{
  "best_metric": 2.1507210731506348,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.995670995670996,
  "eval_steps": 50,
  "global_step": 173,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 2.8213117122650146,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.3594,
      "eval_samples_per_second": 22.48,
      "eval_steps_per_second": 5.735,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 4.985778331756592,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.763190746307373,
      "learning_rate": 3e-05,
      "loss": 2.7875,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.077609062194824,
      "learning_rate": 4e-05,
      "loss": 2.7441,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.072812557220459,
      "learning_rate": 5e-05,
      "loss": 2.8514,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.6697731018066406,
      "learning_rate": 6e-05,
      "loss": 2.9252,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.85693097114563,
      "learning_rate": 7e-05,
      "loss": 2.6601,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.4699630737304688,
      "learning_rate": 8e-05,
      "loss": 2.8323,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.797606945037842,
      "learning_rate": 9e-05,
      "loss": 2.8909,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.5858542919158936,
      "learning_rate": 0.0001,
      "loss": 2.822,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.080673933029175,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5766,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.805807113647461,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7912,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.506392002105713,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8573,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.713083744049072,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.2263,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.9132823944091797,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8389,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.8513776063919067,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4264,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.6016584634780884,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3631,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.684198260307312,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2753,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6534029245376587,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.188,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8303340673446655,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.036,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.1308131217956543,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.352,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.047966957092285,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.2961,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.1768929958343506,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3702,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.389242172241211,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5131,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.320732831954956,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5102,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.5188190937042236,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.5501,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.676851272583008,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4123,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.181878089904785,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1274,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3181054592132568,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.623,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.1700284481048584,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2628,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6111098527908325,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.071,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5531660318374634,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0633,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5699286460876465,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.024,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7361576557159424,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0409,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.9074763059616089,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.2535,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