{
  "best_metric": 2.152366876602173,
  "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": 2.9387435913085938,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.344,
      "eval_samples_per_second": 22.56,
      "eval_steps_per_second": 5.755,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 5.139528274536133,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.914796829223633,
      "learning_rate": 3e-05,
      "loss": 2.7866,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.245682716369629,
      "learning_rate": 4e-05,
      "loss": 2.746,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.1254494190216064,
      "learning_rate": 5e-05,
      "loss": 2.8542,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.7362921237945557,
      "learning_rate": 6e-05,
      "loss": 2.926,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.974932909011841,
      "learning_rate": 7e-05,
      "loss": 2.6606,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.6186652183532715,
      "learning_rate": 8e-05,
      "loss": 2.8325,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.9228475093841553,
      "learning_rate": 9e-05,
      "loss": 2.8958,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.677933931350708,
      "learning_rate": 0.0001,
      "loss": 2.8298,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.1858465671539307,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5817,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.5777268409729,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7875,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.638686180114746,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8591,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.722777366638184,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.2288,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.9620873928070068,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8374,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.897153377532959,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4244,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.651064395904541,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3612,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.699037790298462,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2735,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6841057538986206,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.1853,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8492727279663086,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.0329,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.129349708557129,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.3533,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.077242612838745,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.2993,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.2076005935668945,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3723,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.4256765842437744,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5134,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.3577840328216553,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5137,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.537437677383423,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.5495,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.6806864738464355,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4125,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.173317909240723,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1251,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3416013717651367,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.6231,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.266317367553711,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2668,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6532464027404785,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.0788,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5631037950515747,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0639,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5692074298858643,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.0207,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7426583766937256,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0453,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.9080238342285156,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.2511,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.9635432958602905,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