{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9854731056144483,
  "eval_steps": 80,
  "global_step": 636,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031409501374165686,
      "grad_norm": 5.125,
      "learning_rate": 2e-05,
      "loss": 10.7953,
      "step": 1
    },
    {
      "epoch": 0.0031409501374165686,
      "eval_loss": 10.810359001159668,
      "eval_runtime": 65.1601,
      "eval_samples_per_second": 39.917,
      "eval_steps_per_second": 39.917,
      "step": 1
    },
    {
      "epoch": 0.006281900274833137,
      "grad_norm": 4.59375,
      "learning_rate": 4e-05,
      "loss": 10.599,
      "step": 2
    },
    {
      "epoch": 0.009422850412249705,
      "grad_norm": 5.65625,
      "learning_rate": 6e-05,
      "loss": 10.8341,
      "step": 3
    },
    {
      "epoch": 0.012563800549666274,
      "grad_norm": 4.59375,
      "learning_rate": 8e-05,
      "loss": 10.2321,
      "step": 4
    },
    {
      "epoch": 0.015704750687082842,
      "grad_norm": 5.09375,
      "learning_rate": 0.0001,
      "loss": 9.926,
      "step": 5
    },
    {
      "epoch": 0.01884570082449941,
      "grad_norm": 5.09375,
      "learning_rate": 0.00012,
      "loss": 9.2807,
      "step": 6
    },
    {
      "epoch": 0.02198665096191598,
      "grad_norm": 5.21875,
      "learning_rate": 0.00014,
      "loss": 8.7401,
      "step": 7
    },
    {
      "epoch": 0.02512760109933255,
      "grad_norm": 5.3125,
      "learning_rate": 0.00016,
      "loss": 7.7479,
      "step": 8
    },
    {
      "epoch": 0.028268551236749116,
      "grad_norm": 3.78125,
      "learning_rate": 0.00018,
      "loss": 7.3356,
      "step": 9
    },
    {
      "epoch": 0.031409501374165684,
      "grad_norm": 4.15625,
      "learning_rate": 0.0002,
      "loss": 6.8649,
      "step": 10
    },
    {
      "epoch": 0.03455045151158225,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00019999969015048862,
      "loss": 6.7994,
      "step": 11
    },
    {
      "epoch": 0.03769140164899882,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0001999987606038746,
      "loss": 6.2436,
      "step": 12
    },
    {
      "epoch": 0.040832351786415394,
      "grad_norm": 2.125,
      "learning_rate": 0.0001999972113659183,
      "loss": 6.6684,
      "step": 13
    },
    {
      "epoch": 0.04397330192383196,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00019999504244622043,
      "loss": 6.4968,
      "step": 14
    },
    {
      "epoch": 0.04711425206124853,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019999225385822165,
      "loss": 6.3331,
      "step": 15
    },
    {
      "epoch": 0.0502552021986651,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00019998884561920284,
      "loss": 6.3441,
      "step": 16
    },
    {
      "epoch": 0.053396152336081665,
      "grad_norm": 1.171875,
      "learning_rate": 0.00019998481775028491,
      "loss": 5.8419,
      "step": 17
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0001999801702764284,
      "loss": 6.1942,
      "step": 18
    },
    {
      "epoch": 0.0596780526109148,
      "grad_norm": 1.75,
      "learning_rate": 0.00019997490322643376,
      "loss": 6.017,
      "step": 19
    },
    {
      "epoch": 0.06281900274833137,
      "grad_norm": 1.1875,
      "learning_rate": 0.00019996901663294078,
      "loss": 6.2501,
      "step": 20
    },
    {
      "epoch": 0.06595995288574794,
      "grad_norm": 0.9296875,
      "learning_rate": 0.00019996251053242865,
      "loss": 5.9597,
      "step": 21
    },
    {
      "epoch": 0.0691009030231645,
      "grad_norm": 1.8984375,
      "learning_rate": 0.0001999553849652156,
      "loss": 6.0591,
      "step": 22
    },
    {
      "epoch": 0.07224185316058107,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019994763997545874,
      "loss": 6.2802,
      "step": 23
    },
    {
      "epoch": 0.07538280329799764,
      "grad_norm": 1.7265625,
      "learning_rate": 0.00019993927561115366,
      "loss": 6.082,
      "step": 24
    },
    {
      "epoch": 0.0785237534354142,
      "grad_norm": 1.0,
      "learning_rate": 0.00019993029192413424,
      "loss": 6.1596,
      "step": 25
    },
    {
      "epoch": 0.08166470357283079,
      "grad_norm": 1.609375,
      "learning_rate": 0.00019992068897007232,
      "loss": 5.9254,
      "step": 26
    },
    {
      "epoch": 0.08480565371024736,
      "grad_norm": 1.5234375,
      "learning_rate": 0.0001999104668084773,
      "loss": 5.893,
      "step": 27
    },
    {
      "epoch": 0.08794660384766392,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019989962550269583,
      "loss": 6.1184,
      "step": 28
    },
    {
