{
  "best_metric": 0.14084061980247498,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.6302521008403361,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004201680672268907,
      "grad_norm": 0.49750980734825134,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.1452,
      "step": 1
    },
    {
      "epoch": 0.004201680672268907,
      "eval_loss": 0.36222052574157715,
      "eval_runtime": 234.0564,
      "eval_samples_per_second": 1.713,
      "eval_steps_per_second": 0.432,
      "step": 1
    },
    {
      "epoch": 0.008403361344537815,
      "grad_norm": 0.5146015286445618,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1574,
      "step": 2
    },
    {
      "epoch": 0.012605042016806723,
      "grad_norm": 0.5062153935432434,
      "learning_rate": 3.3e-05,
      "loss": 0.1532,
      "step": 3
    },
    {
      "epoch": 0.01680672268907563,
      "grad_norm": 0.41625574231147766,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1358,
      "step": 4
    },
    {
      "epoch": 0.02100840336134454,
      "grad_norm": 0.17534741759300232,
      "learning_rate": 5.5e-05,
      "loss": 0.1105,
      "step": 5
    },
    {
      "epoch": 0.025210084033613446,
      "grad_norm": 0.1469479352235794,
      "learning_rate": 6.6e-05,
      "loss": 0.1,
      "step": 6
    },
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 0.12348287552595139,
      "learning_rate": 7.7e-05,
      "loss": 0.0873,
      "step": 7
    },
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 0.11953099817037582,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0847,
      "step": 8
    },
    {
      "epoch": 0.037815126050420166,
      "grad_norm": 0.11016067862510681,
      "learning_rate": 9.900000000000001e-05,
      "loss": 0.0695,
      "step": 9
    },
    {
      "epoch": 0.04201680672268908,
      "grad_norm": 0.14919094741344452,
      "learning_rate": 0.00011,
      "loss": 0.0631,
      "step": 10
    },
    {
      "epoch": 0.046218487394957986,
      "grad_norm": 0.0973418578505516,
      "learning_rate": 0.0001099924817745858,
      "loss": 0.05,
      "step": 11
    },
    {
      "epoch": 0.05042016806722689,
      "grad_norm": 0.07051382213830948,
      "learning_rate": 0.00010996992915375093,
      "loss": 0.0442,
      "step": 12
    },
    {
      "epoch": 0.0546218487394958,
      "grad_norm": 0.09474644064903259,
      "learning_rate": 0.00010993234830315676,
      "loss": 0.0438,
      "step": 13
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 0.09510326385498047,
      "learning_rate": 0.0001098797494970326,
      "loss": 0.0452,
      "step": 14
    },
    {
      "epoch": 0.06302521008403361,
      "grad_norm": 0.07116366177797318,
      "learning_rate": 0.00010981214711536684,
      "loss": 0.0477,
      "step": 15
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.12737803161144257,
      "learning_rate": 0.00010972955963997563,
      "loss": 0.0442,
      "step": 16
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.06226251646876335,
      "learning_rate": 0.00010963200964945011,
      "loss": 0.0345,
      "step": 17
    },
    {
      "epoch": 0.07563025210084033,
      "grad_norm": 0.06668021529912949,
      "learning_rate": 0.00010951952381298364,
      "loss": 0.038,
      "step": 18
    },
    {
      "epoch": 0.07983193277310924,
      "grad_norm": 0.07071222364902496,
      "learning_rate": 0.00010939213288308077,
      "loss": 0.0414,
      "step": 19
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.06094304844737053,
      "learning_rate": 0.00010924987168714973,
      "loss": 0.0453,
      "step": 20
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 0.10369093716144562,
      "learning_rate": 0.00010909277911798103,
      "loss": 0.0403,
      "step": 21
