{
  "best_global_step": 203,
  "best_metric": 0.12307652831077576,
  "best_model_checkpoint": "/cache/outputs/checkpoint-203",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 203,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 17.74788475036621,
      "learning_rate": 0.0,
      "loss": 5.2296,
      "step": 1
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 18.899648666381836,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 4.5763,
      "step": 2
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 17.478742599487305,
      "learning_rate": 5.333333333333333e-05,
      "loss": 3.8061,
      "step": 3
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 6.993143081665039,
      "learning_rate": 8e-05,
      "loss": 1.9885,
      "step": 4
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 8.001960754394531,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.7205,
      "step": 5
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 3.1834046840667725,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.1047,
      "step": 6
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 1.3439714908599854,
      "learning_rate": 0.00016,
      "loss": 0.7238,
      "step": 7
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 1.5758135318756104,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.8051,
      "step": 8
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 1.299546241760254,
      "learning_rate": 0.00021333333333333333,
      "loss": 0.7102,
      "step": 9
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.8412534594535828,
      "learning_rate": 0.00024,
      "loss": 0.4769,
      "step": 10
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 0.8651800751686096,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.4883,
      "step": 11
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.7943485975265503,
      "learning_rate": 0.0002933333333333333,
      "loss": 0.5219,
      "step": 12
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 0.6727921366691589,
      "learning_rate": 0.00032,
      "loss": 0.3604,
      "step": 13
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.578971266746521,
      "learning_rate": 0.00034666666666666667,
      "loss": 0.4373,
      "step": 14
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.5071410536766052,
      "learning_rate": 0.0003733333333333334,
      "loss": 0.4108,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.6982496976852417,
      "learning_rate": 0.0004,
      "loss": 0.4349,
      "step": 16
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 0.44865670800209045,
      "learning_rate": 0.00039997207623717143,
      "loss": 0.3644,
      "step": 17
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 0.5113717317581177,
      "learning_rate": 0.00039988831274605094,
      "loss": 0.3863,
      "step": 18
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 0.5012100338935852,
      "learning_rate": 0.0003997487329165572,
      "loss": 0.2768,
      "step": 19
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.4838305413722992,
      "learning_rate": 0.0003995533757246307,
      "loss": 0.3422,
      "step": 20
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 0.6303550004959106,
      "learning_rate": 0.00039930229572135033,
      "loss": 0.3288,
      "step": 21
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 0.5895312428474426,
      "learning_rate": 0.00039899556301770084,
      "loss": 0.2696,
      "step": 22
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 0.5373993515968323,
      "learning_rate": 0.00039863326326499484,
      "loss": 0.3868,
      "step": 23
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.48342981934547424,
      "learning_rate": 0.000398215497630956,
      "loss": 0.3162,
      "step": 24
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.28195714950561523,
      "learning_rate": 0.0003977423827714692,
      "loss": 0.2556,
      "step": 25
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 0.637691855430603,
      "learning_rate": 0.00039721405079800573,
      "loss": 0.3809,
      "step": 26
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 0.3745051920413971,
      "learning_rate": 0.0003966306492407327,
      "loss": 0.2701,
      "step": 27
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.636221170425415,
      "learning_rate": 0.0003959923410073174,
      "loss": 0.308,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6435479521751404,
