{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.993162393162393,
  "eval_steps": 500,
  "global_step": 1752,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 0.9912007491850634,
      "learning_rate": 5e-06,
      "loss": 0.7548,
      "step": 10
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 0.8120341080388481,
      "learning_rate": 5e-06,
      "loss": 0.6988,
      "step": 20
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.9144364506308376,
      "learning_rate": 5e-06,
      "loss": 0.68,
      "step": 30
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 0.8778720973960674,
      "learning_rate": 5e-06,
      "loss": 0.6798,
      "step": 40
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.8083687880277666,
      "learning_rate": 5e-06,
      "loss": 0.6757,
      "step": 50
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.6856245947077141,
      "learning_rate": 5e-06,
      "loss": 0.6555,
      "step": 60
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 0.4549134078131556,
      "learning_rate": 5e-06,
      "loss": 0.6528,
      "step": 70
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.38149974370876494,
      "learning_rate": 5e-06,
      "loss": 0.6557,
      "step": 80
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.31780767590815034,
      "learning_rate": 5e-06,
      "loss": 0.6398,
      "step": 90
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.2979038503551664,
      "learning_rate": 5e-06,
      "loss": 0.6414,
      "step": 100
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.34299995442682374,
      "learning_rate": 5e-06,
      "loss": 0.6326,
      "step": 110
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.31224439631858925,
      "learning_rate": 5e-06,
      "loss": 0.6411,
      "step": 120
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2872702884170918,
      "learning_rate": 5e-06,
      "loss": 0.6421,
      "step": 130
    },
    {
      "epoch": 0.3190883190883191,
      "grad_norm": 0.31843610582508325,
      "learning_rate": 5e-06,
      "loss": 0.6441,
      "step": 140
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.31677020367403513,
      "learning_rate": 5e-06,
      "loss": 0.6369,
      "step": 150
    },
    {
      "epoch": 0.3646723646723647,
      "grad_norm": 0.30778519805576754,
      "learning_rate": 5e-06,
      "loss": 0.6423,
      "step": 160
    },
    {
      "epoch": 0.38746438746438744,
      "grad_norm": 0.3520973006350889,
      "learning_rate": 5e-06,
      "loss": 0.6333,
      "step": 170
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3024095360698375,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 180
    },
    {
      "epoch": 0.43304843304843305,
      "grad_norm": 0.306683195208484,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 190
    },
    {
      "epoch": 0.45584045584045585,
      "grad_norm": 0.3028828247046378,
      "learning_rate": 5e-06,
      "loss": 0.6397,
      "step": 200
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.3090017394413483,
      "learning_rate": 5e-06,
      "loss": 0.6356,
      "step": 210
    },
    {
      "epoch": 0.5014245014245015,
      "grad_norm": 0.29949977441022513,
      "learning_rate": 5e-06,
      "loss": 0.6397,
      "step": 220
    },
    {
      "epoch": 0.5242165242165242,
      "grad_norm": 0.32419318781752016,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.2983992630345295,
      "learning_rate": 5e-06,
      "loss": 0.6311,
      "step": 240
    },
    {
      "epoch": 0.5698005698005698,
      "grad_norm": 0.3388064649445867,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 250
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.30378675945812544,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 260
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3118605836030505,
      "learning_rate": 5e-06,
      "loss": 0.6314,
      "step": 270
    },
    {
      "epoch": 0.6381766381766382,
      "grad_norm": 0.3185910877256985,
      "learning_rate": 5e-06,
      "loss": 0.6427,
      "step": 280
    },
    {
      "epoch": 0.6609686609686609,
      "grad_norm": 0.3238612685790961,
      "learning_rate": 5e-06,
      "loss": 0.6308,
      "step": 290
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2910572930554487,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7065527065527065,
      "grad_norm": 0.2961577217293602,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 310
    },
    {
      "epoch": 0.7293447293447294,
