{
  "best_metric": 0.5862807035446167,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.20171457387796268,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010085728693898135,
      "grad_norm": 1.3256633281707764,
      "learning_rate": 1.001e-05,
      "loss": 0.928,
      "step": 1
    },
    {
      "epoch": 0.0010085728693898135,
      "eval_loss": 1.1040126085281372,
      "eval_runtime": 101.7443,
      "eval_samples_per_second": 4.108,
      "eval_steps_per_second": 1.032,
      "step": 1
    },
    {
      "epoch": 0.002017145738779627,
      "grad_norm": 1.474454641342163,
      "learning_rate": 2.002e-05,
      "loss": 1.1291,
      "step": 2
    },
    {
      "epoch": 0.0030257186081694403,
      "grad_norm": 1.6319197416305542,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 1.0949,
      "step": 3
    },
    {
      "epoch": 0.004034291477559254,
      "grad_norm": 1.4987621307373047,
      "learning_rate": 4.004e-05,
      "loss": 1.0647,
      "step": 4
    },
    {
      "epoch": 0.005042864346949067,
      "grad_norm": 1.5046451091766357,
      "learning_rate": 5.005e-05,
      "loss": 1.1549,
      "step": 5
    },
    {
      "epoch": 0.006051437216338881,
      "grad_norm": 1.1391572952270508,
      "learning_rate": 6.005999999999999e-05,
      "loss": 0.8795,
      "step": 6
    },
    {
      "epoch": 0.0070600100857286935,
      "grad_norm": 1.1890026330947876,
      "learning_rate": 7.006999999999998e-05,
      "loss": 0.7941,
      "step": 7
    },
    {
      "epoch": 0.008068582955118508,
      "grad_norm": 0.9730799794197083,
      "learning_rate": 8.008e-05,
      "loss": 0.7905,
      "step": 8
    },
    {
      "epoch": 0.009077155824508321,
      "grad_norm": 1.2554188966751099,
      "learning_rate": 9.009e-05,
      "loss": 0.8911,
      "step": 9
    },
    {
      "epoch": 0.010085728693898134,
      "grad_norm": 0.9880374073982239,
      "learning_rate": 0.0001001,
      "loss": 0.7361,
      "step": 10
    },
    {
      "epoch": 0.011094301563287948,
      "grad_norm": 0.9911070466041565,
      "learning_rate": 9.957315789473684e-05,
      "loss": 0.7875,
      "step": 11
    },
    {
      "epoch": 0.012102874432677761,
      "grad_norm": 0.9050823450088501,
      "learning_rate": 9.904631578947367e-05,
      "loss": 0.7264,
      "step": 12
    },
    {
      "epoch": 0.013111447302067574,
      "grad_norm": 0.7732548713684082,
      "learning_rate": 9.851947368421052e-05,
      "loss": 0.6789,
      "step": 13
    },
    {
      "epoch": 0.014120020171457387,
      "grad_norm": 0.7884408235549927,
      "learning_rate": 9.799263157894736e-05,
      "loss": 0.6478,
      "step": 14
    },
    {
      "epoch": 0.015128593040847202,
      "grad_norm": 0.7742847204208374,
      "learning_rate": 9.746578947368421e-05,
      "loss": 0.6509,
      "step": 15
    },
    {
      "epoch": 0.016137165910237016,
      "grad_norm": 0.8024091124534607,
      "learning_rate": 9.693894736842104e-05,
      "loss": 0.5802,
      "step": 16
    },
    {
      "epoch": 0.01714573877962683,
      "grad_norm": 0.7542886734008789,
      "learning_rate": 9.641210526315789e-05,
      "loss": 0.5653,
      "step": 17
    },
    {
      "epoch": 0.018154311649016642,
      "grad_norm": 1.0057110786437988,
      "learning_rate": 9.588526315789473e-05,
      "loss": 0.8099,
      "step": 18
    },
    {
      "epoch": 0.019162884518406455,
      "grad_norm": 0.7922680377960205,
      "learning_rate": 9.535842105263157e-05,
      "loss": 0.5516,
      "step": 19
    },
    {
      "epoch": 0.020171457387796268,
      "grad_norm": 0.7331287860870361,
      "learning_rate": 9.483157894736841e-05,
      "loss": 0.6412,
      "step": 20
    },
    {
      "epoch": 0.02118003025718608,
      "grad_norm": 0.720295786857605,
      "learning_rate": 9.430473684210526e-05,
      "loss": 0.6343,
      "step": 21
    },
    {
      "epoch": 0.022188603126575897,
      "grad_norm": 0.735260546207428,
      "learning_rate": 9.37778947368421e-05,
      "loss": 0.524,
      "step": 22
    },
    {
      "epoch": 0.02319717599596571,
      "grad_norm": 0.795688807964325,
      "learning_rate": 9.325105263157894e-05,
      "loss": 0.7379,
      "step": 23
    },
    {
      "epoch": 0.024205748865355523,
      "grad_norm": 0.9573493003845215,
      "learning_rate": 9.272421052631578e-05,
      "loss": 0.655,
      "step": 24
    },
    {
      "epoch": 0.025214321734745335,
      "grad_norm": 0.8053199648857117,
