{
  "best_metric": 1.4315598011016846,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07202016564638099,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036010082823190496,
      "grad_norm": 0.7863615155220032,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2713,
      "step": 1
    },
    {
      "epoch": 0.00036010082823190496,
      "eval_loss": 1.800669550895691,
      "eval_runtime": 350.5123,
      "eval_samples_per_second": 13.343,
      "eval_steps_per_second": 3.338,
      "step": 1
    },
    {
      "epoch": 0.0007202016564638099,
      "grad_norm": 0.915640115737915,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2562,
      "step": 2
    },
    {
      "epoch": 0.0010803024846957148,
      "grad_norm": 0.8614652156829834,
      "learning_rate": 2.4e-05,
      "loss": 1.1652,
      "step": 3
    },
    {
      "epoch": 0.0014404033129276198,
      "grad_norm": 0.8120066523551941,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.1665,
      "step": 4
    },
    {
      "epoch": 0.0018005041411595247,
      "grad_norm": 0.8058522939682007,
      "learning_rate": 4e-05,
      "loss": 1.1652,
      "step": 5
    },
    {
      "epoch": 0.0021606049693914295,
      "grad_norm": 0.7672634124755859,
      "learning_rate": 4.8e-05,
      "loss": 1.1551,
      "step": 6
    },
    {
      "epoch": 0.0025207057976233344,
      "grad_norm": 0.6031802296638489,
      "learning_rate": 5.6e-05,
      "loss": 1.0732,
      "step": 7
    },
    {
      "epoch": 0.0028808066258552397,
      "grad_norm": 0.4752897322177887,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.1206,
      "step": 8
    },
    {
      "epoch": 0.0032409074540871445,
      "grad_norm": 0.39508315920829773,
      "learning_rate": 7.2e-05,
      "loss": 1.0632,
      "step": 9
    },
    {
      "epoch": 0.0036010082823190494,
      "grad_norm": 0.38076189160346985,
      "learning_rate": 8e-05,
      "loss": 1.2369,
      "step": 10
    },
    {
      "epoch": 0.003961109110550955,
      "grad_norm": 0.40446725487709045,
      "learning_rate": 7.999453219969877e-05,
      "loss": 1.1194,
      "step": 11
    },
    {
      "epoch": 0.004321209938782859,
      "grad_norm": 0.4369296729564667,
      "learning_rate": 7.997813029363704e-05,
      "loss": 1.0702,
      "step": 12
    },
    {
      "epoch": 0.004681310767014764,
      "grad_norm": 0.41360488533973694,
      "learning_rate": 7.99507987659322e-05,
      "loss": 1.0601,
      "step": 13
    },
    {
      "epoch": 0.005041411595246669,
      "grad_norm": 0.38158196210861206,
      "learning_rate": 7.991254508875098e-05,
      "loss": 1.0773,
      "step": 14
    },
    {
      "epoch": 0.005401512423478574,
      "grad_norm": 0.4101528525352478,
      "learning_rate": 7.98633797202668e-05,
      "loss": 1.0604,
      "step": 15
    },
    {
      "epoch": 0.005761613251710479,
      "grad_norm": 0.4122559130191803,
      "learning_rate": 7.980331610180046e-05,
      "loss": 1.2719,
      "step": 16
    },
    {
      "epoch": 0.006121714079942384,
      "grad_norm": 0.34931090474128723,
      "learning_rate": 7.973237065414553e-05,
      "loss": 1.2838,
      "step": 17
    },
    {
      "epoch": 0.006481814908174289,
      "grad_norm": 0.38246577978134155,
      "learning_rate": 7.965056277307902e-05,
      "loss": 1.1784,
      "step": 18
    },
    {
      "epoch": 0.0068419157364061935,
      "grad_norm": 0.3690750300884247,
      "learning_rate": 7.955791482405875e-05,
      "loss": 1.2598,
      "step": 19
    },
    {
      "epoch": 0.007202016564638099,
      "grad_norm": 0.4142758548259735,
      "learning_rate": 7.94544521361089e-05,
      "loss": 1.3088,
      "step": 20
    },
    {
      "epoch": 0.007562117392870004,
      "grad_norm": 0.43574273586273193,
      "learning_rate": 7.93402029948953e-05,
      "loss": 1.5369,
      "step": 21
    },
    {
      "epoch": 0.00792221822110191,
      "grad_norm": 0.37755557894706726,
      "learning_rate": 7.921519863499239e-05,
      "loss": 1.2371,
      "step": 22
    },
    {
      "epoch": 0.008282319049333813,
      "grad_norm": 0.361796110868454,
      "learning_rate": 7.907947323134398e-05,
      "loss": 1.2302,
      "step": 23
    },
    {
      "epoch": 0.008642419877565718,
      "grad_norm": 0.416102796792984,
      "learning_rate": 7.893306388992023e-05,
      "loss": 1.412,
      "step": 24
    },
    {
      "epoch": 0.009002520705797623,
      "grad_norm": 0.4576001763343811,