      "epoch": 0.09108755398508049,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00019988816511991135,
      "loss": 5.9582,
      "step": 29
    },
    {
      "epoch": 0.09422850412249706,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019987608573114376,
      "loss": 5.8845,
      "step": 30
    },
    {
      "epoch": 0.09736945425991363,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0001998633874112489,
      "loss": 6.1202,
      "step": 31
    },
    {
      "epoch": 0.1005104043973302,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00019985007023891815,
      "loss": 5.7627,
      "step": 32
    },
    {
      "epoch": 0.10365135453474676,
      "grad_norm": 0.8828125,
      "learning_rate": 0.00019983613429667792,
      "loss": 6.0619,
      "step": 33
    },
    {
      "epoch": 0.10679230467216333,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019982157967088904,
      "loss": 5.683,
      "step": 34
    },
    {
      "epoch": 0.1099332548095799,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0001998064064517464,
      "loss": 5.8008,
      "step": 35
    },
    {
      "epoch": 0.11307420494699646,
      "grad_norm": 1.375,
      "learning_rate": 0.00019979061473327837,
      "loss": 5.8867,
      "step": 36
    },
    {
      "epoch": 0.11621515508441303,
      "grad_norm": 1.671875,
      "learning_rate": 0.000199774204613346,
      "loss": 5.9331,
      "step": 37
    },
    {
      "epoch": 0.1193561052218296,
      "grad_norm": 1.4375,
      "learning_rate": 0.00019975717619364263,
      "loss": 5.4695,
      "step": 38
    },
    {
      "epoch": 0.12249705535924617,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001997395295796933,
      "loss": 5.9711,
      "step": 39
    },
    {
      "epoch": 0.12563800549666274,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00019972126488085378,
      "loss": 5.7401,
      "step": 40
    },
    {
      "epoch": 0.12877895563407932,
      "grad_norm": 1.390625,
      "learning_rate": 0.00019970238221031034,
      "loss": 5.7064,
      "step": 41
    },
    {
      "epoch": 0.13191990577149587,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019968288168507864,
      "loss": 5.6272,
      "step": 42
    },
    {
      "epoch": 0.13506085590891245,
      "grad_norm": 1.8359375,
      "learning_rate": 0.00019966276342600327,
      "loss": 5.4439,
      "step": 43
    },
    {
      "epoch": 0.138201806046329,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001996420275577569,
      "loss": 5.9631,
      "step": 44
    },
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00019962067420883944,
      "loss": 5.8393,
      "step": 45
    },
    {
      "epoch": 0.14448370632116214,
      "grad_norm": 1.53125,
      "learning_rate": 0.00019959870351157747,
      "loss": 5.7997,
      "step": 46
    },
    {
      "epoch": 0.14762465645857872,
      "grad_norm": 1.3984375,
      "learning_rate": 0.0001995761156021231,
      "loss": 5.656,
      "step": 47
    },
    {
      "epoch": 0.15076560659599528,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00019955291062045345,
      "loss": 5.7152,
      "step": 48
    },
    {
      "epoch": 0.15390655673341186,
      "grad_norm": 1.828125,
      "learning_rate": 0.00019952908871036956,
      "loss": 5.7215,
      "step": 49
    },
    {
      "epoch": 0.1570475068708284,
      "grad_norm": 1.0,
      "learning_rate": 0.0001995046500194955,
      "loss": 5.6857,
      "step": 50
    },
    {
      "epoch": 0.160188457008245,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00019947959469927772,
      "loss": 5.6698,
      "step": 51
    },
    {
      "epoch": 0.16332940714566158,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001994539229049837,
      "loss": 5.2906,
      "step": 52
    },
    {
      "epoch": 0.16647035728307813,
      "grad_norm": 1.25,
      "learning_rate": 0.00019942763479570132,
      "loss": 5.4673,
      "step": 53
    },
    {
      "epoch": 0.1696113074204947,
      "grad_norm": 0.890625,
      "learning_rate": 0.00019940073053433777,
      "loss": 5.5959,
      "step": 54
    },
    {
      "epoch": 0.17275225755791127,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019937321028761846,
      "loss": 5.9431,
      "step": 55
    },
    {
      "epoch": 0.17589320769532785,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019934507422608608,
      "loss": 5.754,
      "step": 56
    },
    {
      "epoch": 0.1790341578327444,
      "grad_norm": 0.984375,
      "learning_rate": 0.00019931632252409955,
      "loss": 5.405,
      "step": 57
    },
    {
      "epoch": 0.18217510797016098,
      "grad_norm": 1.03125,