      "learning_rate": 9.219736842105263e-05,
      "loss": 0.6542,
      "step": 25
    },
    {
      "epoch": 0.026222894604135148,
      "grad_norm": 0.7771440744400024,
      "learning_rate": 9.167052631578946e-05,
      "loss": 0.6446,
      "step": 26
    },
    {
      "epoch": 0.02723146747352496,
      "grad_norm": 0.827423095703125,
      "learning_rate": 9.114368421052632e-05,
      "loss": 0.5206,
      "step": 27
    },
    {
      "epoch": 0.028240040342914774,
      "grad_norm": 0.846246600151062,
      "learning_rate": 9.061684210526315e-05,
      "loss": 0.6852,
      "step": 28
    },
    {
      "epoch": 0.02924861321230459,
      "grad_norm": 0.8435190320014954,
      "learning_rate": 9.009e-05,
      "loss": 0.6365,
      "step": 29
    },
    {
      "epoch": 0.030257186081694403,
      "grad_norm": 0.9337050318717957,
      "learning_rate": 8.956315789473683e-05,
      "loss": 0.7902,
      "step": 30
    },
    {
      "epoch": 0.031265758951084216,
      "grad_norm": 0.8614511489868164,
      "learning_rate": 8.903631578947368e-05,
      "loss": 0.8011,
      "step": 31
    },
    {
      "epoch": 0.03227433182047403,
      "grad_norm": 0.7659604549407959,
      "learning_rate": 8.850947368421052e-05,
      "loss": 0.6453,
      "step": 32
    },
    {
      "epoch": 0.03328290468986384,
      "grad_norm": 0.8630499243736267,
      "learning_rate": 8.798263157894736e-05,
      "loss": 0.7389,
      "step": 33
    },
    {
      "epoch": 0.03429147755925366,
      "grad_norm": 0.8765709400177002,
      "learning_rate": 8.745578947368422e-05,
      "loss": 0.7189,
      "step": 34
    },
    {
      "epoch": 0.03530005042864347,
      "grad_norm": 0.8526920676231384,
      "learning_rate": 8.692894736842105e-05,
      "loss": 0.8088,
      "step": 35
    },
    {
      "epoch": 0.036308623298033284,
      "grad_norm": 0.8917660117149353,
      "learning_rate": 8.64021052631579e-05,
      "loss": 0.7846,
      "step": 36
    },
    {
      "epoch": 0.03731719616742309,
      "grad_norm": 0.8361109495162964,
      "learning_rate": 8.587526315789473e-05,
      "loss": 0.7397,
      "step": 37
    },
    {
      "epoch": 0.03832576903681291,
      "grad_norm": 0.7644747495651245,
      "learning_rate": 8.534842105263157e-05,
      "loss": 0.7195,
      "step": 38
    },
    {
      "epoch": 0.039334341906202726,
      "grad_norm": 0.7715050578117371,
      "learning_rate": 8.482157894736842e-05,
      "loss": 0.646,
      "step": 39
    },
    {
      "epoch": 0.040342914775592535,
      "grad_norm": 0.7674934267997742,
      "learning_rate": 8.429473684210525e-05,
      "loss": 0.6252,
      "step": 40
    },
    {
      "epoch": 0.04135148764498235,
      "grad_norm": 0.8960989713668823,
      "learning_rate": 8.376789473684211e-05,
      "loss": 0.7325,
      "step": 41
    },
    {
      "epoch": 0.04236006051437216,
      "grad_norm": 0.9191142916679382,
      "learning_rate": 8.324105263157894e-05,
      "loss": 0.8292,
      "step": 42
    },
    {
      "epoch": 0.04336863338376198,
      "grad_norm": 1.0036343336105347,
      "learning_rate": 8.271421052631579e-05,
      "loss": 0.8007,
      "step": 43
    },
    {
      "epoch": 0.044377206253151794,
      "grad_norm": 0.9207143783569336,
      "learning_rate": 8.218736842105262e-05,
      "loss": 0.7683,
      "step": 44
    },
    {
      "epoch": 0.0453857791225416,
      "grad_norm": 0.8968362212181091,
      "learning_rate": 8.166052631578947e-05,
      "loss": 0.7219,
      "step": 45
    },
    {
      "epoch": 0.04639435199193142,
      "grad_norm": 0.9199109077453613,
      "learning_rate": 8.113368421052631e-05,
      "loss": 0.7528,
      "step": 46
    },
    {
      "epoch": 0.04740292486132123,
      "grad_norm": 0.8678332567214966,
      "learning_rate": 8.060684210526315e-05,
      "loss": 0.7749,
      "step": 47
    },
    {
      "epoch": 0.048411497730711045,
      "grad_norm": 1.1632949113845825,
      "learning_rate": 8.008e-05,
      "loss": 0.802,
      "step": 48
    },
    {
      "epoch": 0.049420070600100854,
      "grad_norm": 0.9920008182525635,
      "learning_rate": 7.955315789473684e-05,
      "loss": 0.7985,
      "step": 49
    },
    {
      "epoch": 0.05042864346949067,
      "grad_norm": 1.165090799331665,
      "learning_rate": 7.902631578947368e-05,
      "loss": 0.8537,
      "step": 50
    },
    {
      "epoch": 0.05042864346949067,
      "eval_loss": 0.6654149293899536,