      "learning_rate": 7.877601063757323e-05,
      "loss": 1.4526,
      "step": 25
    },
    {
      "epoch": 0.009362621534029529,
      "grad_norm": 0.4764253497123718,
      "learning_rate": 7.860835641109395e-05,
      "loss": 1.5504,
      "step": 26
    },
    {
      "epoch": 0.009722722362261434,
      "grad_norm": 0.45336440205574036,
      "learning_rate": 7.843014704547393e-05,
      "loss": 1.5157,
      "step": 27
    },
    {
      "epoch": 0.010082823190493338,
      "grad_norm": 0.4694438576698303,
      "learning_rate": 7.824143126137431e-05,
      "loss": 1.4271,
      "step": 28
    },
    {
      "epoch": 0.010442924018725243,
      "grad_norm": 0.4710056185722351,
      "learning_rate": 7.804226065180615e-05,
      "loss": 1.596,
      "step": 29
    },
    {
      "epoch": 0.010803024846957148,
      "grad_norm": 0.4954136610031128,
      "learning_rate": 7.783268966802539e-05,
      "loss": 1.6747,
      "step": 30
    },
    {
      "epoch": 0.011163125675189053,
      "grad_norm": 0.5075744390487671,
      "learning_rate": 7.761277560464645e-05,
      "loss": 1.6001,
      "step": 31
    },
    {
      "epoch": 0.011523226503420959,
      "grad_norm": 0.5597767233848572,
      "learning_rate": 7.738257858397844e-05,
      "loss": 1.6792,
      "step": 32
    },
    {
      "epoch": 0.011883327331652862,
      "grad_norm": 0.5473968982696533,
      "learning_rate": 7.71421615395883e-05,
      "loss": 1.5957,
      "step": 33
    },
    {
      "epoch": 0.012243428159884768,
      "grad_norm": 0.628345787525177,
      "learning_rate": 7.68915901990954e-05,
      "loss": 1.8923,
      "step": 34
    },
    {
      "epoch": 0.012603528988116673,
      "grad_norm": 0.6227551698684692,
      "learning_rate": 7.663093306620231e-05,
      "loss": 1.724,
      "step": 35
    },
    {
      "epoch": 0.012963629816348578,
      "grad_norm": 0.6094886064529419,
      "learning_rate": 7.636026140196651e-05,
      "loss": 1.888,
      "step": 36
    },
    {
      "epoch": 0.013323730644580483,
      "grad_norm": 0.657168984413147,
      "learning_rate": 7.607964920531837e-05,
      "loss": 1.6704,
      "step": 37
    },
    {
      "epoch": 0.013683831472812387,
      "grad_norm": 0.6255415678024292,
      "learning_rate": 7.578917319283055e-05,
      "loss": 1.8029,
      "step": 38
    },
    {
      "epoch": 0.014043932301044292,
      "grad_norm": 0.7949183583259583,
      "learning_rate": 7.548891277774448e-05,
      "loss": 1.85,
      "step": 39
    },
    {
      "epoch": 0.014404033129276198,
      "grad_norm": 0.7664933800697327,
      "learning_rate": 7.517895004825956e-05,
      "loss": 1.8477,
      "step": 40
    },
    {
      "epoch": 0.014764133957508103,
      "grad_norm": 0.7252883315086365,
      "learning_rate": 7.48593697450911e-05,
      "loss": 1.9001,
      "step": 41
    },
    {
      "epoch": 0.015124234785740008,
      "grad_norm": 0.9363314509391785,
      "learning_rate": 7.453025923830296e-05,
      "loss": 2.0366,
      "step": 42
    },
    {
      "epoch": 0.015484335613971912,
      "grad_norm": 0.9252744317054749,
      "learning_rate": 7.419170850342156e-05,
      "loss": 2.055,
      "step": 43
    },
    {
      "epoch": 0.01584443644220382,
      "grad_norm": 1.0645928382873535,
      "learning_rate": 7.384381009683742e-05,
      "loss": 2.0096,
      "step": 44
    },
    {
      "epoch": 0.01620453727043572,
      "grad_norm": 1.0589935779571533,
      "learning_rate": 7.348665913050115e-05,
      "loss": 2.1188,
      "step": 45
    },
    {
      "epoch": 0.016564638098667626,
      "grad_norm": 1.3916031122207642,
      "learning_rate": 7.312035324592081e-05,
      "loss": 2.1085,
      "step": 46
    },
    {
      "epoch": 0.01692473892689953,
      "grad_norm": 1.385343313217163,
      "learning_rate": 7.274499258746771e-05,
      "loss": 1.9352,
      "step": 47
    },
    {
      "epoch": 0.017284839755131436,
      "grad_norm": 1.647487998008728,
      "learning_rate": 7.236067977499791e-05,
      "loss": 2.1542,
      "step": 48
    },
    {
      "epoch": 0.01764494058336334,
      "grad_norm": 2.208531379699707,
      "learning_rate": 7.196751987579699e-05,
      "loss": 2.1791,
      "step": 49
    },
    {
      "epoch": 0.018005041411595247,
      "grad_norm": 3.1761276721954346,
      "learning_rate": 7.156562037585576e-05,
      "loss": 2.4123,
      "step": 50
    },
    {
      "epoch": 0.018005041411595247,
      "eval_loss": 1.5850434303283691,