      "learning_rate": 0.0003952993043374369,
      "loss": 0.2667,
      "step": 29
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5053671598434448,
      "eval_runtime": 18.682,
      "eval_samples_per_second": 4.389,
      "eval_steps_per_second": 1.124,
      "step": 29
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 0.30985596776008606,
      "learning_rate": 0.00039455173275300745,
      "loss": 0.2241,
      "step": 30
    },
    {
      "epoch": 1.0689655172413792,
      "grad_norm": 0.6296059489250183,
      "learning_rate": 0.0003937498350041451,
      "loss": 0.3091,
      "step": 31
    },
    {
      "epoch": 1.103448275862069,
      "grad_norm": 0.5439299941062927,
      "learning_rate": 0.00039289383501087534,
      "loss": 0.2937,
      "step": 32
    },
    {
      "epoch": 1.1379310344827587,
      "grad_norm": 0.3232507109642029,
      "learning_rate": 0.0003919839718006062,
      "loss": 0.2528,
      "step": 33
    },
    {
      "epoch": 1.1724137931034484,
      "grad_norm": 0.511285662651062,
      "learning_rate": 0.0003910204994413825,
      "loss": 0.2235,
      "step": 34
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 1.3702025413513184,
      "learning_rate": 0.00039000368697094084,
      "loss": 0.2724,
      "step": 35
    },
    {
      "epoch": 1.2413793103448276,
      "grad_norm": 0.5106721520423889,
      "learning_rate": 0.0003889338183215838,
      "loss": 0.289,
      "step": 36
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.4077189266681671,
      "learning_rate": 0.0003878111922408956,
      "loss": 0.2459,
      "step": 37
    },
    {
      "epoch": 1.3103448275862069,
      "grad_norm": 0.7492893934249878,
      "learning_rate": 0.00038663612220832055,
      "loss": 0.2533,
      "step": 38
    },
    {
      "epoch": 1.3448275862068966,
      "grad_norm": 0.5893272757530212,
      "learning_rate": 0.00038540893634762753,
      "loss": 0.2458,
      "step": 39
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.8055713772773743,
      "learning_rate": 0.00038412997733528576,
      "loss": 0.2893,
      "step": 40
    },
    {
      "epoch": 1.4137931034482758,
      "grad_norm": 0.37418168783187866,
      "learning_rate": 0.00038279960230477655,
      "loss": 0.2172,
      "step": 41
    },
    {
      "epoch": 1.4482758620689655,
      "grad_norm": 0.44418400526046753,
      "learning_rate": 0.00038141818274686816,
      "loss": 0.237,
      "step": 42
    },
    {
      "epoch": 1.4827586206896552,
      "grad_norm": 0.3771205246448517,
      "learning_rate": 0.0003799861044058816,
      "loss": 0.2039,
      "step": 43
    },
    {
      "epoch": 1.5172413793103448,
      "grad_norm": 0.43807318806648254,
      "learning_rate": 0.00037850376717197626,
      "loss": 0.2328,
      "step": 44
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.3352651000022888,
      "learning_rate": 0.00037697158496948575,
      "loss": 0.2319,
      "step": 45
    },
    {
      "epoch": 1.5862068965517242,
      "grad_norm": 0.595750629901886,
      "learning_rate": 0.00037538998564133434,
      "loss": 0.3058,
      "step": 46
    },
    {
      "epoch": 1.6206896551724137,
      "grad_norm": 0.4095384478569031,
      "learning_rate": 0.0003737594108295673,
      "loss": 0.2451,
      "step": 47
    },
    {
      "epoch": 1.6551724137931034,
      "grad_norm": 0.3446806073188782,
      "learning_rate": 0.0003720803158520279,
      "loss": 0.2353,
      "step": 48
    },
    {
      "epoch": 1.6896551724137931,
      "grad_norm": 0.4992334842681885,
      "learning_rate": 0.0003703531695752152,
      "loss": 0.2178,
      "step": 49
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.3720123767852783,
      "learning_rate": 0.0003685784542833594,
      "loss": 0.2211,
      "step": 50
    },
    {
      "epoch": 1.7586206896551724,
      "grad_norm": 0.3732210397720337,
      "learning_rate": 0.00036675666554374944,
      "loss": 0.2299,
      "step": 51
    },
    {
      "epoch": 1.793103448275862,
      "grad_norm": 0.3584296703338623,
      "learning_rate": 0.00036488831206835207,
      "loss": 0.2098,
      "step": 52
    },
    {
      "epoch": 1.8275862068965516,
      "grad_norm": 0.3997485637664795,
      "learning_rate": 0.00036297391557176066,
      "loss": 0.2729,
      "step": 53
    },
    {
      "epoch": 1.8620689655172413,
      "grad_norm": 0.4166489243507385,
