loss": 0.2401,
      "step": 1050
    },
    {
      "epoch": 5.67,
      "grad_norm": 0.6302920579910278,
      "learning_rate": 0.0021657754010695187,
      "loss": 0.2492,
      "step": 1060
    },
    {
      "epoch": 5.72,
      "grad_norm": 0.4174397587776184,
      "learning_rate": 0.0021390374331550803,
      "loss": 0.2714,
      "step": 1070
    },
    {
      "epoch": 5.78,
      "grad_norm": 1.0450794696807861,
      "learning_rate": 0.002112299465240642,
      "loss": 0.2855,
      "step": 1080
    },
    {
      "epoch": 5.83,
      "grad_norm": 1.0483543872833252,
      "learning_rate": 0.0020855614973262033,
      "loss": 0.2228,
      "step": 1090
    },
    {
      "epoch": 5.88,
      "grad_norm": 0.9359253644943237,
      "learning_rate": 0.002058823529411765,
      "loss": 0.2784,
      "step": 1100
    },
    {
      "epoch": 5.94,
      "grad_norm": 0.8934263586997986,
      "learning_rate": 0.0020320855614973264,
      "loss": 0.2171,
      "step": 1110
    },
    {
      "epoch": 5.99,
      "grad_norm": 1.1475499868392944,
      "learning_rate": 0.002005347593582888,
      "loss": 0.3138,
      "step": 1120
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9439252336448598,
      "eval_f1": 0.9426316231525895,
      "eval_loss": 0.148016095161438,
      "eval_precision": 0.942094087936167,
      "eval_recall": 0.9482439417517554,
      "eval_runtime": 9.0541,
      "eval_samples_per_second": 189.085,
      "eval_steps_per_second": 11.818,
      "step": 1122
    },
    {
      "epoch": 6.04,
      "grad_norm": 1.3191113471984863,
      "learning_rate": 0.0019786096256684494,
      "loss": 0.3146,
      "step": 1130
    },
    {
      "epoch": 6.1,
      "grad_norm": 0.8933680653572083,
      "learning_rate": 0.0019518716577540108,
      "loss": 0.2226,
      "step": 1140
    },
    {
      "epoch": 6.15,
      "grad_norm": 0.6708208918571472,
      "learning_rate": 0.001925133689839572,
      "loss": 0.2108,
      "step": 1150
    },
    {
      "epoch": 6.2,
      "grad_norm": 0.971500039100647,
      "learning_rate": 0.0018983957219251338,
      "loss": 0.2795,
      "step": 1160
    },
    {
      "epoch": 6.26,
      "grad_norm": 1.081484317779541,
      "learning_rate": 0.0018716577540106951,
      "loss": 0.2544,
      "step": 1170
    },
    {
      "epoch": 6.31,
      "grad_norm": 0.9211081266403198,
      "learning_rate": 0.0018449197860962567,
      "loss": 0.2595,
      "step": 1180
    },
    {
      "epoch": 6.36,
      "grad_norm": 0.7927699685096741,
      "learning_rate": 0.0018181818181818182,
      "loss": 0.2558,
      "step": 1190
    },
    {
      "epoch": 6.42,
      "grad_norm": 0.6074767708778381,
      "learning_rate": 0.0017914438502673797,
      "loss": 0.1803,
      "step": 1200
    },
    {
      "epoch": 6.47,
      "grad_norm": 0.878953754901886,
      "learning_rate": 0.0017647058823529412,
      "loss": 0.2395,
      "step": 1210
    },
    {
      "epoch": 6.52,
      "grad_norm": 0.6277757883071899,
      "learning_rate": 0.0017379679144385028,
      "loss": 0.188,
      "step": 1220
    },
    {
      "epoch": 6.58,
      "grad_norm": 0.7370597124099731,
      "learning_rate": 0.001711229946524064,
      "loss": 0.192,
      "step": 1230
    },
    {
      "epoch": 6.63,
      "grad_norm": 1.1328575611114502,
      "learning_rate": 0.0016844919786096258,
      "loss": 0.2774,
      "step": 1240
    },
    {
      "epoch": 6.68,
      "grad_norm": 0.7046247124671936,
      "learning_rate": 0.0016577540106951871,
      "loss": 0.2984,
      "step": 1250
    },
    {
      "epoch": 6.74,
      "grad_norm": 0.9354172945022583,
      "learning_rate": 0.0016310160427807489,
      "loss": 0.2253,
      "step": 1260
    },
    {
      "epoch": 6.79,
      "grad_norm": 0.9354103803634644,