      "eval_runtime": 101.9851,
      "eval_samples_per_second": 4.099,
      "eval_steps_per_second": 1.03,
      "step": 50
    },
    {
      "epoch": 0.05143721633888049,
      "grad_norm": 0.75869220495224,
      "learning_rate": 7.849947368421052e-05,
      "loss": 0.4562,
      "step": 51
    },
    {
      "epoch": 0.052445789208270296,
      "grad_norm": 0.6621689200401306,
      "learning_rate": 7.797263157894736e-05,
      "loss": 0.6621,
      "step": 52
    },
    {
      "epoch": 0.05345436207766011,
      "grad_norm": 0.7413565516471863,
      "learning_rate": 7.744578947368421e-05,
      "loss": 0.7538,
      "step": 53
    },
    {
      "epoch": 0.05446293494704992,
      "grad_norm": 0.6686313152313232,
      "learning_rate": 7.691894736842104e-05,
      "loss": 0.6138,
      "step": 54
    },
    {
      "epoch": 0.05547150781643974,
      "grad_norm": 0.7127124071121216,
      "learning_rate": 7.63921052631579e-05,
      "loss": 0.6288,
      "step": 55
    },
    {
      "epoch": 0.05648008068582955,
      "grad_norm": 0.6435994505882263,
      "learning_rate": 7.586526315789473e-05,
      "loss": 0.622,
      "step": 56
    },
    {
      "epoch": 0.057488653555219364,
      "grad_norm": 0.8834062814712524,
      "learning_rate": 7.533842105263158e-05,
      "loss": 0.6526,
      "step": 57
    },
    {
      "epoch": 0.05849722642460918,
      "grad_norm": 0.8443036675453186,
      "learning_rate": 7.481157894736841e-05,
      "loss": 0.5807,
      "step": 58
    },
    {
      "epoch": 0.05950579929399899,
      "grad_norm": 0.6164169907569885,
      "learning_rate": 7.428473684210526e-05,
      "loss": 0.4989,
      "step": 59
    },
    {
      "epoch": 0.060514372163388806,
      "grad_norm": 0.6870154738426208,
      "learning_rate": 7.375789473684209e-05,
      "loss": 0.4892,
      "step": 60
    },
    {
      "epoch": 0.061522945032778616,
      "grad_norm": 0.7605435252189636,
      "learning_rate": 7.323105263157895e-05,
      "loss": 0.7713,
      "step": 61
    },
    {
      "epoch": 0.06253151790216843,
      "grad_norm": 0.7348607778549194,
      "learning_rate": 7.270421052631578e-05,
      "loss": 0.574,
      "step": 62
    },
    {
      "epoch": 0.06354009077155824,
      "grad_norm": 0.7731995582580566,
      "learning_rate": 7.217736842105263e-05,
      "loss": 0.6948,
      "step": 63
    },
    {
      "epoch": 0.06454866364094806,
      "grad_norm": 0.6861239671707153,
      "learning_rate": 7.165052631578947e-05,
      "loss": 0.6096,
      "step": 64
    },
    {
      "epoch": 0.06555723651033787,
      "grad_norm": 0.7161320447921753,
      "learning_rate": 7.11236842105263e-05,
      "loss": 0.6452,
      "step": 65
    },
    {
      "epoch": 0.06656580937972768,
      "grad_norm": 0.6679670810699463,
      "learning_rate": 7.059684210526315e-05,
      "loss": 0.5389,
      "step": 66
    },
    {
      "epoch": 0.06757438224911749,
      "grad_norm": 0.693910539150238,
      "learning_rate": 7.006999999999998e-05,
      "loss": 0.6802,
      "step": 67
    },
    {
      "epoch": 0.06858295511850732,
      "grad_norm": 0.6923498511314392,
      "learning_rate": 6.954315789473684e-05,
      "loss": 0.5447,
      "step": 68
    },
    {
      "epoch": 0.06959152798789713,
      "grad_norm": 0.7874863147735596,
      "learning_rate": 6.901631578947368e-05,
      "loss": 0.7356,
      "step": 69
    },
    {
      "epoch": 0.07060010085728693,
      "grad_norm": 0.5882103443145752,
      "learning_rate": 6.848947368421052e-05,
      "loss": 0.4963,
      "step": 70
    },
    {
      "epoch": 0.07160867372667676,
      "grad_norm": 0.7045419812202454,
      "learning_rate": 6.796263157894737e-05,
      "loss": 0.5469,
      "step": 71
    },
    {
      "epoch": 0.07261724659606657,
      "grad_norm": 0.7635371685028076,
      "learning_rate": 6.74357894736842e-05,
      "loss": 0.5583,
      "step": 72
    },
    {
      "epoch": 0.07362581946545638,
      "grad_norm": 0.6490672826766968,
      "learning_rate": 6.690894736842105e-05,
      "loss": 0.5297,
      "step": 73
    },
    {
      "epoch": 0.07463439233484619,
      "grad_norm": 0.7709025740623474,
      "learning_rate": 6.638210526315788e-05,
      "loss": 0.6782,
      "step": 74
    },
    {
      "epoch": 0.07564296520423601,
      "grad_norm": 0.7329003810882568,
      "learning_rate": 6.585526315789474e-05,
      "loss": 0.6662,
      "step": 75
    },
    {
      "epoch": 0.07665153807362582,