    },
    {
      "epoch": 0.09243697478991597,
      "grad_norm": 0.06250135600566864,
      "learning_rate": 0.00010892089812311451,
      "loss": 0.0407,
      "step": 22
    },
    {
      "epoch": 0.09663865546218488,
      "grad_norm": 0.059974078088998795,
      "learning_rate": 0.00010873427569309797,
      "loss": 0.0409,
      "step": 23
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 0.07670460641384125,
      "learning_rate": 0.00010853296284864032,
      "loss": 0.05,
      "step": 24
    },
    {
      "epoch": 0.10504201680672269,
      "grad_norm": 0.053304269909858704,
      "learning_rate": 0.00010831701462666318,
      "loss": 0.0412,
      "step": 25
    },
    {
      "epoch": 0.1092436974789916,
      "grad_norm": 0.11782944202423096,
      "learning_rate": 0.00010808649006525419,
      "loss": 0.053,
      "step": 26
    },
    {
      "epoch": 0.1134453781512605,
      "grad_norm": 0.06433657556772232,
      "learning_rate": 0.00010784145218752665,
      "loss": 0.0587,
      "step": 27
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.08066810667514801,
      "learning_rate": 0.00010758196798438968,
      "loss": 0.0521,
      "step": 28
    },
    {
      "epoch": 0.12184873949579832,
      "grad_norm": 0.05485512688755989,
      "learning_rate": 0.00010730810839623346,
      "loss": 0.0528,
      "step": 29
    },
    {
      "epoch": 0.12605042016806722,
      "grad_norm": 0.17254118621349335,
      "learning_rate": 0.0001070199482935349,
      "loss": 0.0577,
      "step": 30
    },
    {
      "epoch": 0.13025210084033614,
      "grad_norm": 0.11069461703300476,
      "learning_rate": 0.00010671756645638888,
      "loss": 0.0669,
      "step": 31
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 0.12035743147134781,
      "learning_rate": 0.00010640104555297034,
      "loss": 0.0708,
      "step": 32
    },
    {
      "epoch": 0.13865546218487396,
      "grad_norm": 0.061041515320539474,
      "learning_rate": 0.00010607047211693389,
      "loss": 0.0832,
      "step": 33
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.31896713376045227,
      "learning_rate": 0.00010572593652375616,
      "loss": 0.0914,
      "step": 34
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 0.12278568744659424,
      "learning_rate": 0.00010536753296602816,
      "loss": 0.0993,
      "step": 35
    },
    {
      "epoch": 0.15126050420168066,
      "grad_norm": 0.12456497550010681,
      "learning_rate": 0.00010499535942770394,
      "loss": 0.1148,
      "step": 36
    },
    {
      "epoch": 0.15546218487394958,
      "grad_norm": 0.10634661465883255,
      "learning_rate": 0.00010460951765731275,
      "loss": 0.1196,
      "step": 37
    },
    {
      "epoch": 0.15966386554621848,
      "grad_norm": 0.09298716485500336,
      "learning_rate": 0.000104210113140142,
      "loss": 0.1326,
      "step": 38
    },
    {
      "epoch": 0.1638655462184874,
      "grad_norm": 0.06946210563182831,
      "learning_rate": 0.00010379725506939865,
      "loss": 0.1163,
      "step": 39
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.1408974677324295,
      "learning_rate": 0.0001033710563163569,
      "loss": 0.1521,
      "step": 40
    },
    {
      "epoch": 0.1722689075630252,
      "grad_norm": 0.11890745908021927,
      "learning_rate": 0.00010293163339950024,
      "loss": 0.1617,
      "step": 41
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 0.0880684107542038,
      "learning_rate": 0.00010247910645266658,
      "loss": 0.1707,
      "step": 42
    },
    {
      "epoch": 0.18067226890756302,
      "grad_norm": 0.10107150673866272,
      "learning_rate": 0.00010201359919220464,
      "loss": 0.2014,
      "step": 43
    },
    {
      "epoch": 0.18487394957983194,