      "grad_norm": 0.347125995352574,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 320
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.3017718885104704,
      "learning_rate": 5e-06,
      "loss": 0.626,
      "step": 330
    },
    {
      "epoch": 0.7749287749287749,
      "grad_norm": 0.32719242803351367,
      "learning_rate": 5e-06,
      "loss": 0.6319,
      "step": 340
    },
    {
      "epoch": 0.7977207977207977,
      "grad_norm": 0.3355483959267454,
      "learning_rate": 5e-06,
      "loss": 0.6392,
      "step": 350
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.31827824902748364,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 360
    },
    {
      "epoch": 0.8433048433048433,
      "grad_norm": 0.32626776608416697,
      "learning_rate": 5e-06,
      "loss": 0.6245,
      "step": 370
    },
    {
      "epoch": 0.8660968660968661,
      "grad_norm": 0.31292644377425555,
      "learning_rate": 5e-06,
      "loss": 0.6367,
      "step": 380
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.32907302888237766,
      "learning_rate": 5e-06,
      "loss": 0.6353,
      "step": 390
    },
    {
      "epoch": 0.9116809116809117,
      "grad_norm": 0.29588853416504324,
      "learning_rate": 5e-06,
      "loss": 0.6387,
      "step": 400
    },
    {
      "epoch": 0.9344729344729344,
      "grad_norm": 0.28565869479324607,
      "learning_rate": 5e-06,
      "loss": 0.6346,
      "step": 410
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.30338812600636667,
      "learning_rate": 5e-06,
      "loss": 0.6216,
      "step": 420
    },
    {
      "epoch": 0.98005698005698,
      "grad_norm": 0.3526849426643039,
      "learning_rate": 5e-06,
      "loss": 0.6343,
      "step": 430
    },
    {
      "epoch": 0.9982905982905983,
      "eval_loss": 0.6251307129859924,
      "eval_runtime": 223.0,
      "eval_samples_per_second": 53.018,
      "eval_steps_per_second": 0.417,
      "step": 438
    },
    {
      "epoch": 1.002849002849003,
      "grad_norm": 0.3525041598672024,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 440
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.3088212010408478,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 450
    },
    {
      "epoch": 1.0484330484330484,
      "grad_norm": 0.3048735024737802,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 460
    },
    {
      "epoch": 1.0712250712250713,
      "grad_norm": 0.30395209418239993,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 470
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.3224872071873683,
      "learning_rate": 5e-06,
      "loss": 0.6052,
      "step": 480
    },
    {
      "epoch": 1.1168091168091168,
      "grad_norm": 0.31440242200972873,
      "learning_rate": 5e-06,
      "loss": 0.6086,
      "step": 490
    },
    {
      "epoch": 1.1396011396011396,
      "grad_norm": 0.29525108520793303,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 500
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.32620379296750857,
      "learning_rate": 5e-06,
      "loss": 0.5968,
      "step": 510
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.30445507629744495,
      "learning_rate": 5e-06,
      "loss": 0.6017,
      "step": 520
    },
    {
      "epoch": 1.207977207977208,
      "grad_norm": 0.2989183656534176,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 530
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.2895135488724733,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 540
    },
    {
      "epoch": 1.2535612535612537,
      "grad_norm": 0.33760774288876744,
      "learning_rate": 5e-06,
      "loss": 0.604,
      "step": 550
    },
    {
      "epoch": 1.2763532763532763,
      "grad_norm": 0.3106514910309685,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 560
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.2931272749092201,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 570
    },
    {
      "epoch": 1.3219373219373218,
      "grad_norm": 0.27937877406216316,
      "learning_rate": 5e-06,
      "loss": 0.5984,
      "step": 580
    },
    {
      "epoch": 1.3447293447293447,
      "grad_norm": 0.2780566360895875,
      "learning_rate": 5e-06,
      "loss": 0.5947,
      "step": 590
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.338396436099565,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 600
    },
    {
      "epoch": 1.3903133903133904,
      "grad_norm": 0.3388673486546411,
      "learning_rate": 5e-06,