      "eval_runtime": 352.3186,
      "eval_samples_per_second": 13.275,
      "eval_steps_per_second": 3.321,
      "step": 50
    },
    {
      "epoch": 0.018365142239827152,
      "grad_norm": 0.5396647453308105,
      "learning_rate": 7.11550911504845e-05,
      "loss": 1.3308,
      "step": 51
    },
    {
      "epoch": 0.018725243068059057,
      "grad_norm": 0.5886169672012329,
      "learning_rate": 7.073604443427437e-05,
      "loss": 1.1507,
      "step": 52
    },
    {
      "epoch": 0.019085343896290963,
      "grad_norm": 0.6277225613594055,
      "learning_rate": 7.03085947904134e-05,
      "loss": 1.2221,
      "step": 53
    },
    {
      "epoch": 0.019445444724522868,
      "grad_norm": 0.552457869052887,
      "learning_rate": 6.987285907936617e-05,
      "loss": 1.0,
      "step": 54
    },
    {
      "epoch": 0.01980554555275477,
      "grad_norm": 0.47208383679389954,
      "learning_rate": 6.942895642692527e-05,
      "loss": 1.1913,
      "step": 55
    },
    {
      "epoch": 0.020165646380986675,
      "grad_norm": 0.40564197301864624,
      "learning_rate": 6.897700819164357e-05,
      "loss": 1.1485,
      "step": 56
    },
    {
      "epoch": 0.02052574720921858,
      "grad_norm": 0.34190523624420166,
      "learning_rate": 6.851713793165589e-05,
      "loss": 1.0862,
      "step": 57
    },
    {
      "epoch": 0.020885848037450486,
      "grad_norm": 0.31114333868026733,
      "learning_rate": 6.804947137089955e-05,
      "loss": 0.9792,
      "step": 58
    },
    {
      "epoch": 0.02124594886568239,
      "grad_norm": 0.2748708128929138,
      "learning_rate": 6.757413636474263e-05,
      "loss": 1.1398,
      "step": 59
    },
    {
      "epoch": 0.021606049693914296,
      "grad_norm": 0.28262221813201904,
      "learning_rate": 6.709126286502965e-05,
      "loss": 1.0137,
      "step": 60
    },
    {
      "epoch": 0.0219661505221462,
      "grad_norm": 0.3110496401786804,
      "learning_rate": 6.660098288455393e-05,
      "loss": 1.1065,
      "step": 61
    },
    {
      "epoch": 0.022326251350378107,
      "grad_norm": 0.28911370038986206,
      "learning_rate": 6.610343046096674e-05,
      "loss": 1.0633,
      "step": 62
    },
    {
      "epoch": 0.022686352178610012,
      "grad_norm": 0.30962398648262024,
      "learning_rate": 6.559874162013267e-05,
      "loss": 1.2423,
      "step": 63
    },
    {
      "epoch": 0.023046453006841917,
      "grad_norm": 0.30083462595939636,
      "learning_rate": 6.508705433894149e-05,
      "loss": 1.1315,
      "step": 64
    },
    {
      "epoch": 0.02340655383507382,
      "grad_norm": 0.3204285800457001,
      "learning_rate": 6.456850850758673e-05,
      "loss": 1.1024,
      "step": 65
    },
    {
      "epoch": 0.023766654663305724,
      "grad_norm": 0.32156258821487427,
      "learning_rate": 6.404324589132101e-05,
      "loss": 1.1587,
      "step": 66
    },
    {
      "epoch": 0.02412675549153763,
      "grad_norm": 0.3117810785770416,
      "learning_rate": 6.351141009169893e-05,
      "loss": 1.0853,
      "step": 67
    },
    {
      "epoch": 0.024486856319769535,
      "grad_norm": 0.32040199637413025,
      "learning_rate": 6.297314650731775e-05,
      "loss": 1.1984,
      "step": 68
    },
    {
      "epoch": 0.02484695714800144,
      "grad_norm": 0.3659551441669464,
      "learning_rate": 6.242860229406692e-05,
      "loss": 1.117,
      "step": 69
    },
    {
      "epoch": 0.025207057976233346,
      "grad_norm": 0.3537808060646057,
      "learning_rate": 6.18779263248971e-05,
      "loss": 1.2022,
      "step": 70
    },
    {
      "epoch": 0.02556715880446525,
      "grad_norm": 0.33273327350616455,
      "learning_rate": 6.132126914911976e-05,
      "loss": 1.2369,
      "step": 71
    },
    {
      "epoch": 0.025927259632697156,
      "grad_norm": 0.3848983943462372,
      "learning_rate": 6.075878295124861e-05,
      "loss": 1.6059,
      "step": 72
    },
    {
      "epoch": 0.02628736046092906,
      "grad_norm": 0.3831624686717987,
      "learning_rate": 6.019062150939376e-05,
      "loss": 1.381,
      "step": 73
    },
    {
      "epoch": 0.026647461289160967,
      "grad_norm": 0.3995639979839325,
      "learning_rate": 5.9616940153220336e-05,
      "loss": 1.3304,
      "step": 74
    },
    {
      "epoch": 0.02700756211739287,
      "grad_norm": 0.439020037651062,
      "learning_rate": 5.903789572148295e-05,
      "loss": 1.4991,
      "step": 75
    },
    {