      "learning_rate": 0.0003610140106255126,
      "loss": 0.2177,
      "step": 54
    },
    {
      "epoch": 1.896551724137931,
      "grad_norm": 0.45685556530952454,
      "learning_rate": 0.0003590091445088166,
      "loss": 0.3138,
      "step": 55
    },
    {
      "epoch": 1.9310344827586206,
      "grad_norm": 0.49145734310150146,
      "learning_rate": 0.0003569598770557322,
      "loss": 0.2876,
      "step": 56
    },
    {
      "epoch": 1.9655172413793105,
      "grad_norm": 0.5870755910873413,
      "learning_rate": 0.0003548667804988427,
      "loss": 0.2103,
      "step": 57
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.601203441619873,
      "learning_rate": 0.00035273043930946646,
      "loss": 0.2372,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3301706910133362,
      "eval_runtime": 11.7909,
      "eval_samples_per_second": 6.955,
      "eval_steps_per_second": 1.781,
      "step": 58
    },
    {
      "epoch": 2.0344827586206895,
      "grad_norm": 0.6023654341697693,
      "learning_rate": 0.00035055145003445024,
      "loss": 0.2392,
      "step": 59
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 0.42505472898483276,
      "learning_rate": 0.00034833042112959153,
      "loss": 0.2214,
      "step": 60
    },
    {
      "epoch": 2.103448275862069,
      "grad_norm": 0.39177656173706055,
      "learning_rate": 0.0003460679727897339,
      "loss": 0.2266,
      "step": 61
    },
    {
      "epoch": 2.1379310344827585,
      "grad_norm": 0.4654797911643982,
      "learning_rate": 0.0003437647367755859,
      "loss": 0.2738,
      "step": 62
    },
    {
      "epoch": 2.1724137931034484,
      "grad_norm": 0.4213922917842865,
      "learning_rate": 0.0003414213562373095,
      "loss": 0.2064,
      "step": 63
    },
    {
      "epoch": 2.206896551724138,
      "grad_norm": 0.35119640827178955,
      "learning_rate": 0.0003390384855349285,
      "loss": 0.1575,
      "step": 64
    },
    {
      "epoch": 2.2413793103448274,
      "grad_norm": 0.3433196544647217,
      "learning_rate": 0.0003366167900556062,
      "loss": 0.1858,
      "step": 65
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 0.6012677550315857,
      "learning_rate": 0.0003341569460278447,
      "loss": 0.2321,
      "step": 66
    },
    {
      "epoch": 2.310344827586207,
      "grad_norm": 0.36528632044792175,
      "learning_rate": 0.00033165964033265636,
      "loss": 0.1871,
      "step": 67
    },
    {
      "epoch": 2.344827586206897,
      "grad_norm": 0.33606716990470886,
      "learning_rate": 0.0003291255703117605,
      "loss": 0.1316,
      "step": 68
    },
    {
      "epoch": 2.3793103448275863,
      "grad_norm": 0.4607170820236206,
      "learning_rate": 0.0003265554435728597,
      "loss": 0.23,
      "step": 69
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 0.35001179575920105,
      "learning_rate": 0.00032394997779204896,
      "loss": 0.1665,
      "step": 70
    },
    {
      "epoch": 2.4482758620689653,
      "grad_norm": 0.3442467451095581,
      "learning_rate": 0.0003213099005134135,
      "loss": 0.1568,
      "step": 71
    },
    {
      "epoch": 2.4827586206896552,
      "grad_norm": 0.35078802704811096,
      "learning_rate": 0.00031863594894587105,
      "loss": 0.168,
      "step": 72
    },
    {
      "epoch": 2.5172413793103448,
      "grad_norm": 0.3411742150783539,
      "learning_rate": 0.00031592886975731553,
      "loss": 0.2015,
      "step": 73
    },
    {
      "epoch": 2.5517241379310347,
      "grad_norm": 0.608189046382904,
      "learning_rate": 0.0003131894188661191,
      "loss": 0.24,
      "step": 74
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.9807543754577637,
      "learning_rate": 0.00031041836123005137,
      "loss": 0.2216,
      "step": 75
    },
    {
      "epoch": 2.6206896551724137,
      "grad_norm": 0.3027774691581726,
      "learning_rate": 0.00030761647063267457,
      "loss": 0.195,
      "step": 76
    },
    {
      "epoch": 2.655172413793103,
      "grad_norm": 0.3149068057537079,
      "learning_rate": 0.00030478452946727374,
      "loss": 0.1468,
      "step": 77
    },
    {
      "epoch": 2.689655172413793,
      "grad_norm": 0.29977571964263916,
      "learning_rate": 0.0003019233285183835,
      "loss": 0.162,
      "step": 78
    },
    {
      "epoch": 2.7241379310344827,
      "grad_norm": 0.33947068452835083,
      "learning_rate": 0.00029903366674097074,
      "loss": 0.1389,
      "step": 79