      "learning_rate": 0.00019928695535983287,
      "loss": 5.5907,
      "step": 58
    },
    {
      "epoch": 0.18531605810757754,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00019925697291527415,
      "loss": 5.7941,
      "step": 59
    },
    {
      "epoch": 0.18845700824499412,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019922637537622418,
      "loss": 5.6169,
      "step": 60
    },
    {
      "epoch": 0.19159795838241067,
      "grad_norm": 1.5,
      "learning_rate": 0.00019919516293229569,
      "loss": 5.5379,
      "step": 61
    },
    {
      "epoch": 0.19473890851982725,
      "grad_norm": 0.8203125,
      "learning_rate": 0.00019916333577691184,
      "loss": 5.6157,
      "step": 62
    },
    {
      "epoch": 0.1978798586572438,
      "grad_norm": 1.484375,
      "learning_rate": 0.00019913089410730526,
      "loss": 5.5043,
      "step": 63
    },
    {
      "epoch": 0.2010208087946604,
      "grad_norm": 0.98046875,
      "learning_rate": 0.00019909783812451664,
      "loss": 5.7083,
      "step": 64
    },
    {
      "epoch": 0.20416175893207694,
      "grad_norm": 1.125,
      "learning_rate": 0.00019906416803339353,
      "loss": 5.5739,
      "step": 65
    },
    {
      "epoch": 0.20730270906949352,
      "grad_norm": 1.375,
      "learning_rate": 0.00019902988404258922,
      "loss": 5.5447,
      "step": 66
    },
    {
      "epoch": 0.21044365920691008,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019899498636456126,
      "loss": 5.3392,
      "step": 67
    },
    {
      "epoch": 0.21358460934432666,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001989594752155702,
      "loss": 5.3176,
      "step": 68
    },
    {
      "epoch": 0.21672555948174324,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019892335081567826,
      "loss": 5.1688,
      "step": 69
    },
    {
      "epoch": 0.2198665096191598,
      "grad_norm": 0.953125,
      "learning_rate": 0.00019888661338874803,
      "loss": 5.5142,
      "step": 70
    },
    {
      "epoch": 0.22300745975657638,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000198849263162441,
      "loss": 5.3004,
      "step": 71
    },
    {
      "epoch": 0.22614840989399293,
      "grad_norm": 0.7890625,
      "learning_rate": 0.0001988113003682161,
      "loss": 5.5914,
      "step": 72
    },
    {
      "epoch": 0.2292893600314095,
      "grad_norm": 0.71484375,
      "learning_rate": 0.00019877272524132847,
      "loss": 5.4175,
      "step": 73
    },
    {
      "epoch": 0.23243031016882607,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00019873353802082771,
      "loss": 5.0854,
      "step": 74
    },
    {
      "epoch": 0.23557126030624265,
      "grad_norm": 1.046875,
      "learning_rate": 0.00019869373894955669,
      "loss": 5.5772,
      "step": 75
    },
    {
      "epoch": 0.2387122104436592,
      "grad_norm": 1.390625,
      "learning_rate": 0.00019865332827414988,
      "loss": 5.4289,
      "step": 76
    },
    {
      "epoch": 0.24185316058107578,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0001986123062450318,
      "loss": 5.5427,
      "step": 77
    },
    {
      "epoch": 0.24499411071849234,
      "grad_norm": 0.82421875,
      "learning_rate": 0.0001985706731164156,
      "loss": 5.3294,
      "step": 78
    },
    {
      "epoch": 0.24813506085590892,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00019852842914630137,
      "loss": 5.3756,
      "step": 79
    },
    {
      "epoch": 0.25127601099332547,
      "grad_norm": 1.375,
      "learning_rate": 0.00019848557459647455,
      "loss": 5.4963,
      "step": 80
    },
    {
      "epoch": 0.25127601099332547,
      "eval_loss": 5.410098075866699,
      "eval_runtime": 66.9514,
      "eval_samples_per_second": 38.849,
      "eval_steps_per_second": 38.849,
      "step": 80
    },
    {
      "epoch": 0.254416961130742,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019844210973250437,
      "loss": 5.4053,
      "step": 81
    },
    {
      "epoch": 0.25755791126815863,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001983980348237422,
      "loss": 5.3084,
      "step": 82
    },
    {
      "epoch": 0.2606988614055752,
      "grad_norm": 0.95703125,
      "learning_rate": 0.00019835335014331976,
      "loss": 5.4774,
      "step": 83
    },
    {
      "epoch": 0.26383981154299174,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019830805596814766,
      "loss": 5.3591,
      "step": 84
    },
    {
      "epoch": 0.2669807616804083,
      "grad_norm": 1.46875,
      "learning_rate": 0.00019826215257891342,
      "loss": 5.2504,
      "step": 85
    },
    {