      "epoch": 0.027367662945624774,
      "grad_norm": 0.38694366812705994,
      "learning_rate": 5.845364651914752e-05,
      "loss": 1.3432,
      "step": 76
    },
    {
      "epoch": 0.02772776377385668,
      "grad_norm": 0.4259042739868164,
      "learning_rate": 5.786435227411227e-05,
      "loss": 1.4677,
      "step": 77
    },
    {
      "epoch": 0.028087864602088584,
      "grad_norm": 0.42080992460250854,
      "learning_rate": 5.727017409353971e-05,
      "loss": 1.5115,
      "step": 78
    },
    {
      "epoch": 0.02844796543032049,
      "grad_norm": 0.4072776734828949,
      "learning_rate": 5.667127441981162e-05,
      "loss": 1.4107,
      "step": 79
    },
    {
      "epoch": 0.028808066258552395,
      "grad_norm": 0.43466779589653015,
      "learning_rate": 5.606781698611879e-05,
      "loss": 1.5465,
      "step": 80
    },
    {
      "epoch": 0.0291681670867843,
      "grad_norm": 0.4168336093425751,
      "learning_rate": 5.5459966771698096e-05,
      "loss": 1.6694,
      "step": 81
    },
    {
      "epoch": 0.029528267915016206,
      "grad_norm": 0.5250816345214844,
      "learning_rate": 5.4847889956728834e-05,
      "loss": 1.796,
      "step": 82
    },
    {
      "epoch": 0.02988836874324811,
      "grad_norm": 0.5515179634094238,
      "learning_rate": 5.423175387690067e-05,
      "loss": 1.6945,
      "step": 83
    },
    {
      "epoch": 0.030248469571480016,
      "grad_norm": 0.5818299651145935,
      "learning_rate": 5.361172697766573e-05,
      "loss": 1.634,
      "step": 84
    },
    {
      "epoch": 0.030608570399711918,
      "grad_norm": 0.5926039814949036,
      "learning_rate": 5.298797876818735e-05,
      "loss": 1.7657,
      "step": 85
    },
    {
      "epoch": 0.030968671227943823,
      "grad_norm": 0.6447036862373352,
      "learning_rate": 5.23606797749979e-05,
      "loss": 1.8414,
      "step": 86
    },
    {
      "epoch": 0.03132877205617573,
      "grad_norm": 0.574548602104187,
      "learning_rate": 5.17300014953786e-05,
      "loss": 1.8444,
      "step": 87
    },
    {
      "epoch": 0.03168887288440764,
      "grad_norm": 0.645301103591919,
      "learning_rate": 5.109611635047379e-05,
      "loss": 1.7747,
      "step": 88
    },
    {
      "epoch": 0.03204897371263954,
      "grad_norm": 0.6297435760498047,
      "learning_rate": 5.04591976381528e-05,
      "loss": 1.9292,
      "step": 89
    },
    {
      "epoch": 0.03240907454087144,
      "grad_norm": 0.6943683624267578,
      "learning_rate": 4.981941948563197e-05,
      "loss": 1.8509,
      "step": 90
    },
    {
      "epoch": 0.03276917536910335,
      "grad_norm": 0.7677454352378845,
      "learning_rate": 4.9176956801870065e-05,
      "loss": 1.7289,
      "step": 91
    },
    {
      "epoch": 0.03312927619733525,
      "grad_norm": 0.846775233745575,
      "learning_rate": 4.853198522974988e-05,
      "loss": 1.8011,
      "step": 92
    },
    {
      "epoch": 0.03348937702556716,
      "grad_norm": 0.9709502458572388,
      "learning_rate": 4.788468109805921e-05,
      "loss": 2.0327,
      "step": 93
    },
    {
      "epoch": 0.03384947785379906,
      "grad_norm": 0.9475632309913635,
      "learning_rate": 4.7235221373284407e-05,
      "loss": 1.8737,
      "step": 94
    },
    {
      "epoch": 0.03420957868203097,
      "grad_norm": 0.979775607585907,
      "learning_rate": 4.658378361122936e-05,
      "loss": 1.7808,
      "step": 95
    },
    {
      "epoch": 0.03456967951026287,
      "grad_norm": 1.1734482049942017,
      "learning_rate": 4.593054590847368e-05,
      "loss": 1.9409,
      "step": 96
    },
    {
      "epoch": 0.03492978033849478,
      "grad_norm": 1.2772958278656006,
      "learning_rate": 4.5275686853682765e-05,
      "loss": 1.9487,
      "step": 97
    },
    {
      "epoch": 0.03528988116672668,
      "grad_norm": 1.4188159704208374,
      "learning_rate": 4.4619385478783456e-05,
      "loss": 1.9205,
      "step": 98
    },
    {
      "epoch": 0.035649981994958585,
      "grad_norm": 1.8587150573730469,
      "learning_rate": 4.396182121001852e-05,
      "loss": 2.1834,
      "step": 99
    },
    {
      "epoch": 0.036010082823190494,
      "grad_norm": 3.5931663513183594,
      "learning_rate": 4.33031738188933e-05,
      "loss": 2.2956,
      "step": 100
    },
    {
      "epoch": 0.036010082823190494,
      "eval_loss": 1.4850772619247437,
      "eval_runtime": 353.549,
      "eval_samples_per_second": 13.229,
      "eval_steps_per_second": 3.309,