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.38519802689552307,
      "learning_rate": 0.00029611635103733675,
      "loss": 0.1543,
      "step": 80
    },
    {
      "epoch": 2.793103448275862,
      "grad_norm": 0.3749842941761017,
      "learning_rate": 0.00029317219603179964,
      "loss": 0.1761,
      "step": 81
    },
    {
      "epoch": 2.8275862068965516,
      "grad_norm": 0.4311760663986206,
      "learning_rate": 0.00029020202384322035,
      "loss": 0.2,
      "step": 82
    },
    {
      "epoch": 2.862068965517241,
      "grad_norm": 0.6397997736930847,
      "learning_rate": 0.0002872066638554366,
      "loss": 0.1925,
      "step": 83
    },
    {
      "epoch": 2.896551724137931,
      "grad_norm": 0.4956374764442444,
      "learning_rate": 0.000284186952485667,
      "loss": 0.16,
      "step": 84
    },
    {
      "epoch": 2.9310344827586206,
      "grad_norm": 0.3576422929763794,
      "learning_rate": 0.0002811437329509528,
      "loss": 0.1277,
      "step": 85
    },
    {
      "epoch": 2.9655172413793105,
      "grad_norm": 0.5354539155960083,
      "learning_rate": 0.00027807785503269894,
      "loss": 0.1905,
      "step": 86
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7227762341499329,
      "learning_rate": 0.00027499017483938426,
      "loss": 0.1457,
      "step": 87
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2014383226633072,
      "eval_runtime": 11.1734,
      "eval_samples_per_second": 7.339,
      "eval_steps_per_second": 1.879,
      "step": 87
    },
    {
      "epoch": 3.0344827586206895,
      "grad_norm": 0.4662579298019409,
      "learning_rate": 0.00027188155456750256,
      "loss": 0.1631,
      "step": 88
    },
    {
      "epoch": 3.0689655172413794,
      "grad_norm": 0.4082823097705841,
      "learning_rate": 0.00026875286226080603,
      "loss": 0.1211,
      "step": 89
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 0.33196941018104553,
      "learning_rate": 0.0002656049715679138,
      "loss": 0.1293,
      "step": 90
    },
    {
      "epoch": 3.1379310344827585,
      "grad_norm": 0.38381531834602356,
      "learning_rate": 0.0002624387614983573,
      "loss": 0.157,
      "step": 91
    },
    {
      "epoch": 3.1724137931034484,
      "grad_norm": 0.46282660961151123,
      "learning_rate": 0.00025925511617712685,
      "loss": 0.1516,
      "step": 92
    },
    {
      "epoch": 3.206896551724138,
      "grad_norm": 0.5028776526451111,
      "learning_rate": 0.00025605492459779126,
      "loss": 0.1341,
      "step": 93
    },
    {
      "epoch": 3.2413793103448274,
      "grad_norm": 0.40640944242477417,
      "learning_rate": 0.00025283908037425725,
      "loss": 0.1473,
      "step": 94
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 0.36019614338874817,
      "learning_rate": 0.00024960848149123866,
      "loss": 0.1496,
      "step": 95
    },
    {
      "epoch": 3.310344827586207,
      "grad_norm": 0.40027180314064026,
      "learning_rate": 0.0002463640300535057,
      "loss": 0.1315,
      "step": 96
    },
    {
      "epoch": 3.344827586206897,
      "grad_norm": 0.3519420027732849,
      "learning_rate": 0.00024310663203398273,
      "loss": 0.1558,
      "step": 97
    },
    {
      "epoch": 3.3793103448275863,
      "grad_norm": 0.31895291805267334,
      "learning_rate": 0.0002398371970207672,
      "loss": 0.1316,
      "step": 98
    },
    {
      "epoch": 3.413793103448276,
      "grad_norm": 0.5188913345336914,
      "learning_rate": 0.0002365566379631381,
      "loss": 0.1717,
      "step": 99
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.3724120557308197,
      "learning_rate": 0.00023326587091662603,
      "loss": 0.1305,
      "step": 100
    },
    {
      "epoch": 3.4827586206896552,
      "grad_norm": 0.37616410851478577,
      "learning_rate": 0.0002299658147872163,
      "loss": 0.1123,
      "step": 101
    },
    {
      "epoch": 3.5172413793103448,
      "grad_norm": 0.3182910680770874,
      "learning_rate": 0.0002266573910747558,
      "loss": 0.1483,
      "step": 102
    },
    {
      "epoch": 3.5517241379310347,
      "grad_norm": 0.3919450044631958,
      "learning_rate": 0.00022334152361563528,
      "loss": 0.1844,
      "step": 103
    },
    {
      "epoch": 3.586206896551724,
      "grad_norm": 0.37084081768989563,
      "learning_rate": 0.0002200191383248197,
      "loss": 0.147,
      "step": 104
    },
    {
