{
  "best_metric": 0.22548285126686096,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 1.219157338142395,
      "learning_rate": 5e-06,
      "loss": 0.8063,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 0.7730486392974854,
      "eval_runtime": 14.8632,
      "eval_samples_per_second": 12.178,
      "eval_steps_per_second": 3.095,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 1.7119722366333008,
      "learning_rate": 1e-05,
      "loss": 0.8924,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 1.5100245475769043,
      "learning_rate": 1.5e-05,
      "loss": 0.6591,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 1.3723516464233398,
      "learning_rate": 2e-05,
      "loss": 0.462,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 1.1930196285247803,
      "learning_rate": 2.5e-05,
      "loss": 0.4925,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.3553060293197632,
      "learning_rate": 3e-05,
      "loss": 0.4217,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 1.2735092639923096,
      "learning_rate": 3.5e-05,
      "loss": 0.4065,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.3319530487060547,
      "learning_rate": 4e-05,
      "loss": 0.504,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 1.405493140220642,
      "learning_rate": 4.5e-05,
      "loss": 0.4416,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.4536367654800415,
      "learning_rate": 5e-05,
      "loss": 0.3942,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 0.9741217494010925,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.3058,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.8427817225456238,
      "learning_rate": 6e-05,
      "loss": 0.3532,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.992837131023407,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.3923,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 1.4447782039642334,
      "learning_rate": 7e-05,
      "loss": 0.4725,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 1.0296854972839355,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3854,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.047565221786499,
      "learning_rate": 8e-05,
      "loss": 0.4919,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 1.0961558818817139,
      "learning_rate": 8.5e-05,
      "loss": 0.461,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.8683053255081177,
      "learning_rate": 9e-05,
      "loss": 0.3748,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.8468982577323914,
      "learning_rate": 9.5e-05,
      "loss": 0.451,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.9975036978721619,
      "learning_rate": 0.0001,
      "loss": 0.453,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 1.0233877897262573,
      "learning_rate": 9.996740476948385e-05,
      "loss": 0.4505,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.9718571901321411,
      "learning_rate": 9.98696615758975e-05,
      "loss": 0.3857,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 1.1713796854019165,
      "learning_rate": 9.970689785771798e-05,
      "loss": 0.4409,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 1.089770793914795,
      "learning_rate": 9.947932582778188e-05,
      "loss": 0.5367,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 1.1054497957229614,
      "learning_rate": 9.918724219660013e-05,
      "loss": 0.5278,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 1.2821669578552246,
      "learning_rate": 9.883102778550434e-05,
      "loss": 0.4241,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 1.2064378261566162,
      "learning_rate": 9.841114703012817e-05,
      "loss": 0.5981,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.9326714277267456,
      "learning_rate": 9.792814737487207e-05,
      "loss": 0.5156,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.6832557916641235,
      "learning_rate": 9.738265855914013e-05,
      "loss": 0.2917,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.5775344967842102,
      "learning_rate": 9.677539179628005e-05,
      "loss": 0.1908,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.6104221343994141,
      "learning_rate": 9.610713884629666e-05,
      "loss": 0.1956,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.5428737998008728,
      "learning_rate": 9.537877098354786e-05,
      "loss": 0.2339,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.833243727684021,
      "learning_rate": 9.459123786076912e-05,
      "loss": 0.3178,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.7536976337432861,
      "learning_rate": 9.374556627090749e-05,
      "loss": 0.3205,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 0.76767897605896,
      "learning_rate": 9.284285880837946e-05,
      "loss": 0.3133,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 0.6184180974960327,
      "learning_rate": 9.188429243149824e-05,
      "loss": 0.2139,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 0.7646700143814087,
      "learning_rate": 9.087111692794459e-05,
      "loss": 0.3285,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.7544060349464417,