      "grad_norm": 0.11371296644210815,
      "learning_rate": 0.00010153523888315144,
      "loss": 0.2271,
      "step": 44
    },
    {
      "epoch": 0.18907563025210083,
      "grad_norm": 0.13401076197624207,
      "learning_rate": 0.00010104415630443907,
      "loss": 0.2555,
      "step": 45
    },
    {
      "epoch": 0.19327731092436976,
      "grad_norm": 0.16017286479473114,
      "learning_rate": 0.0001005404857131411,
      "loss": 0.3304,
      "step": 46
    },
    {
      "epoch": 0.19747899159663865,
      "grad_norm": 0.16582688689231873,
      "learning_rate": 0.00010002436480776809,
      "loss": 0.4034,
      "step": 47
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 0.2239397168159485,
      "learning_rate": 9.949593469062211e-05,
      "loss": 0.5349,
      "step": 48
    },
    {
      "epoch": 0.20588235294117646,
      "grad_norm": 0.3563201129436493,
      "learning_rate": 9.895533982922087e-05,
      "loss": 0.9682,
      "step": 49
    },
    {
      "epoch": 0.21008403361344538,
      "grad_norm": 0.4066728353500366,
      "learning_rate": 9.840272801680165e-05,
      "loss": 1.2013,
      "step": 50
    },
    {
      "epoch": 0.21008403361344538,
      "eval_loss": 0.521058976650238,
      "eval_runtime": 245.7858,
      "eval_samples_per_second": 1.632,
      "eval_steps_per_second": 0.411,
      "step": 50
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.0479297637939453,
      "learning_rate": 9.783825033191619e-05,
      "loss": 0.549,
      "step": 51
    },
    {
      "epoch": 0.2184873949579832,
      "grad_norm": 1.3544615507125854,
      "learning_rate": 9.726206109712725e-05,
      "loss": 0.2489,
      "step": 52
    },
    {
      "epoch": 0.22268907563025211,
      "grad_norm": 0.32278114557266235,
      "learning_rate": 9.667431783681842e-05,
      "loss": 0.0716,
      "step": 53
    },
    {
      "epoch": 0.226890756302521,
      "grad_norm": 0.08393025398254395,
      "learning_rate": 9.607518123412847e-05,
      "loss": 0.0438,
      "step": 54
    },
    {
      "epoch": 0.23109243697478993,
      "grad_norm": 0.07648172974586487,
      "learning_rate": 9.546481508702224e-05,
      "loss": 0.0427,
      "step": 55
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.07890063524246216,
      "learning_rate": 9.48433862635099e-05,
      "loss": 0.0433,
      "step": 56
    },
    {
      "epoch": 0.23949579831932774,
      "grad_norm": 0.0927102193236351,
      "learning_rate": 9.421106465602684e-05,
      "loss": 0.0453,
      "step": 57
    },
    {
      "epoch": 0.24369747899159663,
      "grad_norm": 0.08202504366636276,
      "learning_rate": 9.356802313498687e-05,
      "loss": 0.0378,
      "step": 58
    },
    {
      "epoch": 0.24789915966386555,
      "grad_norm": 0.07329721003770828,
      "learning_rate": 9.291443750152112e-05,
      "loss": 0.0344,
      "step": 59
    },
    {
      "epoch": 0.25210084033613445,
      "grad_norm": 0.059026774019002914,
      "learning_rate": 9.225048643941577e-05,
      "loss": 0.0429,
      "step": 60
    },
    {
      "epoch": 0.25630252100840334,
      "grad_norm": 0.05524129793047905,
      "learning_rate": 9.157635146626164e-05,
      "loss": 0.0362,
      "step": 61
    },
    {
      "epoch": 0.2605042016806723,
      "grad_norm": 0.08096156269311905,
      "learning_rate": 9.089221688382928e-05,
      "loss": 0.0396,
      "step": 62
    },
    {
      "epoch": 0.2647058823529412,
      "grad_norm": 0.08996499329805374,
      "learning_rate": 9.019826972768242e-05,
      "loss": 0.0384,
      "step": 63
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 0.04689677432179451,
      "learning_rate": 8.949469971604454e-05,
      "loss": 0.0348,
      "step": 64
    },
    {
      "epoch": 0.27310924369747897,