      "learning_rate": 0.0016042780748663102,
      "loss": 0.2233,
      "step": 1270
    },
    {
      "epoch": 6.84,
      "grad_norm": 1.4302254915237427,
      "learning_rate": 0.0015775401069518715,
      "loss": 0.2252,
      "step": 1280
    },
    {
      "epoch": 6.9,
      "grad_norm": 0.879564642906189,
      "learning_rate": 0.0015508021390374333,
      "loss": 0.2222,
      "step": 1290
    },
    {
      "epoch": 6.95,
      "grad_norm": 0.8771746158599854,
      "learning_rate": 0.0015240641711229946,
      "loss": 0.2489,
      "step": 1300
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9620327102803738,
      "eval_f1": 0.9562861087932668,
      "eval_loss": 0.11337984353303909,
      "eval_precision": 0.9535730521530188,
      "eval_recall": 0.9609340740213044,
      "eval_runtime": 9.0379,
      "eval_samples_per_second": 189.424,
      "eval_steps_per_second": 11.839,
      "step": 1309
    },
    {
      "epoch": 7.01,
      "grad_norm": 1.0121431350708008,
      "learning_rate": 0.001497326203208556,
      "loss": 0.2303,
      "step": 1310
    },
    {
      "epoch": 7.06,
      "grad_norm": 1.2874377965927124,
      "learning_rate": 0.0014705882352941176,
      "loss": 0.2637,
      "step": 1320
    },
    {
      "epoch": 7.11,
      "grad_norm": 0.838621199131012,
      "learning_rate": 0.0014438502673796792,
      "loss": 0.1681,
      "step": 1330
    },
    {
      "epoch": 7.17,
      "grad_norm": 0.7134861946105957,
      "learning_rate": 0.0014171122994652407,
      "loss": 0.2441,
      "step": 1340
    },
    {
      "epoch": 7.22,
      "grad_norm": 1.5448678731918335,
      "learning_rate": 0.0013903743315508022,
      "loss": 0.2167,
      "step": 1350
    },
    {
      "epoch": 7.27,
      "grad_norm": 0.8171320557594299,
      "learning_rate": 0.0013636363636363635,
      "loss": 0.201,
      "step": 1360
    },
    {
      "epoch": 7.33,
      "grad_norm": 0.9818800091743469,
      "learning_rate": 0.0013368983957219253,
      "loss": 0.1853,
      "step": 1370
    },
    {
      "epoch": 7.38,
      "grad_norm": 0.7382510900497437,
      "learning_rate": 0.0013101604278074866,
      "loss": 0.2012,
      "step": 1380
    },
    {
      "epoch": 7.43,
      "grad_norm": 0.9468443393707275,
      "learning_rate": 0.0012834224598930483,
      "loss": 0.1579,
      "step": 1390
    },
    {
      "epoch": 7.49,
      "grad_norm": 0.6972719430923462,
      "learning_rate": 0.0012566844919786096,
      "loss": 0.2077,
      "step": 1400
    },
    {
      "epoch": 7.54,
      "grad_norm": 0.8953404426574707,
      "learning_rate": 0.0012299465240641712,
      "loss": 0.2617,
      "step": 1410
    },
    {
      "epoch": 7.59,
      "grad_norm": 0.9293211102485657,
      "learning_rate": 0.0012032085561497327,
      "loss": 0.2337,
      "step": 1420
    },
    {
      "epoch": 7.65,
      "grad_norm": 0.6336411237716675,
      "learning_rate": 0.0011764705882352942,
      "loss": 0.1855,
      "step": 1430
    },
    {
      "epoch": 7.7,
      "grad_norm": 0.6554710268974304,
      "learning_rate": 0.0011497326203208558,
      "loss": 0.2039,
      "step": 1440
    },
    {
      "epoch": 7.75,
      "grad_norm": 0.725406289100647,
      "learning_rate": 0.0011229946524064173,
      "loss": 0.1857,
      "step": 1450
    },
    {
      "epoch": 7.81,
      "grad_norm": 0.8667876720428467,
      "learning_rate": 0.0010962566844919786,
      "loss": 0.1764,
      "step": 1460
    },
    {
      "epoch": 7.86,
      "grad_norm": 1.1264532804489136,
      "learning_rate": 0.0010695187165775401,
      "loss": 0.2717,
      "step": 1470
    },
    {
      "epoch": 7.91,
      "grad_norm": 1.0109556913375854,
      "learning_rate": 0.0010427807486631017,
      "loss": 0.2283,
      "step": 1480
    },
    {
      "epoch": 7.97,
      "grad_norm": 0.6521192193031311,