      "loss": 0.6,
      "step": 610
    },
    {
      "epoch": 1.413105413105413,
      "grad_norm": 0.2960462008725661,
      "learning_rate": 5e-06,
      "loss": 0.6048,
      "step": 620
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.31261947283205377,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 630
    },
    {
      "epoch": 1.4586894586894588,
      "grad_norm": 0.31540213681546253,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 640
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.3011418333363954,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 650
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.29770496669495466,
      "learning_rate": 5e-06,
      "loss": 0.5953,
      "step": 660
    },
    {
      "epoch": 1.5270655270655271,
      "grad_norm": 0.3227357467535432,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 670
    },
    {
      "epoch": 1.54985754985755,
      "grad_norm": 0.2926461969068394,
      "learning_rate": 5e-06,
      "loss": 0.5924,
      "step": 680
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.3151144341930611,
      "learning_rate": 5e-06,
      "loss": 0.5932,
      "step": 690
    },
    {
      "epoch": 1.5954415954415955,
      "grad_norm": 0.28487938842896926,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 700
    },
    {
      "epoch": 1.618233618233618,
      "grad_norm": 0.30356180399923843,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 710
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.2856653342858608,
      "learning_rate": 5e-06,
      "loss": 0.6005,
      "step": 720
    },
    {
      "epoch": 1.6638176638176638,
      "grad_norm": 0.34957562019945143,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 730
    },
    {
      "epoch": 1.6866096866096867,
      "grad_norm": 0.3269288669640998,
      "learning_rate": 5e-06,
      "loss": 0.5939,
      "step": 740
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.30774086259571193,
      "learning_rate": 5e-06,
      "loss": 0.5958,
      "step": 750
    },
    {
      "epoch": 1.7321937321937322,
      "grad_norm": 0.296846543928719,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 760
    },
    {
      "epoch": 1.7549857549857548,
      "grad_norm": 0.2981885551582998,
      "learning_rate": 5e-06,
      "loss": 0.593,
      "step": 770
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.31214489545002166,
      "learning_rate": 5e-06,
      "loss": 0.6025,
      "step": 780
    },
    {
      "epoch": 1.8005698005698005,
      "grad_norm": 0.3192140300099497,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 790
    },
    {
      "epoch": 1.8233618233618234,
      "grad_norm": 0.32130945178436227,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 800
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.3148559521921556,
      "learning_rate": 5e-06,
      "loss": 0.5904,
      "step": 810
    },
    {
      "epoch": 1.868945868945869,
      "grad_norm": 0.3112411609133845,
      "learning_rate": 5e-06,
      "loss": 0.5917,
      "step": 820
    },
    {
      "epoch": 1.8917378917378918,
      "grad_norm": 0.3161978881525877,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 830
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.31432684111426584,
      "learning_rate": 5e-06,
      "loss": 0.5989,
      "step": 840
    },
    {
      "epoch": 1.9373219373219372,
      "grad_norm": 0.2968776393628373,
      "learning_rate": 5e-06,
      "loss": 0.5991,
      "step": 850
    },
    {
      "epoch": 1.96011396011396,
      "grad_norm": 0.30501940664641986,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 860
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.34243750839103754,
      "learning_rate": 5e-06,
      "loss": 0.5965,
      "step": 870
    },
    {
      "epoch": 1.998860398860399,
      "eval_loss": 0.6187237501144409,
      "eval_runtime": 223.8992,
      "eval_samples_per_second": 52.805,
      "eval_steps_per_second": 0.415,
      "step": 877
    },
    {
      "epoch": 2.005698005698006,
      "grad_norm": 0.3076552665931079,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 880
    },
    {
      "epoch": 2.0284900284900287,
      "grad_norm": 0.316707349656788,
      "learning_rate": 5e-06,
      "loss": 0.5544,
      "step": 890
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.314619421056384,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 900
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.3676853811483963,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 910