      "grad_norm": 0.6491856575012207,
      "learning_rate": 6.532842105263157e-05,
      "loss": 0.5737,
      "step": 76
    },
    {
      "epoch": 0.07766011094301563,
      "grad_norm": 0.7173510789871216,
      "learning_rate": 6.480157894736842e-05,
      "loss": 0.5759,
      "step": 77
    },
    {
      "epoch": 0.07866868381240545,
      "grad_norm": 0.6393573880195618,
      "learning_rate": 6.427473684210526e-05,
      "loss": 0.502,
      "step": 78
    },
    {
      "epoch": 0.07967725668179526,
      "grad_norm": 0.843249499797821,
      "learning_rate": 6.37478947368421e-05,
      "loss": 0.5322,
      "step": 79
    },
    {
      "epoch": 0.08068582955118507,
      "grad_norm": 0.8811123371124268,
      "learning_rate": 6.322105263157894e-05,
      "loss": 0.6599,
      "step": 80
    },
    {
      "epoch": 0.08169440242057488,
      "grad_norm": 0.7545380592346191,
      "learning_rate": 6.269421052631577e-05,
      "loss": 0.6079,
      "step": 81
    },
    {
      "epoch": 0.0827029752899647,
      "grad_norm": 0.6854647397994995,
      "learning_rate": 6.216736842105263e-05,
      "loss": 0.5863,
      "step": 82
    },
    {
      "epoch": 0.08371154815935451,
      "grad_norm": 0.7682092785835266,
      "learning_rate": 6.164052631578947e-05,
      "loss": 0.6459,
      "step": 83
    },
    {
      "epoch": 0.08472012102874432,
      "grad_norm": 0.7870449423789978,
      "learning_rate": 6.111368421052631e-05,
      "loss": 0.6161,
      "step": 84
    },
    {
      "epoch": 0.08572869389813415,
      "grad_norm": 0.7527886033058167,
      "learning_rate": 6.058684210526315e-05,
      "loss": 0.6622,
      "step": 85
    },
    {
      "epoch": 0.08673726676752395,
      "grad_norm": 0.7345116138458252,
      "learning_rate": 6.005999999999999e-05,
      "loss": 0.6325,
      "step": 86
    },
    {
      "epoch": 0.08774583963691376,
      "grad_norm": 0.7864583730697632,
      "learning_rate": 5.953315789473684e-05,
      "loss": 0.6947,
      "step": 87
    },
    {
      "epoch": 0.08875441250630359,
      "grad_norm": 0.8470887541770935,
      "learning_rate": 5.9006315789473676e-05,
      "loss": 0.6575,
      "step": 88
    },
    {
      "epoch": 0.0897629853756934,
      "grad_norm": 0.8628408312797546,
      "learning_rate": 5.847947368421053e-05,
      "loss": 0.7473,
      "step": 89
    },
    {
      "epoch": 0.0907715582450832,
      "grad_norm": 0.9028116464614868,
      "learning_rate": 5.795263157894737e-05,
      "loss": 0.792,
      "step": 90
    },
    {
      "epoch": 0.09178013111447302,
      "grad_norm": 0.8097394704818726,
      "learning_rate": 5.742578947368421e-05,
      "loss": 0.6131,
      "step": 91
    },
    {
      "epoch": 0.09278870398386284,
      "grad_norm": 0.7861637473106384,
      "learning_rate": 5.6898947368421046e-05,
      "loss": 0.7173,
      "step": 92
    },
    {
      "epoch": 0.09379727685325265,
      "grad_norm": 0.8539028167724609,
      "learning_rate": 5.6372105263157886e-05,
      "loss": 0.6537,
      "step": 93
    },
    {
      "epoch": 0.09480584972264246,
      "grad_norm": 0.8035638332366943,
      "learning_rate": 5.584526315789473e-05,
      "loss": 0.6684,
      "step": 94
    },
    {
      "epoch": 0.09581442259203228,
      "grad_norm": 0.7700064182281494,
      "learning_rate": 5.531842105263158e-05,
      "loss": 0.5639,
      "step": 95
    },
    {
      "epoch": 0.09682299546142209,
      "grad_norm": 1.0524873733520508,
      "learning_rate": 5.4791578947368424e-05,
      "loss": 0.8324,
      "step": 96
    },
    {
      "epoch": 0.0978315683308119,
      "grad_norm": 0.9328493475914001,
      "learning_rate": 5.426473684210526e-05,
      "loss": 0.7634,
      "step": 97
    },
    {
      "epoch": 0.09884014120020171,
      "grad_norm": 0.9576036930084229,
      "learning_rate": 5.37378947368421e-05,
      "loss": 0.7166,
      "step": 98
    },
    {
      "epoch": 0.09984871406959153,
      "grad_norm": 1.1150087118148804,
      "learning_rate": 5.321105263157894e-05,
      "loss": 0.8622,
      "step": 99
    },
    {
      "epoch": 0.10085728693898134,
      "grad_norm": 1.2727713584899902,
      "learning_rate": 5.268421052631578e-05,
      "loss": 0.8645,
      "step": 100
    },
    {
      "epoch": 0.10085728693898134,
      "eval_loss": 0.6352062821388245,
      "eval_runtime": 101.5713,
      "eval_samples_per_second": 4.115,
      "eval_steps_per_second": 1.034,