      "grad_norm": 0.06765469908714294,
      "learning_rate": 8.878169919793173e-05,
      "loss": 0.0352,
      "step": 65
    },
    {
      "epoch": 0.2773109243697479,
      "grad_norm": 0.07770418375730515,
      "learning_rate": 8.805946310056638e-05,
      "loss": 0.0358,
      "step": 66
    },
    {
      "epoch": 0.2815126050420168,
      "grad_norm": 0.05707339197397232,
      "learning_rate": 8.732818887608602e-05,
      "loss": 0.0351,
      "step": 67
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.07923433184623718,
      "learning_rate": 8.65880764475619e-05,
      "loss": 0.0396,
      "step": 68
    },
    {
      "epoch": 0.28991596638655465,
      "grad_norm": 0.07886988669633865,
      "learning_rate": 8.583932815434201e-05,
      "loss": 0.0361,
      "step": 69
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.07595830410718918,
      "learning_rate": 8.50821486967335e-05,
      "loss": 0.0389,
      "step": 70
    },
    {
      "epoch": 0.29831932773109243,
      "grad_norm": 0.08922255039215088,
      "learning_rate": 8.431674508003966e-05,
      "loss": 0.0403,
      "step": 71
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": 0.05408494919538498,
      "learning_rate": 8.354332655796683e-05,
      "loss": 0.0442,
      "step": 72
    },
    {
      "epoch": 0.3067226890756303,
      "grad_norm": 0.18477368354797363,
      "learning_rate": 8.276210457541642e-05,
      "loss": 0.0405,
      "step": 73
    },
    {
      "epoch": 0.31092436974789917,
      "grad_norm": 0.19412672519683838,
      "learning_rate": 8.197329271067796e-05,
      "loss": 0.0453,
      "step": 74
    },
    {
      "epoch": 0.31512605042016806,
      "grad_norm": 0.17333091795444489,
      "learning_rate": 8.117710661703905e-05,
      "loss": 0.0523,
      "step": 75
    },
    {
      "epoch": 0.31932773109243695,
      "grad_norm": 0.34910866618156433,
      "learning_rate": 8.037376396382784e-05,
      "loss": 0.0482,
      "step": 76
    },
    {
      "epoch": 0.3235294117647059,
      "grad_norm": 0.12087592482566833,
      "learning_rate": 7.956348437690437e-05,
      "loss": 0.0492,
      "step": 77
    },
    {
      "epoch": 0.3277310924369748,
      "grad_norm": 0.13387855887413025,
      "learning_rate": 7.87464893786171e-05,
      "loss": 0.0586,
      "step": 78
    },
    {
      "epoch": 0.3319327731092437,
      "grad_norm": 0.10430057346820831,
      "learning_rate": 7.792300232724097e-05,
      "loss": 0.0577,
      "step": 79
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.058383017778396606,
      "learning_rate": 7.709324835591332e-05,
      "loss": 0.0578,
      "step": 80
    },
    {
      "epoch": 0.3403361344537815,
      "grad_norm": 0.2369661182165146,
      "learning_rate": 7.625745431108487e-05,
      "loss": 0.0654,
      "step": 81
    },
    {
      "epoch": 0.3445378151260504,
      "grad_norm": 0.0711449384689331,
      "learning_rate": 7.541584869050213e-05,
      "loss": 0.0725,
      "step": 82
    },
    {
      "epoch": 0.3487394957983193,
      "grad_norm": 0.11881482601165771,
      "learning_rate": 7.456866158073842e-05,
      "loss": 0.0738,
      "step": 83
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.1186806783080101,
      "learning_rate": 7.371612459429037e-05,
      "loss": 0.093,
      "step": 84
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.07813920825719833,
      "learning_rate": 7.28584708062576e-05,
      "loss": 0.0819,
      "step": 85
    },
    {
      "epoch": 0.36134453781512604,
      "grad_norm": 0.14843684434890747,
      "learning_rate": 7.19959346906221e-05,
      "loss": 0.1048,
      "step": 86
    },
    {
      "epoch": 0.36554621848739494,
      "grad_norm": 0.1119343712925911,