      "epoch": 3.6206896551724137,
      "grad_norm": 0.21913090348243713,
      "learning_rate": 0.000216691162937298,
      "loss": 0.0857,
      "step": 105
    },
    {
      "epoch": 3.655172413793103,
      "grad_norm": 0.5852271914482117,
      "learning_rate": 0.00021335852674902434,
      "loss": 0.153,
      "step": 106
    },
    {
      "epoch": 3.689655172413793,
      "grad_norm": 0.3712017238140106,
      "learning_rate": 0.00021002216035742385,
      "loss": 0.1354,
      "step": 107
    },
    {
      "epoch": 3.7241379310344827,
      "grad_norm": 0.3357457220554352,
      "learning_rate": 0.00020668299540153493,
      "loss": 0.1256,
      "step": 108
    },
    {
      "epoch": 3.7586206896551726,
      "grad_norm": 0.5734804272651672,
      "learning_rate": 0.00020334196430186018,
      "loss": 0.1405,
      "step": 109
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 0.5242103934288025,
      "learning_rate": 0.0002,
      "loss": 0.1469,
      "step": 110
    },
    {
      "epoch": 3.8275862068965516,
      "grad_norm": 0.5228754878044128,
      "learning_rate": 0.0001966580356981398,
      "loss": 0.2241,
      "step": 111
    },
    {
      "epoch": 3.862068965517241,
      "grad_norm": 0.4682646691799164,
      "learning_rate": 0.00019331700459846517,
      "loss": 0.1912,
      "step": 112
    },
    {
      "epoch": 3.896551724137931,
      "grad_norm": 0.3244553208351135,
      "learning_rate": 0.00018997783964257617,
      "loss": 0.1303,
      "step": 113
    },
    {
      "epoch": 3.9310344827586206,
      "grad_norm": 0.32039758563041687,
      "learning_rate": 0.00018664147325097568,
      "loss": 0.1048,
      "step": 114
    },
    {
      "epoch": 3.9655172413793105,
      "grad_norm": 0.28546416759490967,
      "learning_rate": 0.00018330883706270209,
      "loss": 0.1166,
      "step": 115
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.49577587842941284,
      "learning_rate": 0.00017998086167518034,
      "loss": 0.0808,
      "step": 116
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.1669382005929947,
      "eval_runtime": 11.4691,
      "eval_samples_per_second": 7.15,
      "eval_steps_per_second": 1.831,
      "step": 116
    },
    {
      "epoch": 4.0344827586206895,
      "grad_norm": 0.29314538836479187,
      "learning_rate": 0.00017665847638436476,
      "loss": 0.123,
      "step": 117
    },
    {
      "epoch": 4.068965517241379,
      "grad_norm": 0.3075414299964905,
      "learning_rate": 0.0001733426089252443,
      "loss": 0.1309,
      "step": 118
    },
    {
      "epoch": 4.103448275862069,
      "grad_norm": 0.35980483889579773,
      "learning_rate": 0.00017003418521278373,
      "loss": 0.124,
      "step": 119
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.3515003025531769,
      "learning_rate": 0.00016673412908337401,
      "loss": 0.0992,
      "step": 120
    },
    {
      "epoch": 4.172413793103448,
      "grad_norm": 0.3396667242050171,
      "learning_rate": 0.00016344336203686198,
      "loss": 0.1256,
      "step": 121
    },
    {
      "epoch": 4.206896551724138,
      "grad_norm": 0.3930714428424835,
      "learning_rate": 0.00016016280297923282,
      "loss": 0.1003,
      "step": 122
    },
    {
      "epoch": 4.241379310344827,
      "grad_norm": 0.3275085985660553,
      "learning_rate": 0.0001568933679660173,
      "loss": 0.1025,
      "step": 123
    },
    {
      "epoch": 4.275862068965517,
      "grad_norm": 0.29073071479797363,
      "learning_rate": 0.00015363596994649433,
      "loss": 0.117,
      "step": 124
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 0.3251801133155823,
      "learning_rate": 0.00015039151850876134,
      "loss": 0.0929,
      "step": 125
    },
    {
      "epoch": 4.344827586206897,
      "grad_norm": 0.36564385890960693,
      "learning_rate": 0.00014716091962574282,
      "loss": 0.1114,
      "step": 126
    },
    {
      "epoch": 4.379310344827586,
      "grad_norm": 0.3105633556842804,
      "learning_rate": 0.00014394507540220876,
      "loss": 0.1069,
      "step": 127
    },
    {
      "epoch": 4.413793103448276,
      "grad_norm": 0.24759739637374878,
      "learning_rate": 0.00014074488382287322,
      "loss": 0.0831,
      "step": 128
    },
    {
      "epoch": 4.448275862068965,
      "grad_norm": 0.3449052572250366,
      "learning_rate": 0.00013756123850164274,
      "loss": 0.1032,
      "step": 129
    },
    {
      "epoch": 4.482758620689655,