      "step": 100
    },
    {
      "epoch": 0.10186585980837115,
      "grad_norm": 0.6869097352027893,
      "learning_rate": 5.2157368421052626e-05,
      "loss": 0.6356,
      "step": 101
    },
    {
      "epoch": 0.10287443267776097,
      "grad_norm": 0.6879076957702637,
      "learning_rate": 5.163052631578947e-05,
      "loss": 0.6521,
      "step": 102
    },
    {
      "epoch": 0.10388300554715078,
      "grad_norm": 0.66792893409729,
      "learning_rate": 5.110368421052632e-05,
      "loss": 0.6565,
      "step": 103
    },
    {
      "epoch": 0.10489157841654059,
      "grad_norm": 0.6843271851539612,
      "learning_rate": 5.057684210526316e-05,
      "loss": 0.5228,
      "step": 104
    },
    {
      "epoch": 0.1059001512859304,
      "grad_norm": 0.6975498795509338,
      "learning_rate": 5.005e-05,
      "loss": 0.6419,
      "step": 105
    },
    {
      "epoch": 0.10690872415532023,
      "grad_norm": 0.6737810969352722,
      "learning_rate": 4.9523157894736836e-05,
      "loss": 0.6125,
      "step": 106
    },
    {
      "epoch": 0.10791729702471003,
      "grad_norm": 0.6993482112884521,
      "learning_rate": 4.899631578947368e-05,
      "loss": 0.562,
      "step": 107
    },
    {
      "epoch": 0.10892586989409984,
      "grad_norm": 0.8742977976799011,
      "learning_rate": 4.846947368421052e-05,
      "loss": 0.5416,
      "step": 108
    },
    {
      "epoch": 0.10993444276348967,
      "grad_norm": 0.583231508731842,
      "learning_rate": 4.794263157894737e-05,
      "loss": 0.51,
      "step": 109
    },
    {
      "epoch": 0.11094301563287948,
      "grad_norm": 0.588787317276001,
      "learning_rate": 4.7415789473684206e-05,
      "loss": 0.5598,
      "step": 110
    },
    {
      "epoch": 0.11195158850226929,
      "grad_norm": 0.6221970915794373,
      "learning_rate": 4.688894736842105e-05,
      "loss": 0.4689,
      "step": 111
    },
    {
      "epoch": 0.1129601613716591,
      "grad_norm": 0.8723281621932983,
      "learning_rate": 4.636210526315789e-05,
      "loss": 0.6268,
      "step": 112
    },
    {
      "epoch": 0.11396873424104892,
      "grad_norm": 0.6584269404411316,
      "learning_rate": 4.583526315789473e-05,
      "loss": 0.5304,
      "step": 113
    },
    {
      "epoch": 0.11497730711043873,
      "grad_norm": 0.6377540826797485,
      "learning_rate": 4.530842105263158e-05,
      "loss": 0.5684,
      "step": 114
    },
    {
      "epoch": 0.11598587997982854,
      "grad_norm": 0.6488873362541199,
      "learning_rate": 4.4781578947368416e-05,
      "loss": 0.665,
      "step": 115
    },
    {
      "epoch": 0.11699445284921836,
      "grad_norm": 0.6601778268814087,
      "learning_rate": 4.425473684210526e-05,
      "loss": 0.5466,
      "step": 116
    },
    {
      "epoch": 0.11800302571860817,
      "grad_norm": 0.7301647067070007,
      "learning_rate": 4.372789473684211e-05,
      "loss": 0.6203,
      "step": 117
    },
    {
      "epoch": 0.11901159858799798,
      "grad_norm": 0.6224742531776428,
      "learning_rate": 4.320105263157895e-05,
      "loss": 0.6334,
      "step": 118
    },
    {
      "epoch": 0.1200201714573878,
      "grad_norm": 0.7299985885620117,
      "learning_rate": 4.2674210526315786e-05,
      "loss": 0.6082,
      "step": 119
    },
    {
      "epoch": 0.12102874432677761,
      "grad_norm": 0.6680064797401428,
      "learning_rate": 4.2147368421052626e-05,
      "loss": 0.5914,
      "step": 120
    },
    {
      "epoch": 0.12203731719616742,
      "grad_norm": 0.7570561170578003,
      "learning_rate": 4.162052631578947e-05,
      "loss": 0.6341,
      "step": 121
    },
    {
      "epoch": 0.12304589006555723,
      "grad_norm": 0.7060465216636658,
      "learning_rate": 4.109368421052631e-05,
      "loss": 0.608,
      "step": 122
    },
    {
      "epoch": 0.12405446293494705,
      "grad_norm": 0.7083133459091187,
      "learning_rate": 4.056684210526316e-05,
      "loss": 0.6731,
      "step": 123
    },
    {
      "epoch": 0.12506303580433686,
      "grad_norm": 0.6821840405464172,
      "learning_rate": 4.004e-05,
      "loss": 0.5981,
      "step": 124
    },
    {
      "epoch": 0.1260716086737267,
      "grad_norm": 0.8325244784355164,
      "learning_rate": 3.951315789473684e-05,
      "loss": 0.6842,
      "step": 125
    },
    {
      "epoch": 0.12708018154311648,
      "grad_norm": 0.7018126845359802,
      "learning_rate": 3.898631578947368e-05,
      "loss": 0.5196,