    },
    {
      "epoch": 2.096866096866097,
      "grad_norm": 0.3405104791289966,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 920
    },
    {
      "epoch": 2.1196581196581197,
      "grad_norm": 0.30588234453097496,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 930
    },
    {
      "epoch": 2.1424501424501425,
      "grad_norm": 0.3159010620787154,
      "learning_rate": 5e-06,
      "loss": 0.565,
      "step": 940
    },
    {
      "epoch": 2.1652421652421654,
      "grad_norm": 0.31276096665138237,
      "learning_rate": 5e-06,
      "loss": 0.5637,
      "step": 950
    },
    {
      "epoch": 2.1880341880341883,
      "grad_norm": 0.32793772773197,
      "learning_rate": 5e-06,
      "loss": 0.569,
      "step": 960
    },
    {
      "epoch": 2.2108262108262107,
      "grad_norm": 0.3039440121244138,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 970
    },
    {
      "epoch": 2.2336182336182335,
      "grad_norm": 0.29684753392141544,
      "learning_rate": 5e-06,
      "loss": 0.5615,
      "step": 980
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.30214100814674827,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 990
    },
    {
      "epoch": 2.2792022792022792,
      "grad_norm": 0.3283314542723796,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1000
    },
    {
      "epoch": 2.301994301994302,
      "grad_norm": 0.28655825406701363,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 1010
    },
    {
      "epoch": 2.324786324786325,
      "grad_norm": 0.3172763262482182,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 1020
    },
    {
      "epoch": 2.347578347578348,
      "grad_norm": 0.29685961712777825,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 1030
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3083523951805142,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 1040
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 0.30997548246110007,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 1050
    },
    {
      "epoch": 2.415954415954416,
      "grad_norm": 0.30789457003363374,
      "learning_rate": 5e-06,
      "loss": 0.5774,
      "step": 1060
    },
    {
      "epoch": 2.438746438746439,
      "grad_norm": 0.34506757910084734,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 1070
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.29907001031582975,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 1080
    },
    {
      "epoch": 2.484330484330484,
      "grad_norm": 0.3061615554843654,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 1090
    },
    {
      "epoch": 2.5071225071225074,
      "grad_norm": 0.3222138386350068,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 1100
    },
    {
      "epoch": 2.52991452991453,
      "grad_norm": 0.3080789218888492,
      "learning_rate": 5e-06,
      "loss": 0.5715,
      "step": 1110
    },
    {
      "epoch": 2.5527065527065527,
      "grad_norm": 0.29258951587176035,
      "learning_rate": 5e-06,
      "loss": 0.5685,
      "step": 1120
    },
    {
      "epoch": 2.5754985754985755,
      "grad_norm": 0.3281842313884605,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 1130
    },
    {
      "epoch": 2.5982905982905984,
      "grad_norm": 0.29411671998782135,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 1140
    },
    {
      "epoch": 2.6210826210826212,
      "grad_norm": 0.29959622578924333,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 1150
    },
    {
      "epoch": 2.6438746438746437,
      "grad_norm": 0.30740185285745697,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 1160
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.2839640105696346,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 1170
    },
    {
      "epoch": 2.6894586894586894,
      "grad_norm": 0.2896360639343294,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 1180
    },
    {
      "epoch": 2.7122507122507122,
      "grad_norm": 0.3247548012145319,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 1190
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 0.29034523418069846,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 1200
    },
    {
      "epoch": 2.757834757834758,
      "grad_norm": 0.2853110947522709,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 1210
    },
    {
      "epoch": 2.780626780626781,
      "grad_norm": 0.2828550287829409,
      "learning_rate": 5e-06,
      "loss": 0.5641,