      "step": 100
    },
    {
      "epoch": 0.036370183651422396,
      "grad_norm": 0.31662315130233765,
      "learning_rate": 4.264362337302798e-05,
      "loss": 1.0832,
      "step": 101
    },
    {
      "epoch": 0.036730284479654304,
      "grad_norm": 0.35080909729003906,
      "learning_rate": 4.1983350186928894e-05,
      "loss": 0.964,
      "step": 102
    },
    {
      "epoch": 0.037090385307886206,
      "grad_norm": 0.36373916268348694,
      "learning_rate": 4.132253477269233e-05,
      "loss": 0.9958,
      "step": 103
    },
    {
      "epoch": 0.037450486136118115,
      "grad_norm": 0.4141411781311035,
      "learning_rate": 4.0661357790654345e-05,
      "loss": 1.0403,
      "step": 104
    },
    {
      "epoch": 0.03781058696435002,
      "grad_norm": 0.42372411489486694,
      "learning_rate": 4e-05,
      "loss": 1.0866,
      "step": 105
    },
    {
      "epoch": 0.038170687792581925,
      "grad_norm": 0.48200201988220215,
      "learning_rate": 3.933864220934566e-05,
      "loss": 1.0786,
      "step": 106
    },
    {
      "epoch": 0.03853078862081383,
      "grad_norm": 0.4316590130329132,
      "learning_rate": 3.8677465227307676e-05,
      "loss": 0.9489,
      "step": 107
    },
    {
      "epoch": 0.038890889449045736,
      "grad_norm": 0.40134397149086,
      "learning_rate": 3.8016649813071106e-05,
      "loss": 1.0985,
      "step": 108
    },
    {
      "epoch": 0.03925099027727764,
      "grad_norm": 0.43675699830055237,
      "learning_rate": 3.735637662697203e-05,
      "loss": 1.0101,
      "step": 109
    },
    {
      "epoch": 0.03961109110550954,
      "grad_norm": 0.38096266984939575,
      "learning_rate": 3.669682618110671e-05,
      "loss": 1.0738,
      "step": 110
    },
    {
      "epoch": 0.03997119193374145,
      "grad_norm": 0.31821751594543457,
      "learning_rate": 3.6038178789981494e-05,
      "loss": 1.0365,
      "step": 111
    },
    {
      "epoch": 0.04033129276197335,
      "grad_norm": 0.35773828625679016,
      "learning_rate": 3.538061452121656e-05,
      "loss": 0.9939,
      "step": 112
    },
    {
      "epoch": 0.04069139359020526,
      "grad_norm": 0.33209124207496643,
      "learning_rate": 3.472431314631724e-05,
      "loss": 0.979,
      "step": 113
    },
    {
      "epoch": 0.04105149441843716,
      "grad_norm": 0.3005915582180023,
      "learning_rate": 3.406945409152632e-05,
      "loss": 1.0878,
      "step": 114
    },
    {
      "epoch": 0.04141159524666907,
      "grad_norm": 0.2932342290878296,
      "learning_rate": 3.341621638877064e-05,
      "loss": 1.0154,
      "step": 115
    },
    {
      "epoch": 0.04177169607490097,
      "grad_norm": 0.3328295052051544,
      "learning_rate": 3.276477862671562e-05,
      "loss": 1.156,
      "step": 116
    },
    {
      "epoch": 0.04213179690313288,
      "grad_norm": 0.34108060598373413,
      "learning_rate": 3.21153189019408e-05,
      "loss": 1.3088,
      "step": 117
    },
    {
      "epoch": 0.04249189773136478,
      "grad_norm": 0.319013774394989,
      "learning_rate": 3.146801477025013e-05,
      "loss": 1.3014,
      "step": 118
    },
    {
      "epoch": 0.042851998559596684,
      "grad_norm": 0.3462431728839874,
      "learning_rate": 3.082304319812994e-05,
      "loss": 1.3673,
      "step": 119
    },
    {
      "epoch": 0.04321209938782859,
      "grad_norm": 0.34266746044158936,
      "learning_rate": 3.0180580514368037e-05,
      "loss": 1.4107,
      "step": 120
    },
    {
      "epoch": 0.043572200216060494,
      "grad_norm": 0.31460511684417725,
      "learning_rate": 2.9540802361847212e-05,
      "loss": 1.1764,
      "step": 121
    },
    {
      "epoch": 0.0439323010442924,
      "grad_norm": 0.31650468707084656,
      "learning_rate": 2.890388364952623e-05,
      "loss": 1.1812,
      "step": 122
    },
    {
      "epoch": 0.044292401872524305,
      "grad_norm": 0.34145647287368774,
      "learning_rate": 2.8269998504621416e-05,
      "loss": 1.368,
      "step": 123
    },
    {
      "epoch": 0.044652502700756214,
      "grad_norm": 0.3476177155971527,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 1.188,
      "step": 124
    },
    {
      "epoch": 0.045012603528988115,
      "grad_norm": 0.4023088812828064,
      "learning_rate": 2.7012021231812666e-05,
      "loss": 1.5084,
      "step": 125
    },
    {
      "epoch": 0.045372704357220024,
      "grad_norm": 0.39794808626174927,
      "learning_rate": 2.638827302233428e-05,