      "step": 126
    },
    {
      "epoch": 0.1280887544125063,
      "grad_norm": 0.6488572359085083,
      "learning_rate": 3.845947368421052e-05,
      "loss": 0.5191,
      "step": 127
    },
    {
      "epoch": 0.12909732728189613,
      "grad_norm": 0.7428427338600159,
      "learning_rate": 3.7932631578947367e-05,
      "loss": 0.6441,
      "step": 128
    },
    {
      "epoch": 0.13010590015128592,
      "grad_norm": 0.795226514339447,
      "learning_rate": 3.7405789473684206e-05,
      "loss": 0.5661,
      "step": 129
    },
    {
      "epoch": 0.13111447302067575,
      "grad_norm": 0.6325244903564453,
      "learning_rate": 3.6878947368421045e-05,
      "loss": 0.5422,
      "step": 130
    },
    {
      "epoch": 0.13212304589006554,
      "grad_norm": 0.7234381437301636,
      "learning_rate": 3.635210526315789e-05,
      "loss": 0.5709,
      "step": 131
    },
    {
      "epoch": 0.13313161875945537,
      "grad_norm": 0.7622341513633728,
      "learning_rate": 3.582526315789474e-05,
      "loss": 0.4704,
      "step": 132
    },
    {
      "epoch": 0.1341401916288452,
      "grad_norm": 0.707838237285614,
      "learning_rate": 3.5298421052631576e-05,
      "loss": 0.6442,
      "step": 133
    },
    {
      "epoch": 0.13514876449823499,
      "grad_norm": 0.7565646767616272,
      "learning_rate": 3.477157894736842e-05,
      "loss": 0.7482,
      "step": 134
    },
    {
      "epoch": 0.1361573373676248,
      "grad_norm": 0.7385073304176331,
      "learning_rate": 3.424473684210526e-05,
      "loss": 0.6644,
      "step": 135
    },
    {
      "epoch": 0.13716591023701463,
      "grad_norm": 0.6985095143318176,
      "learning_rate": 3.37178947368421e-05,
      "loss": 0.5484,
      "step": 136
    },
    {
      "epoch": 0.13817448310640443,
      "grad_norm": 0.7134766578674316,
      "learning_rate": 3.319105263157894e-05,
      "loss": 0.542,
      "step": 137
    },
    {
      "epoch": 0.13918305597579425,
      "grad_norm": 0.7676419019699097,
      "learning_rate": 3.2664210526315786e-05,
      "loss": 0.6308,
      "step": 138
    },
    {
      "epoch": 0.14019162884518407,
      "grad_norm": 0.8243915438652039,
      "learning_rate": 3.213736842105263e-05,
      "loss": 0.6686,
      "step": 139
    },
    {
      "epoch": 0.14120020171457387,
      "grad_norm": 0.7785696387290955,
      "learning_rate": 3.161052631578947e-05,
      "loss": 0.6185,
      "step": 140
    },
    {
      "epoch": 0.1422087745839637,
      "grad_norm": 0.8271362781524658,
      "learning_rate": 3.108368421052632e-05,
      "loss": 0.6464,
      "step": 141
    },
    {
      "epoch": 0.14321734745335352,
      "grad_norm": 1.1796181201934814,
      "learning_rate": 3.0556842105263156e-05,
      "loss": 0.6272,
      "step": 142
    },
    {
      "epoch": 0.1442259203227433,
      "grad_norm": 0.7917830348014832,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 0.614,
      "step": 143
    },
    {
      "epoch": 0.14523449319213314,
      "grad_norm": 0.8672283887863159,
      "learning_rate": 2.9503157894736838e-05,
      "loss": 0.6808,
      "step": 144
    },
    {
      "epoch": 0.14624306606152296,
      "grad_norm": 1.00629723072052,
      "learning_rate": 2.8976315789473684e-05,
      "loss": 0.8009,
      "step": 145
    },
    {
      "epoch": 0.14725163893091275,
      "grad_norm": 0.9548422694206238,
      "learning_rate": 2.8449473684210523e-05,
      "loss": 0.715,
      "step": 146
    },
    {
      "epoch": 0.14826021180030258,
      "grad_norm": 0.9227573871612549,
      "learning_rate": 2.7922631578947366e-05,
      "loss": 0.73,
      "step": 147
    },
    {
      "epoch": 0.14926878466969237,
      "grad_norm": 0.9087833762168884,
      "learning_rate": 2.7395789473684212e-05,
      "loss": 0.6576,
      "step": 148
    },
    {
      "epoch": 0.1502773575390822,
      "grad_norm": 0.9994284510612488,
      "learning_rate": 2.686894736842105e-05,
      "loss": 0.7382,
      "step": 149
    },
    {
      "epoch": 0.15128593040847202,
      "grad_norm": 1.1259467601776123,
      "learning_rate": 2.634210526315789e-05,
      "loss": 0.7146,
      "step": 150
    },
    {
      "epoch": 0.15128593040847202,
      "eval_loss": 0.6004343032836914,
      "eval_runtime": 101.5492,
      "eval_samples_per_second": 4.116,
      "eval_steps_per_second": 1.034,
      "step": 150
    },
    {
      "epoch": 0.15229450327786181,
      "grad_norm": 0.6159412860870361,