.9367103576660156,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1472,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.172595262527466,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3721,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.279202699661255,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.6207,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.3072283267974854,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3583,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.4182658195495605,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.3313,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.541595220565796,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.381,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.249802112579346,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3142,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.995394229888916,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7486,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.733182430267334,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.057,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.6964753866195679,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0244,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.5640254020690918,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8624,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.5645256042480469,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1798,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.4937459230422974,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0126,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6373777389526367,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.879,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.8210711479187012,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.1558,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.257964849472046,
      "eval_runtime": 4.389,
      "eval_samples_per_second": 22.329,
      "eval_steps_per_second": 5.696,
      "step": 50
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 2.078730344772339,
      "learning_rate": 8.518457335743926e-05,
      "loss": 2.3291,
      "step": 51
    },
    {
      "epoch": 0.9004329004329005,
      "grad_norm": 2.2976505756378174,
      "learning_rate": 8.449338172278059e-05,
      "loss": 2.4847,
      "step": 52
    },
    {
      "epoch": 0.9177489177489178,
      "grad_norm": 2.3204331398010254,
      "learning_rate": 8.378937720492384e-05,
      "loss": 2.2143,
      "step": 53
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 2.5574119091033936,
      "learning_rate": 8.307282131280804e-05,
      "loss": 2.2599,
      "step": 54
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.842057228088379,
      "learning_rate": 8.23439802176954e-05,
      "loss": 2.398,
      "step": 55
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 5.180115222930908,
      "learning_rate": 8.160312465429952e-05,
      "loss": 2.8077,
      "step": 56
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 1.269924521446228,
      "learning_rate": 8.085052982021847e-05,
      "loss": 1.8004,
      "step": 57
    },
    {
      "epoch": 1.0043290043290043,
      "grad_norm": 3.555042266845703,
      "learning_rate": 8.008647527371023e-05,
      "loss": 2.9331,
      "step": 58
    },
    {
      "epoch": 1.0216450216450217,
      "grad_norm": 0.9649820327758789,
      "learning_rate": 7.931124482984802e-05,
      "loss": 1.6347,
      "step": 59
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 1.0270448923110962,
      "learning_rate": 7.85251264550948e-05,
      "loss": 1.7292,
      "step": 60
    },
    {
      "epoch": 1.0562770562770563,
      "grad_norm": 1.1698195934295654,
      "learning_rate": 7.772841216033533e-05,
      "loss": 1.7121,
      "step": 61
    },
    {
      "epoch": 1.0735930735930737,
      "grad_norm": 1.318803071975708,
      "learning_rate": 7.692139789240611e-05,
      "loss": 1.6378,
      "step": 62
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.3806180953979492,
      "learning_rate": 7.610438342416319e-05,
      "loss": 1.5165,
      "step": 63
    },
    {
      "epoch": 1.1082251082251082,
      "grad_norm": 1.6144442558288574,
      "learning_rate": 7.527767224312883e-05,
      "loss": 1.8815,
      "step": 64
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 1.3800272941589355,
      "learning_rate": 7.44415714387582e-05,
      "loss": 1.489,
      "step": 65
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.5080249309539795,
      "learning_rate": 7.359639158836828e-05,