      "learning_rate": 8.980465328528219e-05,
      "loss": 0.3763,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 0.6204481720924377,
      "learning_rate": 8.868629196864182e-05,
      "loss": 0.2277,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.7366188764572144,
      "learning_rate": 8.751749110782012e-05,
      "loss": 0.3514,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 0.7830935120582581,
      "learning_rate": 8.629977459615655e-05,
      "loss": 0.3578,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.7259529829025269,
      "learning_rate": 8.503473010366713e-05,
      "loss": 0.3621,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 0.9217443466186523,
      "learning_rate": 8.37240070070257e-05,
      "loss": 0.3575,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 1.0388785600662231,
      "learning_rate": 8.236931423909138e-05,
      "loss": 0.3794,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.9039023518562317,
      "learning_rate": 8.097241806078615e-05,
      "loss": 0.3187,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.827473521232605,
      "learning_rate": 7.953513975822755e-05,
      "loss": 0.3712,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.8149646520614624,
      "learning_rate": 7.805935326811912e-05,
      "loss": 0.3352,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.8157217502593994,
      "learning_rate": 7.654698273449435e-05,
      "loss": 0.3255,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.8530291318893433,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2957,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.9379925727844238,
      "learning_rate": 7.342042203498951e-05,
      "loss": 0.3483,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": 1.189587950706482,
      "learning_rate": 7.181030830777837e-05,
      "loss": 0.3288,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 0.9817992448806763,
      "learning_rate": 7.017175809949044e-05,
      "loss": 0.3369,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": 0.6129629015922546,
      "learning_rate": 6.850690776699573e-05,
      "loss": 0.388,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 1.1100006103515625,
      "learning_rate": 6.681792795750875e-05,
      "loss": 0.7037,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": 0.5911304950714111,
      "learning_rate": 6.510702077847863e-05,
      "loss": 0.2106,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.5433168411254883,
      "learning_rate": 6.337641692646106e-05,
      "loss": 0.1864,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": 0.6343222856521606,
      "learning_rate": 6.162837277871553e-05,
      "loss": 0.1989,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 0.6482139825820923,
      "learning_rate": 5.9865167451320005e-05,
      "loss": 0.1979,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": 0.5622913837432861,
      "learning_rate": 5.808909982763825e-05,
      "loss": 0.2228,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.6482579112052917,
      "learning_rate": 5.6302485561014475e-05,
      "loss": 0.26,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": 0.5825400948524475,
      "learning_rate": 5.4507654055603275e-05,
      "loss": 0.2134,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 0.6285723447799683,
      "learning_rate": 5.270694542927088e-05,
      "loss": 0.1732,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": 0.7923870086669922,
      "learning_rate": 5.090270746252802e-05,
      "loss": 0.2472,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.5260159969329834,
      "learning_rate": 4.909729253747197e-05,
      "loss": 0.1921,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": 0.881934642791748,
      "learning_rate": 4.729305457072913e-05,
      "loss": 0.3575,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 0.7392538785934448,
      "learning_rate": 4.549234594439674e-05,
      "loss": 0.2821,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": 0.8430290818214417,
      "learning_rate": 4.3697514438985536e-05,
      "loss": 0.3758,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 0.6846808195114136,
      "learning_rate": 4.1910900172361764e-05,
      "loss": 0.2926,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": 0.7678614854812622,
      "learning_rate": 4.0134832548680006e-05,
      "loss": 0.3424,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.8086291551589966,
      "learning_rate": 3.8371627221284495e-05,
      "loss": 0.3233,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": 0.7273069024085999,
      "learning_rate": 3.6623583073538966e-05,
      "loss": 0.3083,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.7899916172027588,
      "learning_rate": 3.489297922152136e-05,
      "loss": 0.3279,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": 0.789638340473175,
      "learning_rate": 3.3182072042491244e-05,
      "loss": 0.2258,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 0.7459571361541748,
      "learning_rate": 3.149309223300428e-05,
      "loss": 0.2821,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 0.7506718039512634,