1541,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.1697998046875,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3753,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.313002109527588,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.624,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.327439069747925,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3621,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.42288875579834,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.3368,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.5706088542938232,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.3773,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.355373859405518,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3191,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.9972807168960571,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7458,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.7161154747009277,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.056,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.6952000856399536,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0244,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.5799423456192017,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8622,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.5837287902832031,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1797,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.508253574371338,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0132,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6631190776824951,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.8781,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.8189866542816162,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.1498,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.2541444301605225,
      "eval_runtime": 4.3801,
      "eval_samples_per_second": 22.374,
      "eval_steps_per_second": 5.708,
      "step": 50
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 2.101577043533325,
      "learning_rate": 8.518457335743926e-05,
      "loss": 2.3303,
      "step": 51
    },
    {
      "epoch": 0.9004329004329005,
      "grad_norm": 2.2967660427093506,
      "learning_rate": 8.449338172278059e-05,
      "loss": 2.479,
      "step": 52
    },
    {
      "epoch": 0.9177489177489178,
      "grad_norm": 2.3206093311309814,
      "learning_rate": 8.378937720492384e-05,
      "loss": 2.2109,
      "step": 53
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 2.5713882446289062,
      "learning_rate": 8.307282131280804e-05,
      "loss": 2.2578,
      "step": 54
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.8342926502227783,
      "learning_rate": 8.23439802176954e-05,
      "loss": 2.3931,
      "step": 55
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 5.245887756347656,
      "learning_rate": 8.160312465429952e-05,
      "loss": 2.8091,
      "step": 56
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 1.295880675315857,
      "learning_rate": 8.085052982021847e-05,
      "loss": 1.8011,
      "step": 57
    },
    {
      "epoch": 1.0043290043290043,
      "grad_norm": 3.5758066177368164,
      "learning_rate": 8.008647527371023e-05,
      "loss": 2.9375,
      "step": 58
    },
    {
      "epoch": 1.0216450216450217,
      "grad_norm": 0.979328453540802,
      "learning_rate": 7.931124482984802e-05,
      "loss": 1.6344,
      "step": 59
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 1.0317955017089844,
      "learning_rate": 7.85251264550948e-05,
      "loss": 1.729,
      "step": 60
    },
    {
      "epoch": 1.0562770562770563,
      "grad_norm": 1.1673364639282227,
      "learning_rate": 7.772841216033533e-05,
      "loss": 1.7061,
      "step": 61
    },
    {
      "epoch": 1.0735930735930737,
      "grad_norm": 1.293340802192688,
      "learning_rate": 7.692139789240611e-05,
      "loss": 1.6341,
      "step": 62
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.3787356615066528,
      "learning_rate": 7.610438342416319e-05,
      "loss": 1.5174,
      "step": 63
    },
    {
      "epoch": 1.1082251082251082,
      "grad_norm": 1.6167194843292236,
      "learning_rate": 7.527767224312883e-05,
      "loss": 1.8773,
      "step": 64
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 1.3998445272445679,
      "learning_rate": 7.44415714387582e-05,
      "loss": 1.4874,
      "step": 65
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.5264610052108765,
      "learning_rate": 7.359639158836828e-05,