      "learning_rate": 7.112875205614558e-05,
      "loss": 0.1073,
      "step": 87
    },
    {
      "epoch": 0.3697478991596639,
      "grad_norm": 0.14418436586856842,
      "learning_rate": 7.025715998190145e-05,
      "loss": 0.1069,
      "step": 88
    },
    {
      "epoch": 0.3739495798319328,
      "grad_norm": 0.1696012318134308,
      "learning_rate": 6.938139675246009e-05,
      "loss": 0.1328,
      "step": 89
    },
    {
      "epoch": 0.37815126050420167,
      "grad_norm": 0.07131479680538177,
      "learning_rate": 6.850170179274395e-05,
      "loss": 0.133,
      "step": 90
    },
    {
      "epoch": 0.38235294117647056,
      "grad_norm": 0.214226633310318,
      "learning_rate": 6.761831560257134e-05,
      "loss": 0.1499,
      "step": 91
    },
    {
      "epoch": 0.3865546218487395,
      "grad_norm": 0.2105318009853363,
      "learning_rate": 6.673147969090608e-05,
      "loss": 0.1836,
      "step": 92
    },
    {
      "epoch": 0.3907563025210084,
      "grad_norm": 0.18370755016803741,
      "learning_rate": 6.584143650983141e-05,
      "loss": 0.2001,
      "step": 93
    },
    {
      "epoch": 0.3949579831932773,
      "grad_norm": 0.43610021471977234,
      "learning_rate": 6.494842938826605e-05,
      "loss": 0.217,
      "step": 94
    },
    {
      "epoch": 0.39915966386554624,
      "grad_norm": 0.37327277660369873,
      "learning_rate": 6.405270246544037e-05,
      "loss": 0.2492,
      "step": 95
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 0.30380088090896606,
      "learning_rate": 6.31545006241513e-05,
      "loss": 0.3072,
      "step": 96
    },
    {
      "epoch": 0.40756302521008403,
      "grad_norm": 0.17763619124889374,
      "learning_rate": 6.22540694238138e-05,
      "loss": 0.3711,
      "step": 97
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 0.2223198413848877,
      "learning_rate": 6.135165503332725e-05,
      "loss": 0.55,
      "step": 98
    },
    {
      "epoch": 0.41596638655462187,
      "grad_norm": 0.3319002687931061,
      "learning_rate": 6.0447504163775465e-05,
      "loss": 0.9316,
      "step": 99
    },
    {
      "epoch": 0.42016806722689076,
      "grad_norm": 0.3552457094192505,
      "learning_rate": 5.954186400097829e-05,
      "loss": 1.0921,
      "step": 100
    },
    {
      "epoch": 0.42016806722689076,
      "eval_loss": 0.47890180349349976,
      "eval_runtime": 270.8902,
      "eval_samples_per_second": 1.48,
      "eval_steps_per_second": 0.373,
      "step": 100
    },
    {
      "epoch": 0.42436974789915966,
      "grad_norm": 4.169086933135986,
      "learning_rate": 5.8634982137913465e-05,
      "loss": 0.5264,
      "step": 101
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.9985085725784302,
      "learning_rate": 5.772710650702723e-05,
      "loss": 0.1248,
      "step": 102
    },
    {
      "epoch": 0.4327731092436975,
      "grad_norm": 0.057010602205991745,
      "learning_rate": 5.681848531245195e-05,
      "loss": 0.0331,
      "step": 103
    },
    {
      "epoch": 0.4369747899159664,
      "grad_norm": 0.07370073348283768,
      "learning_rate": 5.590936696214972e-05,
      "loss": 0.0401,
      "step": 104
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 0.07470442354679108,
      "learning_rate": 5.5e-05,
      "loss": 0.0451,
      "step": 105
    },
    {
      "epoch": 0.44537815126050423,
      "grad_norm": 0.07614938914775848,
      "learning_rate": 5.409063303785029e-05,
      "loss": 0.05,
      "step": 106
    },
    {
      "epoch": 0.4495798319327731,
      "grad_norm": 0.07786896824836731,
      "learning_rate": 5.318151468754805e-05,
      "loss": 0.0505,
      "step": 107
    },
    {
      "epoch": 0.453781512605042,
      "grad_norm": 0.07709647715091705,
      "learning_rate": 5.227289349297277e-05,