      "grad_norm": 0.3175407946109772,
      "learning_rate": 0.00013439502843208618,
      "loss": 0.1003,
      "step": 130
    },
    {
      "epoch": 4.517241379310345,
      "grad_norm": 0.2750047445297241,
      "learning_rate": 0.00013124713773919407,
      "loss": 0.0731,
      "step": 131
    },
    {
      "epoch": 4.551724137931035,
      "grad_norm": 0.28757160902023315,
      "learning_rate": 0.00012811844543249748,
      "loss": 0.069,
      "step": 132
    },
    {
      "epoch": 4.586206896551724,
      "grad_norm": 0.392083078622818,
      "learning_rate": 0.00012500982516061582,
      "loss": 0.1213,
      "step": 133
    },
    {
      "epoch": 4.620689655172414,
      "grad_norm": 0.3845164179801941,
      "learning_rate": 0.00012192214496730105,
      "loss": 0.1173,
      "step": 134
    },
    {
      "epoch": 4.655172413793103,
      "grad_norm": 0.35339465737342834,
      "learning_rate": 0.00011885626704904729,
      "loss": 0.0917,
      "step": 135
    },
    {
      "epoch": 4.689655172413794,
      "grad_norm": 0.6020617485046387,
      "learning_rate": 0.00011581304751433304,
      "loss": 0.1217,
      "step": 136
    },
    {
      "epoch": 4.724137931034483,
      "grad_norm": 0.27444228529930115,
      "learning_rate": 0.0001127933361445635,
      "loss": 0.0851,
      "step": 137
    },
    {
      "epoch": 4.758620689655173,
      "grad_norm": 0.2869485020637512,
      "learning_rate": 0.0001097979761567796,
      "loss": 0.0821,
      "step": 138
    },
    {
      "epoch": 4.793103448275862,
      "grad_norm": 0.4190747141838074,
      "learning_rate": 0.00010682780396820038,
      "loss": 0.1453,
      "step": 139
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 0.2771516442298889,
      "learning_rate": 0.00010388364896266325,
      "loss": 0.0943,
      "step": 140
    },
    {
      "epoch": 4.862068965517241,
      "grad_norm": 0.3202371299266815,
      "learning_rate": 0.00010096633325902931,
      "loss": 0.0832,
      "step": 141
    },
    {
      "epoch": 4.896551724137931,
      "grad_norm": 0.3687487840652466,
      "learning_rate": 9.80766714816165e-05,
      "loss": 0.1047,
      "step": 142
    },
    {
      "epoch": 4.931034482758621,
      "grad_norm": 0.3594297170639038,
      "learning_rate": 9.52154705327263e-05,
      "loss": 0.1058,
      "step": 143
    },
    {
      "epoch": 4.9655172413793105,
      "grad_norm": 0.3087465465068817,
      "learning_rate": 9.238352936732549e-05,
      "loss": 0.0829,
      "step": 144
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4151803255081177,
      "learning_rate": 8.95816387699487e-05,
      "loss": 0.0728,
      "step": 145
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.142612025141716,
      "eval_runtime": 11.2217,
      "eval_samples_per_second": 7.307,
      "eval_steps_per_second": 1.871,
      "step": 145
    },
    {
      "epoch": 5.0344827586206895,
      "grad_norm": 0.32192564010620117,
      "learning_rate": 8.681058113388094e-05,
      "loss": 0.0795,
      "step": 146
    },
    {
      "epoch": 5.068965517241379,
      "grad_norm": 0.2751513421535492,
      "learning_rate": 8.407113024268449e-05,
      "loss": 0.096,
      "step": 147
    },
    {
      "epoch": 5.103448275862069,
      "grad_norm": 0.2346341460943222,
      "learning_rate": 8.136405105412897e-05,
      "loss": 0.0797,
      "step": 148
    },
    {
      "epoch": 5.137931034482759,
      "grad_norm": 0.2630951702594757,
      "learning_rate": 7.869009948658652e-05,
      "loss": 0.0687,
      "step": 149
    },
    {
      "epoch": 5.172413793103448,
      "grad_norm": 0.29806041717529297,
      "learning_rate": 7.605002220795106e-05,
      "loss": 0.0835,
      "step": 150
    },
    {
      "epoch": 5.206896551724138,
      "grad_norm": 0.3110710680484772,
      "learning_rate": 7.344455642714028e-05,
      "loss": 0.0694,
      "step": 151
    },
    {
      "epoch": 5.241379310344827,
      "grad_norm": 0.7218759655952454,
      "learning_rate": 7.087442968823952e-05,
      "loss": 0.0673,
      "step": 152
    },
    {
      "epoch": 5.275862068965517,
      "grad_norm": 0.33561110496520996,
      "learning_rate": 6.834035966734369e-05,
      "loss": 0.0874,
      "step": 153
    },
    {
      "epoch": 5.310344827586207,
      "grad_norm": 0.33989977836608887,
      "learning_rate": 6.584305397215536e-05,
      "loss": 0.0732,
      "step": 154
    },
    {
      "epoch": 5.344827586206897,