      "loss": 1.7073,
      "step": 66
    },
    {
      "epoch": 1.1601731601731602,
      "grad_norm": 1.772649884223938,
      "learning_rate": 7.274244664177097e-05,
      "loss": 1.8919,
      "step": 67
    },
    {
      "epoch": 1.1774891774891776,
      "grad_norm": 1.970308780670166,
      "learning_rate": 7.188005380465364e-05,
      "loss": 1.7385,
      "step": 68
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 2.290886878967285,
      "learning_rate": 7.10095334207501e-05,
      "loss": 1.7439,
      "step": 69
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 2.5805447101593018,
      "learning_rate": 7.013120885284598e-05,
      "loss": 1.9473,
      "step": 70
    },
    {
      "epoch": 1.2294372294372296,
      "grad_norm": 2.931612968444824,
      "learning_rate": 6.924540636266272e-05,
      "loss": 1.7793,
      "step": 71
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 3.657952308654785,
      "learning_rate": 6.835245498966461e-05,
      "loss": 1.8468,
      "step": 72
    },
    {
      "epoch": 1.2640692640692641,
      "grad_norm": 1.1832064390182495,
      "learning_rate": 6.745268642883404e-05,
      "loss": 1.3871,
      "step": 73
    },
    {
      "epoch": 1.2813852813852815,
      "grad_norm": 1.508960247039795,
      "learning_rate": 6.654643490746042e-05,
      "loss": 1.8043,
      "step": 74
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.5259658098220825,
      "learning_rate": 6.563403706098833e-05,
      "loss": 1.9086,
      "step": 75
    },
    {
      "epoch": 1.316017316017316,
      "grad_norm": 1.3969491720199585,
      "learning_rate": 6.471583180797121e-05,
      "loss": 1.3115,
      "step": 76
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.5822854042053223,
      "learning_rate": 6.379216022417696e-05,
      "loss": 1.7433,
      "step": 77
    },
    {
      "epoch": 1.3506493506493507,
      "grad_norm": 1.6488702297210693,
      "learning_rate": 6.286336541589224e-05,
      "loss": 1.6653,
      "step": 78
    },
    {
      "epoch": 1.3679653679653678,
      "grad_norm": 1.6403636932373047,
      "learning_rate": 6.192979239247243e-05,
      "loss": 1.5721,
      "step": 79
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 1.7235900163650513,
      "learning_rate": 6.0991787938184784e-05,
      "loss": 1.7767,
      "step": 80
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 1.7675573825836182,
      "learning_rate": 6.004970048339226e-05,
      "loss": 1.5971,
      "step": 81
    },
    {
      "epoch": 1.4199134199134198,
      "grad_norm": 1.861936092376709,
      "learning_rate": 5.910387997512573e-05,
      "loss": 1.7613,
      "step": 82
    },
    {
      "epoch": 1.4372294372294372,
      "grad_norm": 2.0678718090057373,
      "learning_rate": 5.8154677747093134e-05,
      "loss": 1.6704,
      "step": 83
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 2.3533997535705566,
      "learning_rate": 5.7202446389173223e-05,
      "loss": 1.8959,
      "step": 84
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 2.8441483974456787,
      "learning_rate": 5.624753961644281e-05,
      "loss": 1.6507,
      "step": 85
    },
    {
      "epoch": 1.4891774891774892,
      "grad_norm": 2.9798598289489746,
      "learning_rate": 5.5290312137786146e-05,
      "loss": 1.5216,
      "step": 86
    },
    {
      "epoch": 1.5064935064935066,
      "grad_norm": 0.9302645921707153,
      "learning_rate": 5.433111952413495e-05,
      "loss": 1.4515,
      "step": 87
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.2201461791992188,
      "learning_rate": 5.33703180763884e-05,
      "loss": 1.8394,
      "step": 88
    },
    {
      "epoch": 1.5411255411255411,
      "grad_norm": 1.2823046445846558,
      "learning_rate": 5.240826469306187e-05,
      "loss": 1.6479,
      "step": 89
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 1.375806450843811,
      "learning_rate": 5.144531673771363e-05,
      "loss": 1.4712,
      "step": 90
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.4779995679855347,
      "learning_rate": 5.048183190619904e-05,
      "loss": 1.528,
      "step": 91
    },
    {
      "epoch": 1.593073593073593,
      "grad_norm": 1.5921653509140015,
      "learning_rate": 4.951816809380097e-05,
      "loss": 1.5094,
      "step": 92
    },
    {
      "epoch": 1.6103896103896105,
      "grad_norm": 1.7217081785202026,
      "learning_rate": 4.855468326228638e-05,
      "loss": 1.5562,
      "step": 93
    },
    {
      "epoch": 1.6277056277056277,
      "grad_norm": 1.884265422821045,
      "learning_rate": 4.759173530693814e-05,