      "step": 1220
    },
    {
      "epoch": 2.8034188034188032,
      "grad_norm": 0.2979901647854109,
      "learning_rate": 5e-06,
      "loss": 0.5652,
      "step": 1230
    },
    {
      "epoch": 2.826210826210826,
      "grad_norm": 0.29825085966088555,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 1240
    },
    {
      "epoch": 2.849002849002849,
      "grad_norm": 0.29169708831163993,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 1250
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.2972957929068833,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 1260
    },
    {
      "epoch": 2.8945868945868947,
      "grad_norm": 0.31082071951469487,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 1270
    },
    {
      "epoch": 2.9173789173789175,
      "grad_norm": 0.2900888035317228,
      "learning_rate": 5e-06,
      "loss": 0.5623,
      "step": 1280
    },
    {
      "epoch": 2.9401709401709404,
      "grad_norm": 0.3110544935430418,
      "learning_rate": 5e-06,
      "loss": 0.5648,
      "step": 1290
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.31392258075162666,
      "learning_rate": 5e-06,
      "loss": 0.5653,
      "step": 1300
    },
    {
      "epoch": 2.9857549857549857,
      "grad_norm": 0.31856046416041095,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 1310
    },
    {
      "epoch": 2.9994301994301993,
      "eval_loss": 0.6185686588287354,
      "eval_runtime": 222.7671,
      "eval_samples_per_second": 53.073,
      "eval_steps_per_second": 0.417,
      "step": 1316
    },
    {
      "epoch": 3.0085470085470085,
      "grad_norm": 0.3351007793036639,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 1320
    },
    {
      "epoch": 3.0313390313390314,
      "grad_norm": 0.3019286650434241,
      "learning_rate": 5e-06,
      "loss": 0.5399,
      "step": 1330
    },
    {
      "epoch": 3.0541310541310542,
      "grad_norm": 0.3439158785823229,
      "learning_rate": 5e-06,
      "loss": 0.5394,
      "step": 1340
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.3374532391642498,
      "learning_rate": 5e-06,
      "loss": 0.5432,
      "step": 1350
    },
    {
      "epoch": 3.0997150997150995,
      "grad_norm": 0.2989682915138886,
      "learning_rate": 5e-06,
      "loss": 0.5376,
      "step": 1360
    },
    {
      "epoch": 3.1225071225071224,
      "grad_norm": 0.2963980039357649,
      "learning_rate": 5e-06,
      "loss": 0.5395,
      "step": 1370
    },
    {
      "epoch": 3.1452991452991452,
      "grad_norm": 0.2937114794782103,
      "learning_rate": 5e-06,
      "loss": 0.5394,
      "step": 1380
    },
    {
      "epoch": 3.168091168091168,
      "grad_norm": 0.29626505292683575,
      "learning_rate": 5e-06,
      "loss": 0.5389,
      "step": 1390
    },
    {
      "epoch": 3.190883190883191,
      "grad_norm": 0.30686647691318353,
      "learning_rate": 5e-06,
      "loss": 0.5339,
      "step": 1400
    },
    {
      "epoch": 3.213675213675214,
      "grad_norm": 0.28513483825993924,
      "learning_rate": 5e-06,
      "loss": 0.5374,
      "step": 1410
    },
    {
      "epoch": 3.2364672364672367,
      "grad_norm": 0.32112984492909513,
      "learning_rate": 5e-06,
      "loss": 0.5466,
      "step": 1420
    },
    {
      "epoch": 3.259259259259259,
      "grad_norm": 0.28822837064728235,
      "learning_rate": 5e-06,
      "loss": 0.5474,
      "step": 1430
    },
    {
      "epoch": 3.282051282051282,
      "grad_norm": 0.3185576111825181,
      "learning_rate": 5e-06,
      "loss": 0.5366,
      "step": 1440
    },
    {
      "epoch": 3.304843304843305,
      "grad_norm": 0.2792872891044498,
      "learning_rate": 5e-06,
      "loss": 0.5362,
      "step": 1450
    },
    {
      "epoch": 3.3276353276353277,
      "grad_norm": 0.29995676319638775,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 1460
    },
    {
      "epoch": 3.3504273504273505,
      "grad_norm": 0.2920803607745571,
      "learning_rate": 5e-06,
      "loss": 0.5421,
      "step": 1470
    },
    {
      "epoch": 3.3732193732193734,
      "grad_norm": 0.3432358333663625,
      "learning_rate": 5e-06,
      "loss": 0.5438,
      "step": 1480
    },
    {
      "epoch": 3.396011396011396,
      "grad_norm": 0.2917134971418762,
      "learning_rate": 5e-06,
      "loss": 0.5382,
      "step": 1490
    },
    {
      "epoch": 3.4188034188034186,
      "grad_norm": 0.30814260872698784,
      "learning_rate": 5e-06,
      "loss": 0.5395,
      "step": 1500
    },
    {