      "learning_rate": 2.5815263157894736e-05,
      "loss": 0.5644,
      "step": 151
    },
    {
      "epoch": 0.15330307614725164,
      "grad_norm": 0.6521725654602051,
      "learning_rate": 2.528842105263158e-05,
      "loss": 0.5947,
      "step": 152
    },
    {
      "epoch": 0.15431164901664146,
      "grad_norm": 0.6757987141609192,
      "learning_rate": 2.4761578947368418e-05,
      "loss": 0.6322,
      "step": 153
    },
    {
      "epoch": 0.15532022188603126,
      "grad_norm": 0.7489837408065796,
      "learning_rate": 2.423473684210526e-05,
      "loss": 0.6303,
      "step": 154
    },
    {
      "epoch": 0.15632879475542108,
      "grad_norm": 0.6673961877822876,
      "learning_rate": 2.3707894736842103e-05,
      "loss": 0.5193,
      "step": 155
    },
    {
      "epoch": 0.1573373676248109,
      "grad_norm": 0.6868383288383484,
      "learning_rate": 2.3181052631578946e-05,
      "loss": 0.6149,
      "step": 156
    },
    {
      "epoch": 0.1583459404942007,
      "grad_norm": 0.7946422100067139,
      "learning_rate": 2.265421052631579e-05,
      "loss": 0.6796,
      "step": 157
    },
    {
      "epoch": 0.15935451336359052,
      "grad_norm": 0.7221014499664307,
      "learning_rate": 2.212736842105263e-05,
      "loss": 0.5769,
      "step": 158
    },
    {
      "epoch": 0.16036308623298035,
      "grad_norm": 0.786558210849762,
      "learning_rate": 2.1600526315789474e-05,
      "loss": 0.6821,
      "step": 159
    },
    {
      "epoch": 0.16137165910237014,
      "grad_norm": 0.6471860408782959,
      "learning_rate": 2.1073684210526313e-05,
      "loss": 0.5369,
      "step": 160
    },
    {
      "epoch": 0.16238023197175996,
      "grad_norm": 0.6257407665252686,
      "learning_rate": 2.0546842105263155e-05,
      "loss": 0.6196,
      "step": 161
    },
    {
      "epoch": 0.16338880484114976,
      "grad_norm": 0.6558111906051636,
      "learning_rate": 2.002e-05,
      "loss": 0.6484,
      "step": 162
    },
    {
      "epoch": 0.16439737771053958,
      "grad_norm": 0.6279188394546509,
      "learning_rate": 1.949315789473684e-05,
      "loss": 0.6016,
      "step": 163
    },
    {
      "epoch": 0.1654059505799294,
      "grad_norm": 0.7265282273292542,
      "learning_rate": 1.8966315789473683e-05,
      "loss": 0.6696,
      "step": 164
    },
    {
      "epoch": 0.1664145234493192,
      "grad_norm": 0.6316133141517639,
      "learning_rate": 1.8439473684210522e-05,
      "loss": 0.5964,
      "step": 165
    },
    {
      "epoch": 0.16742309631870902,
      "grad_norm": 0.5745766758918762,
      "learning_rate": 1.791263157894737e-05,
      "loss": 0.4827,
      "step": 166
    },
    {
      "epoch": 0.16843166918809885,
      "grad_norm": 0.5827904939651489,
      "learning_rate": 1.738578947368421e-05,
      "loss": 0.5521,
      "step": 167
    },
    {
      "epoch": 0.16944024205748864,
      "grad_norm": 0.668985903263092,
      "learning_rate": 1.685894736842105e-05,
      "loss": 0.5015,
      "step": 168
    },
    {
      "epoch": 0.17044881492687847,
      "grad_norm": 0.653778612613678,
      "learning_rate": 1.6332105263157893e-05,
      "loss": 0.5719,
      "step": 169
    },
    {
      "epoch": 0.1714573877962683,
      "grad_norm": 0.6655924320220947,
      "learning_rate": 1.5805263157894735e-05,
      "loss": 0.6106,
      "step": 170
    },
    {
      "epoch": 0.17246596066565809,
      "grad_norm": 0.6402179002761841,
      "learning_rate": 1.5278421052631578e-05,
      "loss": 0.5839,
      "step": 171
    },
    {
      "epoch": 0.1734745335350479,
      "grad_norm": 0.6910385489463806,
      "learning_rate": 1.4751578947368419e-05,
      "loss": 0.5609,
      "step": 172
    },
    {
      "epoch": 0.17448310640443773,
      "grad_norm": 0.6364717483520508,
      "learning_rate": 1.4224736842105262e-05,
      "loss": 0.5501,
      "step": 173
    },
    {
      "epoch": 0.17549167927382753,
      "grad_norm": 0.7365476489067078,
      "learning_rate": 1.3697894736842106e-05,
      "loss": 0.5665,
      "step": 174
    },
    {
      "epoch": 0.17650025214321735,
      "grad_norm": 0.6225388646125793,
      "learning_rate": 1.3171052631578945e-05,
      "loss": 0.532,
      "step": 175
    },
    {
      "epoch": 0.17750882501260717,
      "grad_norm": 0.8537216186523438,
      "learning_rate": 1.264421052631579e-05,
      "loss": 0.6485,
      "step": 176
    },
    {
      "epoch": 0.17851739788199697,