      "loss": 1.7076,
      "step": 66
    },
    {
      "epoch": 1.1601731601731602,
      "grad_norm": 1.7485432624816895,
      "learning_rate": 7.274244664177097e-05,
      "loss": 1.8926,
      "step": 67
    },
    {
      "epoch": 1.1774891774891776,
      "grad_norm": 1.9501352310180664,
      "learning_rate": 7.188005380465364e-05,
      "loss": 1.7409,
      "step": 68
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 2.2572169303894043,
      "learning_rate": 7.10095334207501e-05,
      "loss": 1.7492,
      "step": 69
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 2.5785837173461914,
      "learning_rate": 7.013120885284598e-05,
      "loss": 1.9541,
      "step": 70
    },
    {
      "epoch": 1.2294372294372296,
      "grad_norm": 2.9430317878723145,
      "learning_rate": 6.924540636266272e-05,
      "loss": 1.7906,
      "step": 71
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 3.6292784214019775,
      "learning_rate": 6.835245498966461e-05,
      "loss": 1.8423,
      "step": 72
    },
    {
      "epoch": 1.2640692640692641,
      "grad_norm": 1.190421462059021,
      "learning_rate": 6.745268642883404e-05,
      "loss": 1.3868,
      "step": 73
    },
    {
      "epoch": 1.2813852813852815,
      "grad_norm": 1.5110549926757812,
      "learning_rate": 6.654643490746042e-05,
      "loss": 1.8033,
      "step": 74
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.511256217956543,
      "learning_rate": 6.563403706098833e-05,
      "loss": 1.911,
      "step": 75
    },
    {
      "epoch": 1.316017316017316,
      "grad_norm": 1.329278588294983,
      "learning_rate": 6.471583180797121e-05,
      "loss": 1.3092,
      "step": 76
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.5857261419296265,
      "learning_rate": 6.379216022417696e-05,
      "loss": 1.7496,
      "step": 77
    },
    {
      "epoch": 1.3506493506493507,
      "grad_norm": 1.6332991123199463,
      "learning_rate": 6.286336541589224e-05,
      "loss": 1.6607,
      "step": 78
    },
    {
      "epoch": 1.3679653679653678,
      "grad_norm": 1.6632938385009766,
      "learning_rate": 6.192979239247243e-05,
      "loss": 1.5656,
      "step": 79
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 1.711585521697998,
      "learning_rate": 6.0991787938184784e-05,
      "loss": 1.7717,
      "step": 80
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 1.7672886848449707,
      "learning_rate": 6.004970048339226e-05,
      "loss": 1.5959,
      "step": 81
    },
    {
      "epoch": 1.4199134199134198,
      "grad_norm": 1.8584389686584473,
      "learning_rate": 5.910387997512573e-05,
      "loss": 1.7643,
      "step": 82
    },
    {
      "epoch": 1.4372294372294372,
      "grad_norm": 2.1086313724517822,
      "learning_rate": 5.8154677747093134e-05,
      "loss": 1.6635,
      "step": 83
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 2.3654050827026367,
      "learning_rate": 5.7202446389173223e-05,
      "loss": 1.9113,
      "step": 84
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 2.853776693344116,
      "learning_rate": 5.624753961644281e-05,
      "loss": 1.6637,
      "step": 85
    },
    {
      "epoch": 1.4891774891774892,
      "grad_norm": 3.0281548500061035,
      "learning_rate": 5.5290312137786146e-05,
      "loss": 1.5317,
      "step": 86
    },
    {
      "epoch": 1.5064935064935066,
      "grad_norm": 0.9081037044525146,
      "learning_rate": 5.433111952413495e-05,
      "loss": 1.4504,
      "step": 87
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.2145230770111084,
      "learning_rate": 5.33703180763884e-05,
      "loss": 1.8371,
      "step": 88
    },
    {
      "epoch": 1.5411255411255411,
      "grad_norm": 1.255497932434082,
      "learning_rate": 5.240826469306187e-05,
      "loss": 1.6484,
      "step": 89
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 1.4401757717132568,
      "learning_rate": 5.144531673771363e-05,
      "loss": 1.4698,
      "step": 90
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.397579550743103,
      "learning_rate": 5.048183190619904e-05,
      "loss": 1.5281,
      "step": 91
    },
    {
      "epoch": 1.593073593073593,
      "grad_norm": 1.5913752317428589,
      "learning_rate": 4.951816809380097e-05,
      "loss": 1.5165,
      "step": 92
    },
    {
      "epoch": 1.6103896103896105,
      "grad_norm": 1.7253613471984863,
      "learning_rate": 4.855468326228638e-05,
      "loss": 1.5576,
      "step": 93
    },
    {
      "epoch": 1.6277056277056277,
      "grad_norm": 1.8811947107315063,
      "learning_rate": 4.759173530693814e-05,