      "epoch": 0.2701217118178249,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019821564026007988,
      "loss": 5.2333,
      "step": 86
    },
    {
      "epoch": 0.27326266195524146,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001981685192998834,
      "loss": 5.4557,
      "step": 87
    },
    {
      "epoch": 0.276403612092658,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019812078999033222,
      "loss": 5.5066,
      "step": 88
    },
    {
      "epoch": 0.2795445622300746,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019807245262720426,
      "loss": 5.3617,
      "step": 89
    },
    {
      "epoch": 0.2826855123674912,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001980235075100458,
      "loss": 5.4076,
      "step": 90
    },
    {
      "epoch": 0.28582646250490773,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019797395494216923,
      "loss": 5.2482,
      "step": 91
    },
    {
      "epoch": 0.2889674126423243,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00019792379523065126,
      "loss": 5.1448,
      "step": 92
    },
    {
      "epoch": 0.2921083627797409,
      "grad_norm": 1.1015625,
      "learning_rate": 0.0001978730286863312,
      "loss": 5.2483,
      "step": 93
    },
    {
      "epoch": 0.29524931291715745,
      "grad_norm": 1.0234375,
      "learning_rate": 0.0001978216556238088,
      "loss": 5.1698,
      "step": 94
    },
    {
      "epoch": 0.298390263054574,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019776967636144245,
      "loss": 5.3225,
      "step": 95
    },
    {
      "epoch": 0.30153121319199055,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00019771709122134713,
      "loss": 5.3077,
      "step": 96
    },
    {
      "epoch": 0.30467216332940716,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019766390052939242,
      "loss": 5.2636,
      "step": 97
    },
    {
      "epoch": 0.3078131134668237,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019761010461520054,
      "loss": 5.4547,
      "step": 98
    },
    {
      "epoch": 0.31095406360424027,
      "grad_norm": 0.85546875,
      "learning_rate": 0.0001975557038121442,
      "loss": 5.2564,
      "step": 99
    },
    {
      "epoch": 0.3140950137416568,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00019750069845734473,
      "loss": 4.9768,
      "step": 100
    },
    {
      "epoch": 0.31723596387907343,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019744508889166966,
      "loss": 5.2283,
      "step": 101
    },
    {
      "epoch": 0.32037691401649,
      "grad_norm": 1.34375,
      "learning_rate": 0.00019738887545973102,
      "loss": 5.4258,
      "step": 102
    },
    {
      "epoch": 0.32351786415390654,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019733205850988285,
      "loss": 5.2331,
      "step": 103
    },
    {
      "epoch": 0.32665881429132315,
      "grad_norm": 0.828125,
      "learning_rate": 0.00019727463839421926,
      "loss": 5.1852,
      "step": 104
    },
    {
      "epoch": 0.3297997644287397,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019721661546857213,
      "loss": 5.4063,
      "step": 105
    },
    {
      "epoch": 0.33294071456615626,
      "grad_norm": 0.8359375,
      "learning_rate": 0.000197157990092509,
      "loss": 5.2671,
      "step": 106
    },
    {
      "epoch": 0.3360816647035728,
      "grad_norm": 0.94140625,
      "learning_rate": 0.00019709876262933066,
      "loss": 5.3544,
      "step": 107
    },
    {
      "epoch": 0.3392226148409894,
      "grad_norm": 0.9609375,
      "learning_rate": 0.0001970389334460692,
      "loss": 5.1728,
      "step": 108
    },
    {
      "epoch": 0.342363564978406,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019697850291348548,
      "loss": 5.3887,
      "step": 109
    },
    {
      "epoch": 0.34550451511582253,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00019691747140606692,
      "loss": 5.1095,
      "step": 110
    },
    {
      "epoch": 0.3486454652532391,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019685583930202514,
      "loss": 5.1703,
      "step": 111
    },
    {
      "epoch": 0.3517864153906557,
      "grad_norm": 0.81640625,
      "learning_rate": 0.0001967936069832937,
      "loss": 5.17,
      "step": 112
    },
    {
      "epoch": 0.35492736552807225,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019673077483552568,
      "loss": 5.0519,
      "step": 113
    },
    {
      "epoch": 0.3580683156654888,
      "grad_norm": 0.87109375,
      "learning_rate": 0.00019666734324809125,
      "loss": 5.186,
      "step": 114
    },
    {