      "loss": 1.5975,
      "step": 126
    },
    {
      "epoch": 0.045732805185451926,
      "grad_norm": 0.46040594577789307,
      "learning_rate": 2.576824612309934e-05,
      "loss": 1.5714,
      "step": 127
    },
    {
      "epoch": 0.046092906013683835,
      "grad_norm": 0.4382641017436981,
      "learning_rate": 2.5152110043271166e-05,
      "loss": 1.575,
      "step": 128
    },
    {
      "epoch": 0.04645300684191574,
      "grad_norm": 0.4103611409664154,
      "learning_rate": 2.454003322830192e-05,
      "loss": 1.5312,
      "step": 129
    },
    {
      "epoch": 0.04681310767014764,
      "grad_norm": 0.443014919757843,
      "learning_rate": 2.393218301388123e-05,
      "loss": 1.3191,
      "step": 130
    },
    {
      "epoch": 0.04717320849837955,
      "grad_norm": 0.4959178864955902,
      "learning_rate": 2.3328725580188395e-05,
      "loss": 1.5888,
      "step": 131
    },
    {
      "epoch": 0.04753330932661145,
      "grad_norm": 0.5022261738777161,
      "learning_rate": 2.272982590646029e-05,
      "loss": 1.5632,
      "step": 132
    },
    {
      "epoch": 0.04789341015484336,
      "grad_norm": 0.45459896326065063,
      "learning_rate": 2.2135647725887744e-05,
      "loss": 1.5,
      "step": 133
    },
    {
      "epoch": 0.04825351098307526,
      "grad_norm": 0.504411518573761,
      "learning_rate": 2.1546353480852495e-05,
      "loss": 1.6626,
      "step": 134
    },
    {
      "epoch": 0.04861361181130717,
      "grad_norm": 0.5704218149185181,
      "learning_rate": 2.096210427851706e-05,
      "loss": 1.9689,
      "step": 135
    },
    {
      "epoch": 0.04897371263953907,
      "grad_norm": 0.5692024230957031,
      "learning_rate": 2.038305984677969e-05,
      "loss": 1.5937,
      "step": 136
    },
    {
      "epoch": 0.04933381346777098,
      "grad_norm": 0.560541033744812,
      "learning_rate": 1.9809378490606264e-05,
      "loss": 1.7188,
      "step": 137
    },
    {
      "epoch": 0.04969391429600288,
      "grad_norm": 0.5904568433761597,
      "learning_rate": 1.9241217048751406e-05,
      "loss": 1.6569,
      "step": 138
    },
    {
      "epoch": 0.05005401512423478,
      "grad_norm": 0.6273323893547058,
      "learning_rate": 1.867873085088026e-05,
      "loss": 1.9395,
      "step": 139
    },
    {
      "epoch": 0.05041411595246669,
      "grad_norm": 0.7930026650428772,
      "learning_rate": 1.8122073675102935e-05,
      "loss": 1.866,
      "step": 140
    },
    {
      "epoch": 0.05077421678069859,
      "grad_norm": 0.7339215278625488,
      "learning_rate": 1.75713977059331e-05,
      "loss": 1.7738,
      "step": 141
    },
    {
      "epoch": 0.0511343176089305,
      "grad_norm": 0.7646173238754272,
      "learning_rate": 1.702685349268226e-05,
      "loss": 1.8332,
      "step": 142
    },
    {
      "epoch": 0.051494418437162404,
      "grad_norm": 0.8946234583854675,
      "learning_rate": 1.648858990830108e-05,
      "loss": 1.9375,
      "step": 143
    },
    {
      "epoch": 0.05185451926539431,
      "grad_norm": 1.015981912612915,
      "learning_rate": 1.5956754108678996e-05,
      "loss": 2.0351,
      "step": 144
    },
    {
      "epoch": 0.052214620093626214,
      "grad_norm": 1.0599825382232666,
      "learning_rate": 1.5431491492413288e-05,
      "loss": 1.959,
      "step": 145
    },
    {
      "epoch": 0.05257472092185812,
      "grad_norm": 1.3140443563461304,
      "learning_rate": 1.491294566105852e-05,
      "loss": 1.9238,
      "step": 146
    },
    {
      "epoch": 0.052934821750090025,
      "grad_norm": 1.3724371194839478,
      "learning_rate": 1.4401258379867335e-05,
      "loss": 1.8381,
      "step": 147
    },
    {
      "epoch": 0.053294922578321934,
      "grad_norm": 1.6155120134353638,
      "learning_rate": 1.3896569539033253e-05,
      "loss": 1.9153,
      "step": 148
    },
    {
      "epoch": 0.053655023406553835,
      "grad_norm": 1.8847979307174683,
      "learning_rate": 1.3399017115446067e-05,
      "loss": 2.0038,
      "step": 149
    },
    {
      "epoch": 0.05401512423478574,
      "grad_norm": 2.680107831954956,
      "learning_rate": 1.2908737134970367e-05,
      "loss": 2.086,
      "step": 150
    },
    {
      "epoch": 0.05401512423478574,
      "eval_loss": 1.4379560947418213,
      "eval_runtime": 352.6306,
      "eval_samples_per_second": 13.263,
      "eval_steps_per_second": 3.318,
      "step": 150
    },
    {
      "epoch": 0.054375225063017646,