      "loss": 1.6702,
      "step": 94
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 1.9672281742095947,
      "learning_rate": 4.6629681923611603e-05,
      "loss": 1.7017,
      "step": 95
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 2.2291691303253174,
      "learning_rate": 4.566888047586507e-05,
      "loss": 1.8685,
      "step": 96
    },
    {
      "epoch": 1.6796536796536796,
      "grad_norm": 2.2788848876953125,
      "learning_rate": 4.4709687862213866e-05,
      "loss": 1.6978,
      "step": 97
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 2.3256399631500244,
      "learning_rate": 4.3752460383557195e-05,
      "loss": 1.7429,
      "step": 98
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 3.4185853004455566,
      "learning_rate": 4.27975536108268e-05,
      "loss": 1.8859,
      "step": 99
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 3.066596031188965,
      "learning_rate": 4.1845322252906864e-05,
      "loss": 1.4093,
      "step": 100
    },
    {
      "epoch": 1.7316017316017316,
      "eval_loss": 2.1507210731506348,
      "eval_runtime": 4.391,
      "eval_samples_per_second": 22.318,
      "eval_steps_per_second": 5.693,
      "step": 100
    },
    {
      "epoch": 1.7489177489177488,
      "grad_norm": 1.0498305559158325,
      "learning_rate": 4.0896120024874286e-05,
      "loss": 1.5793,
      "step": 101
    },
    {
      "epoch": 1.7662337662337664,
      "grad_norm": 1.2344704866409302,
      "learning_rate": 3.9950299516607766e-05,
      "loss": 1.4962,
      "step": 102
    },
    {
      "epoch": 1.7835497835497836,
      "grad_norm": 1.401984691619873,
      "learning_rate": 3.900821206181521e-05,
      "loss": 1.5564,
      "step": 103
    },
    {
      "epoch": 1.8008658008658007,
      "grad_norm": 1.431049108505249,
      "learning_rate": 3.8070207607527584e-05,
      "loss": 1.5089,
      "step": 104
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.506121039390564,
      "learning_rate": 3.713663458410779e-05,
      "loss": 1.4881,
      "step": 105
    },
    {
      "epoch": 1.8354978354978355,
      "grad_norm": 1.7029125690460205,
      "learning_rate": 3.620783977582305e-05,
      "loss": 1.3652,
      "step": 106
    },
    {
      "epoch": 1.8528138528138527,
      "grad_norm": 1.684980869293213,
      "learning_rate": 3.528416819202881e-05,
      "loss": 1.4969,
      "step": 107
    },
    {
      "epoch": 1.87012987012987,
      "grad_norm": 1.84793221950531,
      "learning_rate": 3.43659629390117e-05,
      "loss": 1.741,
      "step": 108
    },
    {
      "epoch": 1.8874458874458875,
      "grad_norm": 2.200406074523926,
      "learning_rate": 3.345356509253959e-05,
      "loss": 1.8311,
      "step": 109
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.0255842208862305,
      "learning_rate": 3.254731357116597e-05,
      "loss": 1.6737,
      "step": 110
    },
    {
      "epoch": 1.922077922077922,
      "grad_norm": 2.303042411804199,
      "learning_rate": 3.16475450103354e-05,
      "loss": 1.5814,
      "step": 111
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 2.6473817825317383,
      "learning_rate": 3.0754593637337276e-05,
      "loss": 1.6909,
      "step": 112
    },
    {
      "epoch": 1.9567099567099566,
      "grad_norm": 3.3562562465667725,
      "learning_rate": 2.986879114715403e-05,
      "loss": 1.7364,
      "step": 113
    },
    {
      "epoch": 1.974025974025974,
      "grad_norm": 3.026970624923706,
      "learning_rate": 2.899046657924992e-05,
      "loss": 1.4776,
      "step": 114
    },
    {
      "epoch": 1.9913419913419914,
      "grad_norm": 2.301281452178955,
      "learning_rate": 2.8119946195346375e-05,
      "loss": 1.7903,
      "step": 115
    },
    {
      "epoch": 2.0086580086580086,
      "grad_norm": 2.0882139205932617,
      "learning_rate": 2.7257553358229034e-05,
      "loss": 1.5866,
      "step": 116
    },
    {
      "epoch": 2.0259740259740258,
      "grad_norm": 0.9352264404296875,
      "learning_rate": 2.6403608411631742e-05,
      "loss": 1.2755,
      "step": 117
    },
    {
      "epoch": 2.0432900432900434,
      "grad_norm": 1.2251120805740356,
      "learning_rate": 2.555842856124182e-05,
      "loss": 1.541,
      "step": 118
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 1.1876617670059204,
      "learning_rate": 2.472232775687119e-05,
      "loss": 1.1754,
      "step": 119
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 1.3045542240142822,
      "learning_rate": 2.389561657583681e-05,
      "loss": 1.2134,
      "step": 120
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 1.4649866819381714,