      "loss": 0.0517,
      "step": 108
    },
    {
      "epoch": 0.4579831932773109,
      "grad_norm": 0.07772062718868256,
      "learning_rate": 5.136501786208654e-05,
      "loss": 0.0539,
      "step": 109
    },
    {
      "epoch": 0.46218487394957986,
      "grad_norm": 0.07466543465852737,
      "learning_rate": 5.045813599902173e-05,
      "loss": 0.0563,
      "step": 110
    },
    {
      "epoch": 0.46638655462184875,
      "grad_norm": 0.07618583738803864,
      "learning_rate": 4.955249583622455e-05,
      "loss": 0.0543,
      "step": 111
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.0762595385313034,
      "learning_rate": 4.8648344966672767e-05,
      "loss": 0.0534,
      "step": 112
    },
    {
      "epoch": 0.47478991596638653,
      "grad_norm": 0.07716407626867294,
      "learning_rate": 4.774593057618621e-05,
      "loss": 0.0501,
      "step": 113
    },
    {
      "epoch": 0.4789915966386555,
      "grad_norm": 0.07322922348976135,
      "learning_rate": 4.6845499375848686e-05,
      "loss": 0.0509,
      "step": 114
    },
    {
      "epoch": 0.4831932773109244,
      "grad_norm": 0.0707123726606369,
      "learning_rate": 4.5947297534559625e-05,
      "loss": 0.0482,
      "step": 115
    },
    {
      "epoch": 0.48739495798319327,
      "grad_norm": 0.07027147710323334,
      "learning_rate": 4.5051570611733976e-05,
      "loss": 0.0489,
      "step": 116
    },
    {
      "epoch": 0.49159663865546216,
      "grad_norm": 0.06395595520734787,
      "learning_rate": 4.415856349016859e-05,
      "loss": 0.045,
      "step": 117
    },
    {
      "epoch": 0.4957983193277311,
      "grad_norm": 0.06482091546058655,
      "learning_rate": 4.326852030909393e-05,
      "loss": 0.0441,
      "step": 118
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.06443566083908081,
      "learning_rate": 4.238168439742867e-05,
      "loss": 0.0436,
      "step": 119
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.06711577624082565,
      "learning_rate": 4.149829820725605e-05,
      "loss": 0.0436,
      "step": 120
    },
    {
      "epoch": 0.5084033613445378,
      "grad_norm": 0.05877511948347092,
      "learning_rate": 4.0618603247539916e-05,
      "loss": 0.0432,
      "step": 121
    },
    {
      "epoch": 0.5126050420168067,
      "grad_norm": 0.06349120289087296,
      "learning_rate": 3.9742840018098564e-05,
      "loss": 0.0508,
      "step": 122
    },
    {
      "epoch": 0.5168067226890757,
      "grad_norm": 0.05786605551838875,
      "learning_rate": 3.887124794385445e-05,
      "loss": 0.0459,
      "step": 123
    },
    {
      "epoch": 0.5210084033613446,
      "grad_norm": 0.058453019708395004,
      "learning_rate": 3.80040653093779e-05,
      "loss": 0.0446,
      "step": 124
    },
    {
      "epoch": 0.5252100840336135,
      "grad_norm": 0.05471871420741081,
      "learning_rate": 3.714152919374241e-05,
      "loss": 0.0485,
      "step": 125
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 0.06058911234140396,
      "learning_rate": 3.628387540570963e-05,
      "loss": 0.0462,
      "step": 126
    },
    {
      "epoch": 0.5336134453781513,
      "grad_norm": 0.05696989595890045,
      "learning_rate": 3.543133841926159e-05,
      "loss": 0.0513,
      "step": 127
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 0.04979941248893738,
      "learning_rate": 3.458415130949785e-05,
      "loss": 0.0616,
      "step": 128
    },
    {
      "epoch": 0.542016806722689,
      "grad_norm": 0.046740416437387466,
      "learning_rate": 3.374254568891514e-05,
      "loss": 0.0597,
      "step": 129
    },
    {
      "epoch": 0.5462184873949579,
      "grad_norm": 0.048966214060783386,
      "learning_rate": 3.290675164408669e-05,
      "loss": 0.0661,