      "grad_norm": 0.6732882857322693,
      "learning_rate": 1.211736842105263e-05,
      "loss": 0.5705,
      "step": 177
    },
    {
      "epoch": 0.1795259707513868,
      "grad_norm": 0.6271360516548157,
      "learning_rate": 1.1590526315789473e-05,
      "loss": 0.5196,
      "step": 178
    },
    {
      "epoch": 0.1805345436207766,
      "grad_norm": 0.7144887447357178,
      "learning_rate": 1.1063684210526316e-05,
      "loss": 0.6474,
      "step": 179
    },
    {
      "epoch": 0.1815431164901664,
      "grad_norm": 0.7253063917160034,
      "learning_rate": 1.0536842105263156e-05,
      "loss": 0.5879,
      "step": 180
    },
    {
      "epoch": 0.18255168935955624,
      "grad_norm": 0.8043211102485657,
      "learning_rate": 1.001e-05,
      "loss": 0.7254,
      "step": 181
    },
    {
      "epoch": 0.18356026222894603,
      "grad_norm": 0.8037781715393066,
      "learning_rate": 9.483157894736842e-06,
      "loss": 0.7209,
      "step": 182
    },
    {
      "epoch": 0.18456883509833585,
      "grad_norm": 0.6927266716957092,
      "learning_rate": 8.956315789473684e-06,
      "loss": 0.5637,
      "step": 183
    },
    {
      "epoch": 0.18557740796772568,
      "grad_norm": 0.7423042058944702,
      "learning_rate": 8.429473684210525e-06,
      "loss": 0.6976,
      "step": 184
    },
    {
      "epoch": 0.18658598083711547,
      "grad_norm": 0.7680438160896301,
      "learning_rate": 7.902631578947368e-06,
      "loss": 0.6765,
      "step": 185
    },
    {
      "epoch": 0.1875945537065053,
      "grad_norm": 0.7825251817703247,
      "learning_rate": 7.3757894736842095e-06,
      "loss": 0.6069,
      "step": 186
    },
    {
      "epoch": 0.18860312657589512,
      "grad_norm": 0.7090364694595337,
      "learning_rate": 6.848947368421053e-06,
      "loss": 0.6792,
      "step": 187
    },
    {
      "epoch": 0.18961169944528491,
      "grad_norm": 0.7658358216285706,
      "learning_rate": 6.322105263157895e-06,
      "loss": 0.6258,
      "step": 188
    },
    {
      "epoch": 0.19062027231467474,
      "grad_norm": 0.7703218460083008,
      "learning_rate": 5.7952631578947365e-06,
      "loss": 0.5897,
      "step": 189
    },
    {
      "epoch": 0.19162884518406456,
      "grad_norm": 0.7696387767791748,
      "learning_rate": 5.268421052631578e-06,
      "loss": 0.6851,
      "step": 190
    },
    {
      "epoch": 0.19263741805345436,
      "grad_norm": 0.824103593826294,
      "learning_rate": 4.741578947368421e-06,
      "loss": 0.7013,
      "step": 191
    },
    {
      "epoch": 0.19364599092284418,
      "grad_norm": 0.7561247944831848,
      "learning_rate": 4.2147368421052626e-06,
      "loss": 0.5654,
      "step": 192
    },
    {
      "epoch": 0.19465456379223398,
      "grad_norm": 0.7880785465240479,
      "learning_rate": 3.6878947368421047e-06,
      "loss": 0.5951,
      "step": 193
    },
    {
      "epoch": 0.1956631366616238,
      "grad_norm": 0.8802310228347778,
      "learning_rate": 3.1610526315789474e-06,
      "loss": 0.731,
      "step": 194
    },
    {
      "epoch": 0.19667170953101362,
      "grad_norm": 0.9237648248672485,
      "learning_rate": 2.634210526315789e-06,
      "loss": 0.7162,
      "step": 195
    },
    {
      "epoch": 0.19768028240040342,
      "grad_norm": 0.8824543356895447,
      "learning_rate": 2.1073684210526313e-06,
      "loss": 0.6355,
      "step": 196
    },
    {
      "epoch": 0.19868885526979324,
      "grad_norm": 0.9669397473335266,
      "learning_rate": 1.5805263157894737e-06,
      "loss": 0.6952,
      "step": 197
    },
    {
      "epoch": 0.19969742813918306,
      "grad_norm": 0.9723389744758606,
      "learning_rate": 1.0536842105263156e-06,
      "loss": 0.6466,
      "step": 198
    },
    {
      "epoch": 0.20070600100857286,
      "grad_norm": 0.9352823495864868,
      "learning_rate": 5.268421052631578e-07,
      "loss": 0.6504,
      "step": 199
    },
    {
      "epoch": 0.20171457387796268,
      "grad_norm": 1.119659662246704,
      "learning_rate": 0.0,
      "loss": 0.7651,
      "step": 200
    },
    {
      "epoch": 0.20171457387796268,
      "eval_loss": 0.5862807035446167,
      "eval_runtime": 101.854,
      "eval_samples_per_second": 4.104,
      "eval_steps_per_second": 1.031,
      "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": 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": 1.733017139675136e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}