      "epoch": 3.4415954415954415,
      "grad_norm": 0.28877135275478877,
      "learning_rate": 5e-06,
      "loss": 0.5446,
      "step": 1510
    },
    {
      "epoch": 3.4643874643874644,
      "grad_norm": 0.29391852963248044,
      "learning_rate": 5e-06,
      "loss": 0.538,
      "step": 1520
    },
    {
      "epoch": 3.4871794871794872,
      "grad_norm": 0.2934166080799258,
      "learning_rate": 5e-06,
      "loss": 0.5501,
      "step": 1530
    },
    {
      "epoch": 3.50997150997151,
      "grad_norm": 0.31731681904845593,
      "learning_rate": 5e-06,
      "loss": 0.5469,
      "step": 1540
    },
    {
      "epoch": 3.532763532763533,
      "grad_norm": 0.3057350977648524,
      "learning_rate": 5e-06,
      "loss": 0.5426,
      "step": 1550
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.3141703306612959,
      "learning_rate": 5e-06,
      "loss": 0.5441,
      "step": 1560
    },
    {
      "epoch": 3.578347578347578,
      "grad_norm": 0.30598298352967457,
      "learning_rate": 5e-06,
      "loss": 0.5475,
      "step": 1570
    },
    {
      "epoch": 3.601139601139601,
      "grad_norm": 0.28570732113004244,
      "learning_rate": 5e-06,
      "loss": 0.5438,
      "step": 1580
    },
    {
      "epoch": 3.623931623931624,
      "grad_norm": 0.29764587818834687,
      "learning_rate": 5e-06,
      "loss": 0.5405,
      "step": 1590
    },
    {
      "epoch": 3.646723646723647,
      "grad_norm": 0.30126884574280993,
      "learning_rate": 5e-06,
      "loss": 0.5365,
      "step": 1600
    },
    {
      "epoch": 3.6695156695156697,
      "grad_norm": 0.2855847909256962,
      "learning_rate": 5e-06,
      "loss": 0.5403,
      "step": 1610
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.2926291093654215,
      "learning_rate": 5e-06,
      "loss": 0.5446,
      "step": 1620
    },
    {
      "epoch": 3.715099715099715,
      "grad_norm": 0.30082477661083823,
      "learning_rate": 5e-06,
      "loss": 0.5425,
      "step": 1630
    },
    {
      "epoch": 3.737891737891738,
      "grad_norm": 0.3371570347062514,
      "learning_rate": 5e-06,
      "loss": 0.5397,
      "step": 1640
    },
    {
      "epoch": 3.7606837606837606,
      "grad_norm": 0.3105947434754125,
      "learning_rate": 5e-06,
      "loss": 0.5533,
      "step": 1650
    },
    {
      "epoch": 3.7834757834757835,
      "grad_norm": 0.316609957936053,
      "learning_rate": 5e-06,
      "loss": 0.5382,
      "step": 1660
    },
    {
      "epoch": 3.8062678062678064,
      "grad_norm": 0.29097493899738613,
      "learning_rate": 5e-06,
      "loss": 0.5495,
      "step": 1670
    },
    {
      "epoch": 3.8290598290598292,
      "grad_norm": 0.29269233881195844,
      "learning_rate": 5e-06,
      "loss": 0.544,
      "step": 1680
    },
    {
      "epoch": 3.851851851851852,
      "grad_norm": 0.26939440151127303,
      "learning_rate": 5e-06,
      "loss": 0.5449,
      "step": 1690
    },
    {
      "epoch": 3.8746438746438745,
      "grad_norm": 0.28613738234540304,
      "learning_rate": 5e-06,
      "loss": 0.5435,
      "step": 1700
    },
    {
      "epoch": 3.8974358974358974,
      "grad_norm": 0.28520024092833124,
      "learning_rate": 5e-06,
      "loss": 0.5482,
      "step": 1710
    },
    {
      "epoch": 3.92022792022792,
      "grad_norm": 0.2957727419479367,
      "learning_rate": 5e-06,
      "loss": 0.5476,
      "step": 1720
    },
    {
      "epoch": 3.943019943019943,
      "grad_norm": 0.2926051428617584,
      "learning_rate": 5e-06,
      "loss": 0.5534,
      "step": 1730
    },
    {
      "epoch": 3.965811965811966,
      "grad_norm": 0.27352601542002747,
      "learning_rate": 5e-06,
      "loss": 0.5475,
      "step": 1740
    },
    {
      "epoch": 3.9886039886039883,
      "grad_norm": 0.2921116881599489,
      "learning_rate": 5e-06,
      "loss": 0.549,
      "step": 1750
    },
    {
      "epoch": 3.993162393162393,
      "eval_loss": 0.6236439347267151,
      "eval_runtime": 223.2896,
      "eval_samples_per_second": 52.949,
      "eval_steps_per_second": 0.416,
      "step": 1752
    },
    {
      "epoch": 3.993162393162393,
      "step": 1752,
      "total_flos": 3673450900094976.0,
      "train_loss": 0.5887784766688194,
      "train_runtime": 47860.2816,
      "train_samples_per_second": 18.773,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 10,
  "max_steps": 1752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3673450900094976.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}