      "learning_rate": 0.0010160427807486632,
      "loss": 0.193,
      "step": 1490
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9637850467289719,
      "eval_f1": 0.9615837557171594,
      "eval_loss": 0.10203568637371063,
      "eval_precision": 0.9665540248425233,
      "eval_recall": 0.9580773424505189,
      "eval_runtime": 9.0516,
      "eval_samples_per_second": 189.138,
      "eval_steps_per_second": 11.821,
      "step": 1496
    },
    {
      "epoch": 8.02,
      "grad_norm": 0.7159696221351624,
      "learning_rate": 0.0009893048128342247,
      "loss": 0.2214,
      "step": 1500
    },
    {
      "epoch": 8.07,
      "grad_norm": 0.8673921823501587,
      "learning_rate": 0.000962566844919786,
      "loss": 0.1605,
      "step": 1510
    },
    {
      "epoch": 8.13,
      "grad_norm": 0.8337764143943787,
      "learning_rate": 0.0009358288770053476,
      "loss": 0.1704,
      "step": 1520
    },
    {
      "epoch": 8.18,
      "grad_norm": 0.5427992343902588,
      "learning_rate": 0.0009090909090909091,
      "loss": 0.1598,
      "step": 1530
    },
    {
      "epoch": 8.24,
      "grad_norm": 0.7265269160270691,
      "learning_rate": 0.0008823529411764706,
      "loss": 0.1931,
      "step": 1540
    },
    {
      "epoch": 8.29,
      "grad_norm": 0.8919804692268372,
      "learning_rate": 0.000855614973262032,
      "loss": 0.2435,
      "step": 1550
    },
    {
      "epoch": 8.34,
      "grad_norm": 0.6623568534851074,
      "learning_rate": 0.0008288770053475936,
      "loss": 0.1521,
      "step": 1560
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.7755681872367859,
      "learning_rate": 0.0008021390374331551,
      "loss": 0.2308,
      "step": 1570
    },
    {
      "epoch": 8.45,
      "grad_norm": 0.9359970092773438,
      "learning_rate": 0.0007754010695187166,
      "loss": 0.2103,
      "step": 1580
    },
    {
      "epoch": 8.5,
      "grad_norm": 0.6170040965080261,
      "learning_rate": 0.000748663101604278,
      "loss": 0.1663,
      "step": 1590
    },
    {
      "epoch": 8.56,
      "grad_norm": 0.6797509789466858,
      "learning_rate": 0.0007219251336898396,
      "loss": 0.1701,
      "step": 1600
    },
    {
      "epoch": 8.61,
      "grad_norm": 1.0805569887161255,
      "learning_rate": 0.0006951871657754011,
      "loss": 0.1833,
      "step": 1610
    },
    {
      "epoch": 8.66,
      "grad_norm": 0.6939735412597656,
      "learning_rate": 0.0006684491978609626,
      "loss": 0.1746,
      "step": 1620
    },
    {
      "epoch": 8.72,
      "grad_norm": 0.6343138813972473,
      "learning_rate": 0.0006417112299465242,
      "loss": 0.1686,
      "step": 1630
    },
    {
      "epoch": 8.77,
      "grad_norm": 0.9811675548553467,
      "learning_rate": 0.0006149732620320856,
      "loss": 0.1746,
      "step": 1640
    },
    {
      "epoch": 8.82,
      "grad_norm": 0.573733389377594,
      "learning_rate": 0.0005882352941176471,
      "loss": 0.1846,
      "step": 1650
    },
    {
      "epoch": 8.88,
      "grad_norm": 0.8457497358322144,
      "learning_rate": 0.0005614973262032086,
      "loss": 0.2011,
      "step": 1660
    },
    {
      "epoch": 8.93,
      "grad_norm": 0.8137268424034119,
      "learning_rate": 0.0005347593582887701,
      "loss": 0.1835,
      "step": 1670
    },
    {
      "epoch": 8.98,
      "grad_norm": 0.8221555352210999,
      "learning_rate": 0.0005080213903743316,
      "loss": 0.1973,
      "step": 1680
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9748831775700935,
      "eval_f1": 0.9743246307049778,
      "eval_loss": 0.07539471238851547,
      "eval_precision": 0.9732729615486463,
      "eval_recall": 0.9761282658354655,
      "eval_runtime": 9.0508,
      "eval_samples_per_second": 189.155,
      "eval_steps_per_second": 11.822,