      "epoch": 0.36120926580290535,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00019660331261407544,
      "loss": 5.0202,
      "step": 115
    },
    {
      "epoch": 0.36435021594032196,
      "grad_norm": 0.70703125,
      "learning_rate": 0.00019653868333027535,
      "loss": 5.1102,
      "step": 116
    },
    {
      "epoch": 0.3674911660777385,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019647345579719807,
      "loss": 5.1,
      "step": 117
    },
    {
      "epoch": 0.37063211621515507,
      "grad_norm": 1.078125,
      "learning_rate": 0.000196407630419058,
      "loss": 5.0466,
      "step": 118
    },
    {
      "epoch": 0.3737730663525716,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00019634120760377428,
      "loss": 5.3088,
      "step": 119
    },
    {
      "epoch": 0.37691401648998824,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00019627418776296858,
      "loss": 5.2293,
      "step": 120
    },
    {
      "epoch": 0.3800549666274048,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019620657131196208,
      "loss": 5.2738,
      "step": 121
    },
    {
      "epoch": 0.38319591676482134,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019613835866977335,
      "loss": 4.9497,
      "step": 122
    },
    {
      "epoch": 0.38633686690223795,
      "grad_norm": 0.9375,
      "learning_rate": 0.00019606955025911542,
      "loss": 5.2231,
      "step": 123
    },
    {
      "epoch": 0.3894778170396545,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019600014650639333,
      "loss": 5.3426,
      "step": 124
    },
    {
      "epoch": 0.39261876717707106,
      "grad_norm": 0.76953125,
      "learning_rate": 0.00019593014784170153,
      "loss": 5.0717,
      "step": 125
    },
    {
      "epoch": 0.3957597173144876,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00019585955469882097,
      "loss": 5.1569,
      "step": 126
    },
    {
      "epoch": 0.3989006674519042,
      "grad_norm": 0.75390625,
      "learning_rate": 0.0001957883675152167,
      "loss": 4.9017,
      "step": 127
    },
    {
      "epoch": 0.4020416175893208,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00019571658673203502,
      "loss": 5.1124,
      "step": 128
    },
    {
      "epoch": 0.40518256772673733,
      "grad_norm": 0.953125,
      "learning_rate": 0.00019564421279410075,
      "loss": 4.7849,
      "step": 129
    },
    {
      "epoch": 0.4083235178641539,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019557124614991443,
      "loss": 5.1534,
      "step": 130
    },
    {
      "epoch": 0.4114644680015705,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019549768725164967,
      "loss": 5.2731,
      "step": 131
    },
    {
      "epoch": 0.41460541813898705,
      "grad_norm": 1.0,
      "learning_rate": 0.00019542353655515023,
      "loss": 5.0467,
      "step": 132
    },
    {
      "epoch": 0.4177463682764036,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00019534879451992728,
      "loss": 4.8911,
      "step": 133
    },
    {
      "epoch": 0.42088731841382016,
      "grad_norm": 0.875,
      "learning_rate": 0.00019527346160915646,
      "loss": 5.2338,
      "step": 134
    },
    {
      "epoch": 0.42402826855123676,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019519753828967508,
      "loss": 5.1705,
      "step": 135
    },
    {
      "epoch": 0.4271692186886533,
      "grad_norm": 0.96484375,
      "learning_rate": 0.00019512102503197923,
      "loss": 5.3178,
      "step": 136
    },
    {
      "epoch": 0.43031016882606987,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019504392231022076,
      "loss": 5.1462,
      "step": 137
    },
    {
      "epoch": 0.4334511189634865,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00019496623060220457,
      "loss": 5.0293,
      "step": 138
    },
    {
      "epoch": 0.43659206910090304,
      "grad_norm": 1.046875,
      "learning_rate": 0.00019488795038938536,
      "loss": 5.0523,
      "step": 139
    },
    {
      "epoch": 0.4397330192383196,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00019480908215686486,
      "loss": 5.0893,
      "step": 140
    },
    {
      "epoch": 0.44287396937573614,
      "grad_norm": 0.79296875,
      "learning_rate": 0.00019472962639338875,
      "loss": 5.0682,
      "step": 141
    },
    {
      "epoch": 0.44601491951315275,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019464958359134354,
      "loss": 5.1261,
      "step": 142
    },
    {
      "epoch": 0.4491558696505693,
      "grad_norm": 1.09375,
      "learning_rate": 0.00019456895424675382,
      "loss": 5.2513,
      "step": 143
    },
    {
      "epoch": 0.45229681978798586,