      "loss": 1.6685,
      "step": 94
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 1.9784315824508667,
      "learning_rate": 4.6629681923611603e-05,
      "loss": 1.7055,
      "step": 95
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 2.1871612071990967,
      "learning_rate": 4.566888047586507e-05,
      "loss": 1.8709,
      "step": 96
    },
    {
      "epoch": 1.6796536796536796,
      "grad_norm": 2.2329485416412354,
      "learning_rate": 4.4709687862213866e-05,
      "loss": 1.6894,
      "step": 97
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 2.2948484420776367,
      "learning_rate": 4.3752460383557195e-05,
      "loss": 1.739,
      "step": 98
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 3.3799450397491455,
      "learning_rate": 4.27975536108268e-05,
      "loss": 1.8718,
      "step": 99
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 3.0665993690490723,
      "learning_rate": 4.1845322252906864e-05,
      "loss": 1.4103,
      "step": 100
    },
    {
      "epoch": 1.7316017316017316,
      "eval_loss": 2.152366876602173,
      "eval_runtime": 4.3829,
      "eval_samples_per_second": 22.36,
      "eval_steps_per_second": 5.704,
      "step": 100
    },
    {
      "epoch": 1.7489177489177488,
      "grad_norm": 1.0602937936782837,
      "learning_rate": 4.0896120024874286e-05,
      "loss": 1.5822,
      "step": 101
    },
    {
      "epoch": 1.7662337662337664,
      "grad_norm": 1.2743157148361206,
      "learning_rate": 3.9950299516607766e-05,
      "loss": 1.4989,
      "step": 102
    },
    {
      "epoch": 1.7835497835497836,
      "grad_norm": 1.4190746545791626,
      "learning_rate": 3.900821206181521e-05,
      "loss": 1.5602,
      "step": 103
    },
    {
      "epoch": 1.8008658008658007,
      "grad_norm": 1.4261486530303955,
      "learning_rate": 3.8070207607527584e-05,
      "loss": 1.5089,
      "step": 104
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.489911437034607,
      "learning_rate": 3.713663458410779e-05,
      "loss": 1.4844,
      "step": 105
    },
    {
      "epoch": 1.8354978354978355,
      "grad_norm": 1.632286787033081,
      "learning_rate": 3.620783977582305e-05,
      "loss": 1.3581,
      "step": 106
    },
    {
      "epoch": 1.8528138528138527,
      "grad_norm": 1.6675395965576172,
      "learning_rate": 3.528416819202881e-05,
      "loss": 1.4892,
      "step": 107
    },
    {
      "epoch": 1.87012987012987,
      "grad_norm": 1.831213116645813,
      "learning_rate": 3.43659629390117e-05,
      "loss": 1.7402,
      "step": 108
    },
    {
      "epoch": 1.8874458874458875,
      "grad_norm": 2.213400363922119,
      "learning_rate": 3.345356509253959e-05,
      "loss": 1.8328,
      "step": 109
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.0512423515319824,
      "learning_rate": 3.254731357116597e-05,
      "loss": 1.6726,
      "step": 110
    },
    {
      "epoch": 1.922077922077922,
      "grad_norm": 2.2323615550994873,
      "learning_rate": 3.16475450103354e-05,
      "loss": 1.5791,
      "step": 111
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 2.652622938156128,
      "learning_rate": 3.0754593637337276e-05,
      "loss": 1.6847,
      "step": 112
    },
    {
      "epoch": 1.9567099567099566,
      "grad_norm": 3.4202094078063965,
      "learning_rate": 2.986879114715403e-05,
      "loss": 1.7346,
      "step": 113
    },
    {
      "epoch": 1.974025974025974,
      "grad_norm": 3.1738879680633545,
      "learning_rate": 2.899046657924992e-05,
      "loss": 1.4815,
      "step": 114
    },
    {
      "epoch": 1.9913419913419914,
      "grad_norm": 2.2915525436401367,
      "learning_rate": 2.8119946195346375e-05,
      "loss": 1.7886,
      "step": 115
    },
    {
      "epoch": 2.0086580086580086,
      "grad_norm": 2.1202521324157715,
      "learning_rate": 2.7257553358229034e-05,
      "loss": 1.5861,
      "step": 116
    },
    {
      "epoch": 2.0259740259740258,
      "grad_norm": 0.9431533813476562,
      "learning_rate": 2.6403608411631742e-05,
      "loss": 1.2763,
      "step": 117
    },
    {
      "epoch": 2.0432900432900434,
      "grad_norm": 1.2390758991241455,
      "learning_rate": 2.555842856124182e-05,
      "loss": 1.5445,
      "step": 118
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 1.2009048461914062,
      "learning_rate": 2.472232775687119e-05,
      "loss": 1.1775,
      "step": 119
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 1.298903465270996,
      "learning_rate": 2.389561657583681e-05,
      "loss": 1.2104,
      "step": 120