      "grad_norm": 0.17845895886421204,
      "learning_rate": 1.242586363525737e-05,
      "loss": 1.2068,
      "step": 151
    },
    {
      "epoch": 0.05473532589124955,
      "grad_norm": 0.182268425822258,
      "learning_rate": 1.1950528629100457e-05,
      "loss": 0.9337,
      "step": 152
    },
    {
      "epoch": 0.055095426719481456,
      "grad_norm": 0.2000552862882614,
      "learning_rate": 1.1482862068344121e-05,
      "loss": 1.063,
      "step": 153
    },
    {
      "epoch": 0.05545552754771336,
      "grad_norm": 0.24774210155010223,
      "learning_rate": 1.1022991808356442e-05,
      "loss": 0.9987,
      "step": 154
    },
    {
      "epoch": 0.05581562837594527,
      "grad_norm": 0.24467074871063232,
      "learning_rate": 1.0571043573074737e-05,
      "loss": 1.0237,
      "step": 155
    },
    {
      "epoch": 0.05617572920417717,
      "grad_norm": 0.26388347148895264,
      "learning_rate": 1.0127140920633857e-05,
      "loss": 1.094,
      "step": 156
    },
    {
      "epoch": 0.05653583003240908,
      "grad_norm": 0.26566648483276367,
      "learning_rate": 9.69140520958662e-06,
      "loss": 0.9359,
      "step": 157
    },
    {
      "epoch": 0.05689593086064098,
      "grad_norm": 0.2803097665309906,
      "learning_rate": 9.263955565725648e-06,
      "loss": 0.9668,
      "step": 158
    },
    {
      "epoch": 0.05725603168887288,
      "grad_norm": 0.3015349805355072,
      "learning_rate": 8.844908849515509e-06,
      "loss": 0.9699,
      "step": 159
    },
    {
      "epoch": 0.05761613251710479,
      "grad_norm": 0.32080352306365967,
      "learning_rate": 8.434379624144261e-06,
      "loss": 1.0425,
      "step": 160
    },
    {
      "epoch": 0.05797623334533669,
      "grad_norm": 0.3093397617340088,
      "learning_rate": 8.032480124203013e-06,
      "loss": 1.0277,
      "step": 161
    },
    {
      "epoch": 0.0583363341735686,
      "grad_norm": 0.35267412662506104,
      "learning_rate": 7.639320225002106e-06,
      "loss": 1.0362,
      "step": 162
    },
    {
      "epoch": 0.0586964350018005,
      "grad_norm": 0.3147299885749817,
      "learning_rate": 7.255007412532307e-06,
      "loss": 1.2137,
      "step": 163
    },
    {
      "epoch": 0.05905653583003241,
      "grad_norm": 0.3240807354450226,
      "learning_rate": 6.8796467540791986e-06,
      "loss": 1.1423,
      "step": 164
    },
    {
      "epoch": 0.05941663665826431,
      "grad_norm": 0.34494078159332275,
      "learning_rate": 6.513340869498859e-06,
      "loss": 1.0648,
      "step": 165
    },
    {
      "epoch": 0.05977673748649622,
      "grad_norm": 0.344433456659317,
      "learning_rate": 6.1561899031625794e-06,
      "loss": 1.1728,
      "step": 166
    },
    {
      "epoch": 0.060136838314728124,
      "grad_norm": 0.3598881959915161,
      "learning_rate": 5.808291496578435e-06,
      "loss": 1.243,
      "step": 167
    },
    {
      "epoch": 0.06049693914296003,
      "grad_norm": 0.32712891697883606,
      "learning_rate": 5.469740761697044e-06,
      "loss": 1.1395,
      "step": 168
    },
    {
      "epoch": 0.060857039971191934,
      "grad_norm": 0.3846420347690582,
      "learning_rate": 5.140630254908905e-06,
      "loss": 1.228,
      "step": 169
    },
    {
      "epoch": 0.061217140799423836,
      "grad_norm": 0.38621753454208374,
      "learning_rate": 4.821049951740442e-06,
      "loss": 1.2447,
      "step": 170
    },
    {
      "epoch": 0.061577241627655745,
      "grad_norm": 0.3678813874721527,
      "learning_rate": 4.511087222255528e-06,
      "loss": 1.4654,
      "step": 171
    },
    {
      "epoch": 0.061937342455887646,
      "grad_norm": 0.42819997668266296,
      "learning_rate": 4.2108268071694616e-06,
      "loss": 1.346,
      "step": 172
    },
    {
      "epoch": 0.062297443284119555,
      "grad_norm": 0.4565679430961609,
      "learning_rate": 3.9203507946816445e-06,
      "loss": 1.5151,
      "step": 173
    },
    {
      "epoch": 0.06265754411235146,
      "grad_norm": 0.45869430899620056,
      "learning_rate": 3.6397385980335e-06,
      "loss": 1.5592,
      "step": 174
    },
    {
      "epoch": 0.06301764494058336,
      "grad_norm": 0.4956825375556946,
      "learning_rate": 3.3690669337977e-06,
      "loss": 1.492,
      "step": 175
    },
    {
      "epoch": 0.06337774576881527,
      "grad_norm": 0.485346257686615,
      "learning_rate": 3.1084098009046106e-06,
      "loss": 1.3435,
      "step": 176