      "learning_rate": 2.982824190050958e-05,
      "loss": 0.2913,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.9580733180046082,
      "learning_rate": 2.8189691692221627e-05,
      "loss": 0.291,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": 0.7518978714942932,
      "learning_rate": 2.65795779650105e-05,
      "loss": 0.2862,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 1.0413604974746704,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3709,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": 0.6182491183280945,
      "learning_rate": 2.3453017265505673e-05,
      "loss": 0.5246,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.948544442653656,
      "learning_rate": 2.194064673188089e-05,
      "loss": 0.4829,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": 0.5522446632385254,
      "learning_rate": 2.0464860241772455e-05,
      "loss": 0.206,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 0.40932267904281616,
      "learning_rate": 1.902758193921385e-05,
      "loss": 0.1145,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": 0.5272003412246704,
      "learning_rate": 1.7630685760908622e-05,
      "loss": 0.2035,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 0.5209049582481384,
      "learning_rate": 1.6275992992974308e-05,
      "loss": 0.1672,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": 0.7782484292984009,
      "learning_rate": 1.4965269896332885e-05,
      "loss": 0.3367,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.6654481291770935,
      "learning_rate": 1.3700225403843469e-05,
      "loss": 0.2275,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": 0.7058405876159668,
      "learning_rate": 1.2482508892179884e-05,
      "loss": 0.2104,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.588880717754364,
      "learning_rate": 1.1313708031358183e-05,
      "loss": 0.1839,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": 0.5858724117279053,
      "learning_rate": 1.0195346714717813e-05,
      "loss": 0.2116,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.6534013748168945,
      "learning_rate": 9.12888307205541e-06,
      "loss": 0.2299,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": 0.8321280479431152,
      "learning_rate": 8.115707568501768e-06,
      "loss": 0.2796,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 0.6398549675941467,
      "learning_rate": 7.157141191620548e-06,
      "loss": 0.2129,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": 0.5791231989860535,
      "learning_rate": 6.2544337290925185e-06,
      "loss": 0.2257,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 0.7193149924278259,
      "learning_rate": 5.408762139230888e-06,
      "loss": 0.2494,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": 0.6383216381072998,
      "learning_rate": 4.621229016452156e-06,
      "loss": 0.2472,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.5994362831115723,
      "learning_rate": 3.892861153703342e-06,
      "loss": 0.2441,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": 0.5224132537841797,
      "learning_rate": 3.2246082037199532e-06,
      "loss": 0.1762,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 0.5928333401679993,
      "learning_rate": 2.6173414408598827e-06,
      "loss": 0.2302,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": 0.6083561182022095,
      "learning_rate": 2.0718526251279346e-06,
      "loss": 0.227,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.568109393119812,
      "learning_rate": 1.5888529698718346e-06,
      "loss": 0.1576,
      "step": 100
    },
    {
      "epoch": 0.9345794392523364,
      "eval_loss": 0.22548285126686096,
      "eval_runtime": 15.1343,
      "eval_samples_per_second": 11.96,
      "eval_steps_per_second": 3.039,
      "step": 100
    },
    {
      "epoch": 0.9439252336448598,
      "grad_norm": 0.7059941291809082,
      "learning_rate": 1.1689722144956671e-06,
      "loss": 0.2496,
      "step": 101
    },
    {
      "epoch": 0.9532710280373832,
      "grad_norm": 0.6286365985870361,
      "learning_rate": 8.127578033998662e-07,
      "loss": 0.1745,
      "step": 102
    },
    {
      "epoch": 0.9626168224299065,
      "grad_norm": 0.7547852993011475,
      "learning_rate": 5.206741722181386e-07,
      "loss": 0.2797,
      "step": 103
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 0.7173730134963989,
      "learning_rate": 2.9310214228202013e-07,
      "loss": 0.258,
      "step": 104
    },
    {
      "epoch": 0.9813084112149533,
      "grad_norm": 0.5055248737335205,
      "learning_rate": 1.3033842410251075e-07,
      "loss": 0.2182,
      "step": 105
    },
    {
      "epoch": 0.9906542056074766,
      "grad_norm": 0.6892708539962769,
      "learning_rate": 3.259523051615254e-08,
      "loss": 0.312,
      "step": 106
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.596139669418335,
      "learning_rate": 0.0,
      "loss": 0.2149,
      "step": 107
    }
  ],
  "logging_steps": 1,
  "max_steps": 107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.7536470352920576e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}