      "grad_norm": 0.87890625,
      "learning_rate": 0.00019448773885927877,
      "loss": 5.0248,
      "step": 144
    },
    {
      "epoch": 0.4554377699254024,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00019440593793220936,
      "loss": 4.9527,
      "step": 145
    },
    {
      "epoch": 0.458578720062819,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019432355197246515,
      "loss": 5.1182,
      "step": 146
    },
    {
      "epoch": 0.4617196702002356,
      "grad_norm": 1.125,
      "learning_rate": 0.00019424058149059112,
      "loss": 5.043,
      "step": 147
    },
    {
      "epoch": 0.46486062033765213,
      "grad_norm": 0.98828125,
      "learning_rate": 0.00019415702700075453,
      "loss": 5.1351,
      "step": 148
    },
    {
      "epoch": 0.4680015704750687,
      "grad_norm": 1.234375,
      "learning_rate": 0.00019407288902074176,
      "loss": 5.0489,
      "step": 149
    },
    {
      "epoch": 0.4711425206124853,
      "grad_norm": 1.265625,
      "learning_rate": 0.00019398816807195498,
      "loss": 4.8494,
      "step": 150
    },
    {
      "epoch": 0.47428347074990185,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00019390286467940918,
      "loss": 5.196,
      "step": 151
    },
    {
      "epoch": 0.4774244208873184,
      "grad_norm": 1.0859375,
      "learning_rate": 0.0001938169793717286,
      "loss": 4.9598,
      "step": 152
    },
    {
      "epoch": 0.48056537102473496,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001937305126811437,
      "loss": 5.1067,
      "step": 153
    },
    {
      "epoch": 0.48370632116215156,
      "grad_norm": 0.7890625,
      "learning_rate": 0.0001936434651434876,
      "loss": 5.1599,
      "step": 154
    },
    {
      "epoch": 0.4868472712995681,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019355583729819317,
      "loss": 4.9971,
      "step": 155
    },
    {
      "epoch": 0.48998822143698467,
      "grad_norm": 1.25,
      "learning_rate": 0.0001934676296882892,
      "loss": 5.0528,
      "step": 156
    },
    {
      "epoch": 0.4931291715744013,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019337884286039746,
      "loss": 5.2021,
      "step": 157
    },
    {
      "epoch": 0.49627012171181784,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019328947736472904,
      "loss": 4.7814,
      "step": 158
    },
    {
      "epoch": 0.4994110718492344,
      "grad_norm": 1.0,
      "learning_rate": 0.00019319953375508106,
      "loss": 5.0906,
      "step": 159
    },
    {
      "epoch": 0.5025520219866509,
      "grad_norm": 0.91015625,
      "learning_rate": 0.00019310901258883317,
      "loss": 5.0323,
      "step": 160
    },
    {
      "epoch": 0.5025520219866509,
      "eval_loss": 5.075822353363037,
      "eval_runtime": 66.934,
      "eval_samples_per_second": 38.859,
      "eval_steps_per_second": 38.859,
      "step": 160
    },
    {
      "epoch": 0.5056929721240675,
      "grad_norm": 0.921875,
      "learning_rate": 0.00019301791442694413,
      "loss": 5.1209,
      "step": 161
    },
    {
      "epoch": 0.508833922261484,
      "grad_norm": 2.765625,
      "learning_rate": 0.00019292623983394838,
      "loss": 5.0187,
      "step": 162
    },
    {
      "epoch": 0.5119748723989007,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001928339893779525,
      "loss": 4.9584,
      "step": 163
    },
    {
      "epoch": 0.5151158225363173,
      "grad_norm": 1.28125,
      "learning_rate": 0.00019274116363063163,
      "loss": 4.9459,
      "step": 164
    },
    {
      "epoch": 0.5182567726737338,
      "grad_norm": 0.859375,
      "learning_rate": 0.00019264776316722603,
      "loss": 4.7699,
      "step": 165
    },
    {
      "epoch": 0.5213977228111504,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019255378856653746,
      "loss": 5.0324,
      "step": 166
    },
    {
      "epoch": 0.5245386729485669,
      "grad_norm": 1.15625,
      "learning_rate": 0.00019245924041092562,
      "loss": 5.2702,
      "step": 167
    },
    {
      "epoch": 0.5276796230859835,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019236411928630446,
      "loss": 5.0989,
      "step": 168
    },
    {
      "epoch": 0.5308205732234,
      "grad_norm": 0.93359375,
      "learning_rate": 0.00019226842578213874,
      "loss": 4.7667,
      "step": 169
    },
    {
      "epoch": 0.5339615233608166,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00019217216049144007,
      "loss": 4.8303,
      "step": 170
    },
    {
      "epoch": 0.5371024734982333,
      "grad_norm": 0.8984375,
      "learning_rate": 0.00019207532401076358,
      "loss": 5.0607,