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 1.5227434635162354,
      "learning_rate": 2.30786021075939e-05,
      "loss": 1.4049,
      "step": 121
    },
    {
      "epoch": 2.1125541125541125,
      "grad_norm": 1.4139151573181152,
      "learning_rate": 2.2271587839664672e-05,
      "loss": 1.0843,
      "step": 122
    },
    {
      "epoch": 2.1298701298701297,
      "grad_norm": 1.5628201961517334,
      "learning_rate": 2.1474873544905205e-05,
      "loss": 1.2429,
      "step": 123
    },
    {
      "epoch": 2.1471861471861473,
      "grad_norm": 1.5659676790237427,
      "learning_rate": 2.0688755170151996e-05,
      "loss": 1.2155,
      "step": 124
    },
    {
      "epoch": 2.1645021645021645,
      "grad_norm": 1.9518225193023682,
      "learning_rate": 1.9913524726289784e-05,
      "loss": 1.3845,
      "step": 125
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 2.0258467197418213,
      "learning_rate": 1.914947017978153e-05,
      "loss": 1.3679,
      "step": 126
    },
    {
      "epoch": 2.1991341991341993,
      "grad_norm": 2.1336464881896973,
      "learning_rate": 1.8396875345700497e-05,
      "loss": 1.1927,
      "step": 127
    },
    {
      "epoch": 2.2164502164502164,
      "grad_norm": 2.576885223388672,
      "learning_rate": 1.76560197823046e-05,
      "loss": 1.3654,
      "step": 128
    },
    {
      "epoch": 2.2337662337662336,
      "grad_norm": 3.152988910675049,
      "learning_rate": 1.692717868719195e-05,
      "loss": 1.1457,
      "step": 129
    },
    {
      "epoch": 2.2510822510822512,
      "grad_norm": 2.0141236782073975,
      "learning_rate": 1.621062279507617e-05,
      "loss": 1.0657,
      "step": 130
    },
    {
      "epoch": 2.2683982683982684,
      "grad_norm": 1.1057418584823608,
      "learning_rate": 1.550661827721941e-05,
      "loss": 1.165,
      "step": 131
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.397590160369873,
      "learning_rate": 1.4815426642560754e-05,
      "loss": 1.353,
      "step": 132
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 1.6015745401382446,
      "learning_rate": 1.413730464057616e-05,
      "loss": 1.4035,
      "step": 133
    },
    {
      "epoch": 2.3203463203463204,
      "grad_norm": 1.6769520044326782,
      "learning_rate": 1.3472504165906613e-05,
      "loss": 1.1582,
      "step": 134
    },
    {
      "epoch": 2.3376623376623376,
      "grad_norm": 1.7901424169540405,
      "learning_rate": 1.2821272164789544e-05,
      "loss": 1.2517,
      "step": 135
    },
    {
      "epoch": 2.354978354978355,
      "grad_norm": 1.8109772205352783,
      "learning_rate": 1.2183850543328312e-05,
      "loss": 1.1572,
      "step": 136
    },
    {
      "epoch": 2.3722943722943723,
      "grad_norm": 1.9784982204437256,
      "learning_rate": 1.156047607763407e-05,
      "loss": 1.2877,
      "step": 137
    },
    {
      "epoch": 2.3896103896103895,
      "grad_norm": 2.1514012813568115,
      "learning_rate": 1.0951380325872979e-05,
      "loss": 1.2136,
      "step": 138
    },
    {
      "epoch": 2.4069264069264067,
      "grad_norm": 2.4231860637664795,
      "learning_rate": 1.0356789542251938e-05,
      "loss": 1.3005,
      "step": 139
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 2.3579273223876953,
      "learning_rate": 9.776924592974256e-06,
      "loss": 1.189,
      "step": 140
    },
    {
      "epoch": 2.4415584415584415,
      "grad_norm": 2.524210214614868,
      "learning_rate": 9.212000874196953e-06,
      "loss": 1.2174,
      "step": 141
    },
    {
      "epoch": 2.458874458874459,
      "grad_norm": 3.0270493030548096,
      "learning_rate": 8.662228232019876e-06,
      "loss": 1.4422,
      "step": 142
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 3.490323781967163,
      "learning_rate": 8.127810884536403e-06,
      "loss": 1.0179,
      "step": 143
    },
    {
      "epoch": 2.4935064935064934,
      "grad_norm": 2.0213398933410645,
      "learning_rate": 7.60894734597476e-06,
      "loss": 1.0308,
      "step": 144
    },
    {
      "epoch": 2.5108225108225106,
      "grad_norm": 1.3074225187301636,
      "learning_rate": 7.105830352958142e-06,
      "loss": 1.3988,
      "step": 145
    },
    {
      "epoch": 2.5281385281385282,
      "grad_norm": 1.4296869039535522,
      "learning_rate": 6.618646792910893e-06,
      "loss": 1.2677,
      "step": 146
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.7244904041290283,
      "learning_rate": 6.147577634637414e-06,
      "loss": 1.3325,
      "step": 147
    },
    {
      "epoch": 2.562770562770563,