      "learning_rate": 2.30786021075939e-05,
      "loss": 1.4063,
      "step": 121
    },
    {
      "epoch": 2.1125541125541125,
      "grad_norm": 1.4156118631362915,
      "learning_rate": 2.2271587839664672e-05,
      "loss": 1.0884,
      "step": 122
    },
    {
      "epoch": 2.1298701298701297,
      "grad_norm": 1.5468546152114868,
      "learning_rate": 2.1474873544905205e-05,
      "loss": 1.2391,
      "step": 123
    },
    {
      "epoch": 2.1471861471861473,
      "grad_norm": 1.5604561567306519,
      "learning_rate": 2.0688755170151996e-05,
      "loss": 1.2168,
      "step": 124
    },
    {
      "epoch": 2.1645021645021645,
      "grad_norm": 1.9809437990188599,
      "learning_rate": 1.9913524726289784e-05,
      "loss": 1.3889,
      "step": 125
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 2.0183825492858887,
      "learning_rate": 1.914947017978153e-05,
      "loss": 1.3733,
      "step": 126
    },
    {
      "epoch": 2.1991341991341993,
      "grad_norm": 2.0843398571014404,
      "learning_rate": 1.8396875345700497e-05,
      "loss": 1.1898,
      "step": 127
    },
    {
      "epoch": 2.2164502164502164,
      "grad_norm": 2.6395606994628906,
      "learning_rate": 1.76560197823046e-05,
      "loss": 1.3807,
      "step": 128
    },
    {
      "epoch": 2.2337662337662336,
      "grad_norm": 3.146881341934204,
      "learning_rate": 1.692717868719195e-05,
      "loss": 1.1517,
      "step": 129
    },
    {
      "epoch": 2.2510822510822512,
      "grad_norm": 2.617090940475464,
      "learning_rate": 1.621062279507617e-05,
      "loss": 1.0857,
      "step": 130
    },
    {
      "epoch": 2.2683982683982684,
      "grad_norm": 1.1143049001693726,
      "learning_rate": 1.550661827721941e-05,
      "loss": 1.1666,
      "step": 131
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.417263388633728,
      "learning_rate": 1.4815426642560754e-05,
      "loss": 1.3524,
      "step": 132
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 1.5993542671203613,
      "learning_rate": 1.413730464057616e-05,
      "loss": 1.4026,
      "step": 133
    },
    {
      "epoch": 2.3203463203463204,
      "grad_norm": 1.6387602090835571,
      "learning_rate": 1.3472504165906613e-05,
      "loss": 1.1655,
      "step": 134
    },
    {
      "epoch": 2.3376623376623376,
      "grad_norm": 1.7244728803634644,
      "learning_rate": 1.2821272164789544e-05,
      "loss": 1.245,
      "step": 135
    },
    {
      "epoch": 2.354978354978355,
      "grad_norm": 1.804990291595459,
      "learning_rate": 1.2183850543328312e-05,
      "loss": 1.162,
      "step": 136
    },
    {
      "epoch": 2.3722943722943723,
      "grad_norm": 1.9783991575241089,
      "learning_rate": 1.156047607763407e-05,
      "loss": 1.2835,
      "step": 137
    },
    {
      "epoch": 2.3896103896103895,
      "grad_norm": 2.1209795475006104,
      "learning_rate": 1.0951380325872979e-05,
      "loss": 1.2143,
      "step": 138
    },
    {
      "epoch": 2.4069264069264067,
      "grad_norm": 2.3989975452423096,
      "learning_rate": 1.0356789542251938e-05,
      "loss": 1.3039,
      "step": 139
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 2.3346776962280273,
      "learning_rate": 9.776924592974256e-06,
      "loss": 1.2018,
      "step": 140
    },
    {
      "epoch": 2.4415584415584415,
      "grad_norm": 2.547539234161377,
      "learning_rate": 9.212000874196953e-06,
      "loss": 1.2262,
      "step": 141
    },
    {
      "epoch": 2.458874458874459,
      "grad_norm": 3.0654184818267822,
      "learning_rate": 8.662228232019876e-06,
      "loss": 1.4538,
      "step": 142
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 3.6214401721954346,
      "learning_rate": 8.127810884536403e-06,
      "loss": 1.0349,
      "step": 143
    },
    {
      "epoch": 2.4935064935064934,
      "grad_norm": 2.0259740352630615,
      "learning_rate": 7.60894734597476e-06,
      "loss": 1.0412,
      "step": 144
    },
    {
      "epoch": 2.5108225108225106,
      "grad_norm": 1.3173432350158691,
      "learning_rate": 7.105830352958142e-06,
      "loss": 1.3996,
      "step": 145
    },
    {
      "epoch": 2.5281385281385282,
      "grad_norm": 1.410283088684082,
      "learning_rate": 6.618646792910893e-06,
      "loss": 1.267,
      "step": 146
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.697140097618103,
      "learning_rate": 6.147577634637414e-06,
      "loss": 1.3348,
      "step": 147
    },
    {
      "epoch": 2.562770562770563,
      "grad_norm": 1.521960973739624,
      "learning_rate": 5.692797861099719e-06,