      "step": 171
    },
    {
      "epoch": 0.5402434236356498,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00019197791694020396,
      "loss": 4.96,
      "step": 172
    },
    {
      "epoch": 0.5433843737730664,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00019187993988339192,
      "loss": 5.0107,
      "step": 173
    },
    {
      "epoch": 0.5465253239104829,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001917813934474903,
      "loss": 5.1961,
      "step": 174
    },
    {
      "epoch": 0.5496662740478995,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001916822782431904,
      "loss": 5.0727,
      "step": 175
    },
    {
      "epoch": 0.552807224185316,
      "grad_norm": 1.203125,
      "learning_rate": 0.00019158259488470815,
      "loss": 4.8185,
      "step": 176
    },
    {
      "epoch": 0.5559481743227326,
      "grad_norm": 1.59375,
      "learning_rate": 0.00019148234398978038,
      "loss": 5.2447,
      "step": 177
    },
    {
      "epoch": 0.5590891244601492,
      "grad_norm": 1.25,
      "learning_rate": 0.0001913815261796609,
      "loss": 5.0844,
      "step": 178
    },
    {
      "epoch": 0.5622300745975658,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001912801420791167,
      "loss": 5.0112,
      "step": 179
    },
    {
      "epoch": 0.5653710247349824,
      "grad_norm": 1.3671875,
      "learning_rate": 0.000191178192316424,
      "loss": 5.1335,
      "step": 180
    },
    {
      "epoch": 0.5685119748723989,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019107567752336458,
      "loss": 5.1664,
      "step": 181
    },
    {
      "epoch": 0.5716529250098155,
      "grad_norm": 0.90625,
      "learning_rate": 0.0001909725983352215,
      "loss": 4.9254,
      "step": 182
    },
    {
      "epoch": 0.574793875147232,
      "grad_norm": 0.8515625,
      "learning_rate": 0.00019086895539077562,
      "loss": 4.8303,
      "step": 183
    },
    {
      "epoch": 0.5779348252846486,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019076474933230116,
      "loss": 4.9595,
      "step": 184
    },
    {
      "epoch": 0.5810757754220651,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019065998080556204,
      "loss": 5.0253,
      "step": 185
    },
    {
      "epoch": 0.5842167255594818,
      "grad_norm": 1.078125,
      "learning_rate": 0.00019055465045980782,
      "loss": 5.1003,
      "step": 186
    },
    {
      "epoch": 0.5873576756968983,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00019044875894776966,
      "loss": 4.9631,
      "step": 187
    },
    {
      "epoch": 0.5904986258343149,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00019034230692565614,
      "loss": 4.9462,
      "step": 188
    },
    {
      "epoch": 0.5936395759717314,
      "grad_norm": 1.4453125,
      "learning_rate": 0.0001902352950531495,
      "loss": 4.8688,
      "step": 189
    },
    {
      "epoch": 0.596780526109148,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0001901277239934012,
      "loss": 5.1219,
      "step": 190
    },
    {
      "epoch": 0.5999214762465646,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019001959441302806,
      "loss": 5.0382,
      "step": 191
    },
    {
      "epoch": 0.6030624263839811,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00018991090698210802,
      "loss": 4.9474,
      "step": 192
    },
    {
      "epoch": 0.6062033765213978,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00018980166237417606,
      "loss": 5.034,
      "step": 193
    },
    {
      "epoch": 0.6093443266588143,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018969186126621996,
      "loss": 5.0142,
      "step": 194
    },
    {
      "epoch": 0.6124852767962309,
      "grad_norm": 1.203125,
      "learning_rate": 0.00018958150433867605,
      "loss": 4.7944,
      "step": 195
    },
    {
      "epoch": 0.6156262269336474,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001894705922754252,
      "loss": 4.7905,
      "step": 196
    },
    {
      "epoch": 0.618767177071064,
      "grad_norm": 0.92578125,
      "learning_rate": 0.0001893591257637883,
      "loss": 4.8537,
      "step": 197
    },
    {
      "epoch": 0.6219081272084805,
      "grad_norm": 1.15625,
      "learning_rate": 0.00018924710549452232,
      "loss": 4.8625,
      "step": 198
    },
    {
      "epoch": 0.6250490773458971,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001891345321618157,
      "loss": 5.1188,
      "step": 199
    },
    {
      "epoch": 0.6281900274833137,
      "grad_norm": 0.9921875,
      "learning_rate": 0.00018902140646328435,
      "loss": 4.7798,
      "step": 200