      "grad_norm": 1.5574814081192017,
      "learning_rate": 5.692797861099719e-06,
      "loss": 1.0583,
      "step": 148
    },
    {
      "epoch": 2.58008658008658,
      "grad_norm": 1.9222928285598755,
      "learning_rate": 5.25447640441834e-06,
      "loss": 1.2119,
      "step": 149
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 1.9380241632461548,
      "learning_rate": 4.832776083120982e-06,
      "loss": 1.3008,
      "step": 150
    },
    {
      "epoch": 2.5974025974025974,
      "eval_loss": 2.2245595455169678,
      "eval_runtime": 4.3825,
      "eval_samples_per_second": 22.362,
      "eval_steps_per_second": 5.704,
      "step": 150
    },
    {
      "epoch": 2.6147186147186146,
      "grad_norm": 1.8181335926055908,
      "learning_rate": 4.427853541662091e-06,
      "loss": 1.155,
      "step": 151
    },
    {
      "epoch": 2.632034632034632,
      "grad_norm": 2.2399914264678955,
      "learning_rate": 4.039859192235779e-06,
      "loss": 1.3334,
      "step": 152
    },
    {
      "epoch": 2.6493506493506493,
      "grad_norm": 2.19873309135437,
      "learning_rate": 3.668937158903901e-06,
      "loss": 1.3053,
      "step": 153
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 2.5052037239074707,
      "learning_rate": 3.315225224059809e-06,
      "loss": 1.3906,
      "step": 154
    },
    {
      "epoch": 2.683982683982684,
      "grad_norm": 2.5421435832977295,
      "learning_rate": 2.9788547772478416e-06,
      "loss": 1.3269,
      "step": 155
    },
    {
      "epoch": 2.7012987012987013,
      "grad_norm": 2.761349678039551,
      "learning_rate": 2.6599507663574384e-06,
      "loss": 1.2917,
      "step": 156
    },
    {
      "epoch": 2.7186147186147185,
      "grad_norm": 3.4365580081939697,
      "learning_rate": 2.3586316512101416e-06,
      "loss": 1.0455,
      "step": 157
    },
    {
      "epoch": 2.7359307359307357,
      "grad_norm": 2.1280157566070557,
      "learning_rate": 2.0750093595565733e-06,
      "loss": 0.9159,
      "step": 158
    },
    {
      "epoch": 2.7532467532467533,
      "grad_norm": 1.2609156370162964,
      "learning_rate": 1.8091892454998594e-06,
      "loss": 1.3023,
      "step": 159
    },
    {
      "epoch": 2.7705627705627704,
      "grad_norm": 1.4564933776855469,
      "learning_rate": 1.5612700503608968e-06,
      "loss": 1.2887,
      "step": 160
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 1.5543081760406494,
      "learning_rate": 1.33134386599994e-06,
      "loss": 1.3596,
      "step": 161
    },
    {
      "epoch": 2.8051948051948052,
      "grad_norm": 1.5681473016738892,
      "learning_rate": 1.1194961006082972e-06,
      "loss": 1.0265,
      "step": 162
    },
    {
      "epoch": 2.8225108225108224,
      "grad_norm": 1.7594598531723022,
      "learning_rate": 9.258054469825972e-07,
      "loss": 1.2222,
      "step": 163
    },
    {
      "epoch": 2.8398268398268396,
      "grad_norm": 1.896242618560791,
      "learning_rate": 7.503438532937168e-07,
      "loss": 1.2466,
      "step": 164
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.9518426656723022,
      "learning_rate": 5.931764963608866e-07,
      "loss": 1.2796,
      "step": 165
    },
    {
      "epoch": 2.8744588744588744,
      "grad_norm": 2.096078634262085,
      "learning_rate": 4.543617574412184e-07,
      "loss": 1.263,
      "step": 166
    },
    {
      "epoch": 2.891774891774892,
      "grad_norm": 2.4194352626800537,
      "learning_rate": 3.339512005434309e-07,
      "loss": 1.4151,
      "step": 167
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 2.55708384513855,
      "learning_rate": 2.319895532739369e-07,
      "loss": 1.3309,
      "step": 168
    },
    {
      "epoch": 2.9264069264069263,
      "grad_norm": 2.496046304702759,
      "learning_rate": 1.4851469022234e-07,
      "loss": 1.2512,
      "step": 169
    },
    {
      "epoch": 2.9437229437229435,
      "grad_norm": 2.801349639892578,
      "learning_rate": 8.355761889260461e-08,
      "loss": 1.2877,
      "step": 170
    },
    {
      "epoch": 2.961038961038961,
      "grad_norm": 4.023518085479736,
      "learning_rate": 3.7142468185014104e-08,
      "loss": 1.2639,
      "step": 171
    },
    {
      "epoch": 2.9783549783549783,
      "grad_norm": 2.5057783126831055,
      "learning_rate": 9.286479433257e-09,
      "loss": 1.1965,
      "step": 172
    },
    {
      "epoch": 2.995670995670996,
      "grad_norm": 3.9870026111602783,
      "learning_rate": 0.0,
      "loss": 1.3747,
      "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
}