      "step": 1683
    },
    {
      "epoch": 9.04,
      "grad_norm": 0.5439435839653015,
      "learning_rate": 0.000481283422459893,
      "loss": 0.1444,
      "step": 1690
    },
    {
      "epoch": 9.09,
      "grad_norm": 0.6913427710533142,
      "learning_rate": 0.00045454545454545455,
      "loss": 0.1809,
      "step": 1700
    },
    {
      "epoch": 9.14,
      "grad_norm": 0.7303802371025085,
      "learning_rate": 0.000427807486631016,
      "loss": 0.1396,
      "step": 1710
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.523857057094574,
      "learning_rate": 0.00040106951871657755,
      "loss": 0.174,
      "step": 1720
    },
    {
      "epoch": 9.25,
      "grad_norm": 0.6848942041397095,
      "learning_rate": 0.000374331550802139,
      "loss": 0.1923,
      "step": 1730
    },
    {
      "epoch": 9.3,
      "grad_norm": 0.5525270104408264,
      "learning_rate": 0.00034759358288770055,
      "loss": 0.1438,
      "step": 1740
    },
    {
      "epoch": 9.36,
      "grad_norm": 0.802334725856781,
      "learning_rate": 0.0003208556149732621,
      "loss": 0.1733,
      "step": 1750
    },
    {
      "epoch": 9.41,
      "grad_norm": 0.6787207722663879,
      "learning_rate": 0.00029411764705882356,
      "loss": 0.1637,
      "step": 1760
    },
    {
      "epoch": 9.47,
      "grad_norm": 0.8829286098480225,
      "learning_rate": 0.00026737967914438503,
      "loss": 0.1651,
      "step": 1770
    },
    {
      "epoch": 9.52,
      "grad_norm": 0.6158820986747742,
      "learning_rate": 0.0002406417112299465,
      "loss": 0.1969,
      "step": 1780
    },
    {
      "epoch": 9.57,
      "grad_norm": 0.6652956604957581,
      "learning_rate": 0.000213903743315508,
      "loss": 0.1296,
      "step": 1790
    },
    {
      "epoch": 9.63,
      "grad_norm": 0.4137950539588928,
      "learning_rate": 0.0001871657754010695,
      "loss": 0.141,
      "step": 1800
    },
    {
      "epoch": 9.68,
      "grad_norm": 0.6831213235855103,
      "learning_rate": 0.00016042780748663104,
      "loss": 0.1739,
      "step": 1810
    },
    {
      "epoch": 9.73,
      "grad_norm": 0.6022053956985474,
      "learning_rate": 0.00013368983957219252,
      "loss": 0.1215,
      "step": 1820
    },
    {
      "epoch": 9.79,
      "grad_norm": 0.5832372307777405,
      "learning_rate": 0.000106951871657754,
      "loss": 0.1921,
      "step": 1830
    },
    {
      "epoch": 9.84,
      "grad_norm": 0.5527146458625793,
      "learning_rate": 8.021390374331552e-05,
      "loss": 0.1405,
      "step": 1840
    },
    {
      "epoch": 9.89,
      "grad_norm": 0.8569141030311584,
      "learning_rate": 5.3475935828877e-05,
      "loss": 0.1398,
      "step": 1850
    },
    {
      "epoch": 9.95,
      "grad_norm": 0.37496665120124817,
      "learning_rate": 2.67379679144385e-05,
      "loss": 0.1351,
      "step": 1860
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.0200737714767456,
      "learning_rate": 0.0,
      "loss": 0.1711,
      "step": 1870
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.981892523364486,
      "eval_f1": 0.9824644070672106,
      "eval_loss": 0.05325188860297203,
      "eval_precision": 0.982613511226295,
      "eval_recall": 0.9823689555008165,
      "eval_runtime": 9.0633,
      "eval_samples_per_second": 188.895,
      "eval_steps_per_second": 11.806,
      "step": 1870
    },
    {
      "epoch": 10.0,
      "step": 1870,
      "total_flos": 9.332136680499118e+18,
      "train_loss": 0.3326003640093268,
      "train_runtime": 1377.1458,
      "train_samples_per_second": 86.839,
      "train_steps_per_second": 1.358
    }
  ],
  "logging_steps": 10,
  "max_steps": 1870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 9.332136680499118e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}