      "loss": 1.0552,
      "step": 148
    },
    {
      "epoch": 2.58008658008658,
      "grad_norm": 1.7901246547698975,
      "learning_rate": 5.25447640441834e-06,
      "loss": 1.2096,
      "step": 149
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 1.9669653177261353,
      "learning_rate": 4.832776083120982e-06,
      "loss": 1.3032,
      "step": 150
    },
    {
      "epoch": 2.5974025974025974,
      "eval_loss": 2.2222650051116943,
      "eval_runtime": 4.3939,
      "eval_samples_per_second": 22.304,
      "eval_steps_per_second": 5.69,
      "step": 150
    },
    {
      "epoch": 2.6147186147186146,
      "grad_norm": 1.8027799129486084,
      "learning_rate": 4.427853541662091e-06,
      "loss": 1.1552,
      "step": 151
    },
    {
      "epoch": 2.632034632034632,
      "grad_norm": 2.235262870788574,
      "learning_rate": 4.039859192235779e-06,
      "loss": 1.337,
      "step": 152
    },
    {
      "epoch": 2.6493506493506493,
      "grad_norm": 2.1661159992218018,
      "learning_rate": 3.668937158903901e-06,
      "loss": 1.2975,
      "step": 153
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 2.5141921043395996,
      "learning_rate": 3.315225224059809e-06,
      "loss": 1.3994,
      "step": 154
    },
    {
      "epoch": 2.683982683982684,
      "grad_norm": 2.581247329711914,
      "learning_rate": 2.9788547772478416e-06,
      "loss": 1.3274,
      "step": 155
    },
    {
      "epoch": 2.7012987012987013,
      "grad_norm": 2.8021349906921387,
      "learning_rate": 2.6599507663574384e-06,
      "loss": 1.3022,
      "step": 156
    },
    {
      "epoch": 2.7186147186147185,
      "grad_norm": 3.4175803661346436,
      "learning_rate": 2.3586316512101416e-06,
      "loss": 1.0559,
      "step": 157
    },
    {
      "epoch": 2.7359307359307357,
      "grad_norm": 2.147571325302124,
      "learning_rate": 2.0750093595565733e-06,
      "loss": 0.921,
      "step": 158
    },
    {
      "epoch": 2.7532467532467533,
      "grad_norm": 1.2642135620117188,
      "learning_rate": 1.8091892454998594e-06,
      "loss": 1.3034,
      "step": 159
    },
    {
      "epoch": 2.7705627705627704,
      "grad_norm": 1.4417630434036255,
      "learning_rate": 1.5612700503608968e-06,
      "loss": 1.2898,
      "step": 160
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 1.5540878772735596,
      "learning_rate": 1.33134386599994e-06,
      "loss": 1.3604,
      "step": 161
    },
    {
      "epoch": 2.8051948051948052,
      "grad_norm": 1.5877907276153564,
      "learning_rate": 1.1194961006082972e-06,
      "loss": 1.0281,
      "step": 162
    },
    {
      "epoch": 2.8225108225108224,
      "grad_norm": 1.7505203485488892,
      "learning_rate": 9.258054469825972e-07,
      "loss": 1.2218,
      "step": 163
    },
    {
      "epoch": 2.8398268398268396,
      "grad_norm": 1.8919233083724976,
      "learning_rate": 7.503438532937168e-07,
      "loss": 1.2478,
      "step": 164
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 2.079549551010132,
      "learning_rate": 5.931764963608866e-07,
      "loss": 1.2802,
      "step": 165
    },
    {
      "epoch": 2.8744588744588744,
      "grad_norm": 2.0939548015594482,
      "learning_rate": 4.543617574412184e-07,
      "loss": 1.2624,
      "step": 166
    },
    {
      "epoch": 2.891774891774892,
      "grad_norm": 2.422916889190674,
      "learning_rate": 3.339512005434309e-07,
      "loss": 1.41,
      "step": 167
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 2.525646209716797,
      "learning_rate": 2.319895532739369e-07,
      "loss": 1.3279,
      "step": 168
    },
    {
      "epoch": 2.9264069264069263,
      "grad_norm": 2.577411651611328,
      "learning_rate": 1.4851469022234e-07,
      "loss": 1.2682,
      "step": 169
    },
    {
      "epoch": 2.9437229437229435,
      "grad_norm": 2.868537664413452,
      "learning_rate": 8.355761889260461e-08,
      "loss": 1.2998,
      "step": 170
    },
    {
      "epoch": 2.961038961038961,
      "grad_norm": 3.9087862968444824,
      "learning_rate": 3.7142468185014104e-08,
      "loss": 1.2669,
      "step": 171
    },
    {
      "epoch": 2.9783549783549783,
      "grad_norm": 2.4271037578582764,
      "learning_rate": 9.286479433257e-09,
      "loss": 1.1907,
      "step": 172
    },
    {
      "epoch": 2.995670995670996,
      "grad_norm": 3.979084014892578,
      "learning_rate": 0.0,
      "loss": 1.3893,
      "step": 173
    }
  ],
  "logging_steps": 1,
  "max_steps": 173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.155617850143539e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}