      "grad_norm": 0.4611569046974182,
      "learning_rate": 6.338320994439385e-05,
      "loss": 0.1063,
      "step": 155
    },
    {
      "epoch": 5.379310344827586,
      "grad_norm": 0.2923598289489746,
      "learning_rate": 6.0961514465071545e-05,
      "loss": 0.067,
      "step": 156
    },
    {
      "epoch": 5.413793103448276,
      "grad_norm": 0.3514823913574219,
      "learning_rate": 5.857864376269051e-05,
      "loss": 0.0924,
      "step": 157
    },
    {
      "epoch": 5.448275862068965,
      "grad_norm": 0.26756709814071655,
      "learning_rate": 5.623526322441417e-05,
      "loss": 0.0469,
      "step": 158
    },
    {
      "epoch": 5.482758620689655,
      "grad_norm": 0.3835451602935791,
      "learning_rate": 5.3932027210266177e-05,
      "loss": 0.089,
      "step": 159
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 0.3267417848110199,
      "learning_rate": 5.1669578870408486e-05,
      "loss": 0.0818,
      "step": 160
    },
    {
      "epoch": 5.551724137931035,
      "grad_norm": 0.33168888092041016,
      "learning_rate": 4.944854996554973e-05,
      "loss": 0.0897,
      "step": 161
    },
    {
      "epoch": 5.586206896551724,
      "grad_norm": 0.3530052900314331,
      "learning_rate": 4.726956069053361e-05,
      "loss": 0.102,
      "step": 162
    },
    {
      "epoch": 5.620689655172414,
      "grad_norm": 0.2784576416015625,
      "learning_rate": 4.5133219501157345e-05,
      "loss": 0.0546,
      "step": 163
    },
    {
      "epoch": 5.655172413793103,
      "grad_norm": 0.35242149233818054,
      "learning_rate": 4.3040122944267805e-05,
      "loss": 0.0694,
      "step": 164
    },
    {
      "epoch": 5.689655172413794,
      "grad_norm": 0.31660401821136475,
      "learning_rate": 4.09908554911834e-05,
      "loss": 0.0929,
      "step": 165
    },
    {
      "epoch": 5.724137931034483,
      "grad_norm": 0.40514034032821655,
      "learning_rate": 3.898598937448743e-05,
      "loss": 0.1084,
      "step": 166
    },
    {
      "epoch": 5.758620689655173,
      "grad_norm": 0.293292760848999,
      "learning_rate": 3.702608442823934e-05,
      "loss": 0.0599,
      "step": 167
    },
    {
      "epoch": 5.793103448275862,
      "grad_norm": 0.2863250970840454,
      "learning_rate": 3.5111687931647984e-05,
      "loss": 0.097,
      "step": 168
    },
    {
      "epoch": 5.827586206896552,
      "grad_norm": 0.4727107882499695,
      "learning_rate": 3.3243334456250604e-05,
      "loss": 0.0747,
      "step": 169
    },
    {
      "epoch": 5.862068965517241,
      "grad_norm": 0.3087122142314911,
      "learning_rate": 3.14215457166406e-05,
      "loss": 0.0821,
      "step": 170
    },
    {
      "epoch": 5.896551724137931,
      "grad_norm": 0.4154495596885681,
      "learning_rate": 2.9646830424784754e-05,
      "loss": 0.061,
      "step": 171
    },
    {
      "epoch": 5.931034482758621,
      "grad_norm": 0.4096265435218811,
      "learning_rate": 2.791968414797217e-05,
      "loss": 0.0873,
      "step": 172
    },
    {
      "epoch": 5.9655172413793105,
      "grad_norm": 0.31916359066963196,
      "learning_rate": 2.6240589170432706e-05,
      "loss": 0.0711,
      "step": 173
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.34077519178390503,
      "learning_rate": 2.46100143586657e-05,
      "loss": 0.0205,
      "step": 174
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.13364312052726746,
      "eval_runtime": 11.1536,
      "eval_samples_per_second": 7.352,
      "eval_steps_per_second": 1.883,
      "step": 174
    },
    {
      "epoch": 6.0344827586206895,
      "grad_norm": 0.32007357478141785,
      "learning_rate": 2.3028415030514293e-05,
      "loss": 0.0582,
      "step": 175
    },
    {
      "epoch": 6.068965517241379,
      "grad_norm": 0.44259366393089294,
      "learning_rate": 2.1496232828023776e-05,
      "loss": 0.088,
      "step": 176
    },
    {
      "epoch": 6.103448275862069,
      "grad_norm": 0.376699835062027,
      "learning_rate": 2.0013895594118438e-05,
      "loss": 0.0621,
      "step": 177
    },
    {
      "epoch": 6.137931034482759,
      "grad_norm": 0.298380047082901,
      "learning_rate": 1.858181725313186e-05,
      "loss": 0.0851,
      "step": 178
    },
    {
      "epoch": 6.172413793103448,
      "grad_norm": 0.32520031929016113,
      "learning_rate": 1.7200397695223458e-05,
      "loss": 0.0597,
      "step": 179
    },
    {