    },
    {
      "epoch": 0.06373784659704718,
      "grad_norm": 0.48392120003700256,
      "learning_rate": 2.8578384604117217e-06,
      "loss": 1.2057,
      "step": 177
    },
    {
      "epoch": 0.06409794742527908,
      "grad_norm": 0.549443781375885,
      "learning_rate": 2.6174214160215704e-06,
      "loss": 1.5785,
      "step": 178
    },
    {
      "epoch": 0.06445804825351098,
      "grad_norm": 0.6267411112785339,
      "learning_rate": 2.3872243953535535e-06,
      "loss": 1.4255,
      "step": 179
    },
    {
      "epoch": 0.06481814908174288,
      "grad_norm": 0.6748881936073303,
      "learning_rate": 2.1673103319746146e-06,
      "loss": 1.5805,
      "step": 180
    },
    {
      "epoch": 0.0651782499099748,
      "grad_norm": 0.5772015452384949,
      "learning_rate": 1.957739348193859e-06,
      "loss": 1.5119,
      "step": 181
    },
    {
      "epoch": 0.0655383507382067,
      "grad_norm": 0.6203552484512329,
      "learning_rate": 1.7585687386256944e-06,
      "loss": 1.8784,
      "step": 182
    },
    {
      "epoch": 0.0658984515664386,
      "grad_norm": 0.6191961169242859,
      "learning_rate": 1.5698529545260744e-06,
      "loss": 1.6006,
      "step": 183
    },
    {
      "epoch": 0.0662585523946705,
      "grad_norm": 0.6806838512420654,
      "learning_rate": 1.3916435889060575e-06,
      "loss": 1.8019,
      "step": 184
    },
    {
      "epoch": 0.06661865322290242,
      "grad_norm": 0.6513646841049194,
      "learning_rate": 1.2239893624267852e-06,
      "loss": 1.7764,
      "step": 185
    },
    {
      "epoch": 0.06697875405113432,
      "grad_norm": 0.7780475616455078,
      "learning_rate": 1.0669361100797704e-06,
      "loss": 1.6974,
      "step": 186
    },
    {
      "epoch": 0.06733885487936622,
      "grad_norm": 0.7961820363998413,
      "learning_rate": 9.205267686560293e-07,
      "loss": 1.7828,
      "step": 187
    },
    {
      "epoch": 0.06769895570759812,
      "grad_norm": 0.8191195726394653,
      "learning_rate": 7.848013650076258e-07,
      "loss": 1.6961,
      "step": 188
    },
    {
      "epoch": 0.06805905653583003,
      "grad_norm": 0.751133143901825,
      "learning_rate": 6.597970051047053e-07,
      "loss": 1.7882,
      "step": 189
    },
    {
      "epoch": 0.06841915736406194,
      "grad_norm": 1.0630866289138794,
      "learning_rate": 5.455478638911071e-07,
      "loss": 1.9139,
      "step": 190
    },
    {
      "epoch": 0.06877925819229384,
      "grad_norm": 0.9345506429672241,
      "learning_rate": 4.420851759412603e-07,
      "loss": 2.0675,
      "step": 191
    },
    {
      "epoch": 0.06913935902052575,
      "grad_norm": 1.0234652757644653,
      "learning_rate": 3.4943722692099224e-07,
      "loss": 1.7824,
      "step": 192
    },
    {
      "epoch": 0.06949945984875765,
      "grad_norm": 1.1317789554595947,
      "learning_rate": 2.676293458544743e-07,
      "loss": 2.1633,
      "step": 193
    },
    {
      "epoch": 0.06985956067698956,
      "grad_norm": 1.1043999195098877,
      "learning_rate": 1.9668389819954338e-07,
      "loss": 1.6105,
      "step": 194
    },
    {
      "epoch": 0.07021966150522146,
      "grad_norm": 0.9714563488960266,
      "learning_rate": 1.3662027973320614e-07,
      "loss": 1.9675,
      "step": 195
    },
    {
      "epoch": 0.07057976233345337,
      "grad_norm": 1.1052969694137573,
      "learning_rate": 8.745491124901861e-08,
      "loss": 1.7856,
      "step": 196
    },
    {
      "epoch": 0.07093986316168527,
      "grad_norm": 1.3346896171569824,
      "learning_rate": 4.920123406781052e-08,
      "loss": 2.0093,
      "step": 197
    },
    {
      "epoch": 0.07129996398991717,
      "grad_norm": 1.2368483543395996,
      "learning_rate": 2.1869706362958044e-08,
      "loss": 1.7745,
      "step": 198
    },
    {
      "epoch": 0.07166006481814909,
      "grad_norm": 1.3380067348480225,
      "learning_rate": 5.467800301239834e-09,
      "loss": 1.7581,
      "step": 199
    },
    {
      "epoch": 0.07202016564638099,
      "grad_norm": 1.7450910806655884,
      "learning_rate": 0.0,
      "loss": 1.7731,
      "step": 200
    },
    {
      "epoch": 0.07202016564638099,
      "eval_loss": 1.4315598011016846,
      "eval_runtime": 352.6531,
      "eval_samples_per_second": 13.262,
      "eval_steps_per_second": 3.318,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7075605394200986e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}