      "step": 130
    },
    {
      "epoch": 0.5504201680672269,
      "grad_norm": 0.05556921288371086,
      "learning_rate": 3.207699767275904e-05,
      "loss": 0.0771,
      "step": 131
    },
    {
      "epoch": 0.5546218487394958,
      "grad_norm": 0.058795638382434845,
      "learning_rate": 3.12535106213829e-05,
      "loss": 0.0708,
      "step": 132
    },
    {
      "epoch": 0.5588235294117647,
      "grad_norm": 0.059710677713155746,
      "learning_rate": 3.0436515623095647e-05,
      "loss": 0.0702,
      "step": 133
    },
    {
      "epoch": 0.5630252100840336,
      "grad_norm": 0.06440545618534088,
      "learning_rate": 2.962623603617218e-05,
      "loss": 0.0857,
      "step": 134
    },
    {
      "epoch": 0.5672268907563025,
      "grad_norm": 0.059835322201251984,
      "learning_rate": 2.8822893382960955e-05,
      "loss": 0.0959,
      "step": 135
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.06194557622075081,
      "learning_rate": 2.802670728932207e-05,
      "loss": 0.1121,
      "step": 136
    },
    {
      "epoch": 0.5756302521008403,
      "grad_norm": 0.06737734377384186,
      "learning_rate": 2.723789542458361e-05,
      "loss": 0.1135,
      "step": 137
    },
    {
      "epoch": 0.5798319327731093,
      "grad_norm": 0.06589267402887344,
      "learning_rate": 2.6456673442033183e-05,
      "loss": 0.1125,
      "step": 138
    },
    {
      "epoch": 0.5840336134453782,
      "grad_norm": 0.07247166335582733,
      "learning_rate": 2.5683254919960356e-05,
      "loss": 0.1377,
      "step": 139
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.07507860660552979,
      "learning_rate": 2.4917851303266533e-05,
      "loss": 0.1326,
      "step": 140
    },
    {
      "epoch": 0.592436974789916,
      "grad_norm": 0.09094900637865067,
      "learning_rate": 2.4160671845658007e-05,
      "loss": 0.1411,
      "step": 141
    },
    {
      "epoch": 0.5966386554621849,
      "grad_norm": 0.09972415864467621,
      "learning_rate": 2.3411923552438105e-05,
      "loss": 0.1649,
      "step": 142
    },
    {
      "epoch": 0.6008403361344538,
      "grad_norm": 0.10327650606632233,
      "learning_rate": 2.2671811123913983e-05,
      "loss": 0.185,
      "step": 143
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 0.13001111149787903,
      "learning_rate": 2.194053689943362e-05,
      "loss": 0.2116,
      "step": 144
    },
    {
      "epoch": 0.6092436974789915,
      "grad_norm": 0.10833977162837982,
      "learning_rate": 2.121830080206827e-05,
      "loss": 0.2416,
      "step": 145
    },
    {
      "epoch": 0.6134453781512605,
      "grad_norm": 0.1772170066833496,
      "learning_rate": 2.0505300283955464e-05,
      "loss": 0.3062,
      "step": 146
    },
    {
      "epoch": 0.6176470588235294,
      "grad_norm": 0.2684325873851776,
      "learning_rate": 1.9801730272317585e-05,
      "loss": 0.4366,
      "step": 147
    },
    {
      "epoch": 0.6218487394957983,
      "grad_norm": 0.288666307926178,
      "learning_rate": 1.910778311617072e-05,
      "loss": 0.6787,
      "step": 148
    },
    {
      "epoch": 0.6260504201680672,
      "grad_norm": 0.31838375329971313,
      "learning_rate": 1.8423648533738342e-05,
      "loss": 0.9365,
      "step": 149
    },
    {
      "epoch": 0.6302521008403361,
      "grad_norm": 0.3195730745792389,
      "learning_rate": 1.7749513560584252e-05,
      "loss": 1.051,
      "step": 150
    },
    {
      "epoch": 0.6302521008403361,
      "eval_loss": 0.14084061980247498,
      "eval_runtime": 247.0151,
      "eval_samples_per_second": 1.623,
      "eval_steps_per_second": 0.409,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.86404819402752e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}