      "epoch": 6.206896551724138,
      "grad_norm": 0.2930215895175934,
      "learning_rate": 1.5870022664714224e-05,
      "loss": 0.0568,
      "step": 180
    },
    {
      "epoch": 6.241379310344827,
      "grad_norm": 0.3769894540309906,
      "learning_rate": 1.4591063652372528e-05,
      "loss": 0.0823,
      "step": 181
    },
    {
      "epoch": 6.275862068965517,
      "grad_norm": 0.35215336084365845,
      "learning_rate": 1.3363877791679491e-05,
      "loss": 0.0865,
      "step": 182
    },
    {
      "epoch": 6.310344827586207,
      "grad_norm": 0.36714300513267517,
      "learning_rate": 1.2188807759104426e-05,
      "loss": 0.0803,
      "step": 183
    },
    {
      "epoch": 6.344827586206897,
      "grad_norm": 0.2876943051815033,
      "learning_rate": 1.1066181678416266e-05,
      "loss": 0.065,
      "step": 184
    },
    {
      "epoch": 6.379310344827586,
      "grad_norm": 0.31088706851005554,
      "learning_rate": 9.99631302905919e-06,
      "loss": 0.0489,
      "step": 185
    },
    {
      "epoch": 6.413793103448276,
      "grad_norm": 0.2680237293243408,
      "learning_rate": 8.979500558617515e-06,
      "loss": 0.0499,
      "step": 186
    },
    {
      "epoch": 6.448275862068965,
      "grad_norm": 0.2737422287464142,
      "learning_rate": 8.016028199393844e-06,
      "loss": 0.0624,
      "step": 187
    },
    {
      "epoch": 6.482758620689655,
      "grad_norm": 0.3311713635921478,
      "learning_rate": 7.1061649891247084e-06,
      "loss": 0.0806,
      "step": 188
    },
    {
      "epoch": 6.517241379310345,
      "grad_norm": 0.3095020055770874,
      "learning_rate": 6.250164995854935e-06,
      "loss": 0.0529,
      "step": 189
    },
    {
      "epoch": 6.551724137931035,
      "grad_norm": 0.24900928139686584,
      "learning_rate": 5.448267246992589e-06,
      "loss": 0.0655,
      "step": 190
    },
    {
      "epoch": 6.586206896551724,
      "grad_norm": 0.33236587047576904,
      "learning_rate": 4.7006956625630595e-06,
      "loss": 0.0801,
      "step": 191
    },
    {
      "epoch": 6.620689655172414,
      "grad_norm": 0.2984936535358429,
      "learning_rate": 4.00765899268265e-06,
      "loss": 0.0728,
      "step": 192
    },
    {
      "epoch": 6.655172413793103,
      "grad_norm": 0.25962910056114197,
      "learning_rate": 3.369350759267298e-06,
      "loss": 0.0591,
      "step": 193
    },
    {
      "epoch": 6.689655172413794,
      "grad_norm": 0.42481696605682373,
      "learning_rate": 2.7859492019942866e-06,
      "loss": 0.1136,
      "step": 194
    },
    {
      "epoch": 6.724137931034483,
      "grad_norm": 0.2698614299297333,
      "learning_rate": 2.257617228530773e-06,
      "loss": 0.0668,
      "step": 195
    },
    {
      "epoch": 6.758620689655173,
      "grad_norm": 0.31150490045547485,
      "learning_rate": 1.7845023690439943e-06,
      "loss": 0.0742,
      "step": 196
    },
    {
      "epoch": 6.793103448275862,
      "grad_norm": 0.36004438996315,
      "learning_rate": 1.3667367350051808e-06,
      "loss": 0.0591,
      "step": 197
    },
    {
      "epoch": 6.827586206896552,
      "grad_norm": 0.31732040643692017,
      "learning_rate": 1.0044369822991729e-06,
      "loss": 0.0737,
      "step": 198
    },
    {
      "epoch": 6.862068965517241,
      "grad_norm": 0.24975836277008057,
      "learning_rate": 6.977042786496802e-07,
      "loss": 0.0469,
      "step": 199
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 0.2643037736415863,
      "learning_rate": 4.4662427536936725e-07,
      "loss": 0.0547,
      "step": 200
    },
    {
      "epoch": 6.931034482758621,
      "grad_norm": 0.24362404644489288,
      "learning_rate": 2.512670834428521e-07,
      "loss": 0.0368,
      "step": 201
    },
    {
      "epoch": 6.9655172413793105,
      "grad_norm": 0.2634768784046173,
      "learning_rate": 1.1168725394907764e-07,
      "loss": 0.0537,
      "step": 202
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.3374311923980713,
      "learning_rate": 2.7923762828585555e-08,
      "loss": 0.0299,
      "step": 203
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.12307652831077576,
      "eval_runtime": 11.2127,
      "eval_samples_per_second": 7.313,
      "eval_steps_per_second": 1.873,
      "step": 203
    }
  ],
  "logging_steps": 1,
  "max_steps": 203,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2373731961512346e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}