    },
    {
      "epoch": 0.6313309776207303,
      "grad_norm": 1.234375,
      "learning_rate": 0.0001889077290999671,
      "loss": 4.9184,
      "step": 201
    },
    {
      "epoch": 0.6344719277581469,
      "grad_norm": 1.375,
      "learning_rate": 0.00018879350077632143,
      "loss": 5.0932,
      "step": 202
    },
    {
      "epoch": 0.6376128778955634,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00018867872220021913,
      "loss": 4.9846,
      "step": 203
    },
    {
      "epoch": 0.64075382803298,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00018856339408294202,
      "loss": 4.8107,
      "step": 204
    },
    {
      "epoch": 0.6438947781703965,
      "grad_norm": 1.0625,
      "learning_rate": 0.0001884475171391772,
      "loss": 4.9413,
      "step": 205
    },
    {
      "epoch": 0.6470357283078131,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00018833109208701298,
      "loss": 4.9209,
      "step": 206
    },
    {
      "epoch": 0.6501766784452296,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00018821411964793433,
      "loss": 4.8073,
      "step": 207
    },
    {
      "epoch": 0.6533176285826463,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00018809660054681823,
      "loss": 4.7729,
      "step": 208
    },
    {
      "epoch": 0.6564585787200629,
      "grad_norm": 1.046875,
      "learning_rate": 0.0001879785355119295,
      "loss": 5.0412,
      "step": 209
    },
    {
      "epoch": 0.6595995288574794,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001878599252749159,
      "loss": 4.8707,
      "step": 210
    },
    {
      "epoch": 0.662740478994896,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00018774077057080398,
      "loss": 4.6271,
      "step": 211
    },
    {
      "epoch": 0.6658814291323125,
      "grad_norm": 1.359375,
      "learning_rate": 0.00018762107213799427,
      "loss": 4.8702,
      "step": 212
    },
    {
      "epoch": 0.6690223792697291,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00018750083071825677,
      "loss": 4.8727,
      "step": 213
    },
    {
      "epoch": 0.6721633294071456,
      "grad_norm": 1.71875,
      "learning_rate": 0.0001873800470567264,
      "loss": 4.8376,
      "step": 214
    },
    {
      "epoch": 0.6753042795445622,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00018725872190189827,
      "loss": 4.8666,
      "step": 215
    },
    {
      "epoch": 0.6784452296819788,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018713685600562328,
      "loss": 5.038,
      "step": 216
    },
    {
      "epoch": 0.6815861798193954,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00018701445012310315,
      "loss": 4.9007,
      "step": 217
    },
    {
      "epoch": 0.684727129956812,
      "grad_norm": 1.1875,
      "learning_rate": 0.00018689150501288593,
      "loss": 4.8299,
      "step": 218
    },
    {
      "epoch": 0.6878680800942285,
      "grad_norm": 1.3125,
      "learning_rate": 0.00018676802143686126,
      "loss": 4.801,
      "step": 219
    },
    {
      "epoch": 0.6910090302316451,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00018664400016025568,
      "loss": 4.7097,
      "step": 220
    },
    {
      "epoch": 0.6941499803690616,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018651944195162778,
      "loss": 4.8088,
      "step": 221
    },
    {
      "epoch": 0.6972909305064782,
      "grad_norm": 1.25,
      "learning_rate": 0.0001863943475828636,
      "loss": 4.9253,
      "step": 222
    },
    {
      "epoch": 0.7004318806438948,
      "grad_norm": 1.40625,
      "learning_rate": 0.00018626871782917174,
      "loss": 4.8615,
      "step": 223
    },
    {
      "epoch": 0.7035728307813114,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00018614255346907855,
      "loss": 4.7592,
      "step": 224
    },
    {
      "epoch": 0.7067137809187279,
      "grad_norm": 1.5,
      "learning_rate": 0.0001860158552844233,
      "loss": 4.6569,
      "step": 225
    },
    {
      "epoch": 0.7098547310561445,
      "grad_norm": 1.59375,
      "learning_rate": 0.0001858886240603534,
      "loss": 4.8259,
      "step": 226
    },
    {
      "epoch": 0.712995681193561,
      "grad_norm": 1.53125,
      "learning_rate": 0.00018576086058531957,
      "loss": 4.8066,
      "step": 227
    },
    {
      "epoch": 0.7161366313309776,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00018563256565107072,
      "loss": 4.8039,
      "step": 228
    },
    {
      "epoch": 0.7192775814683942,
      "grad_norm": 1.390625,
      "learning_rate": 0.00018550374005264937,
      "loss": 4.8336,
      "step": 229
    },
    {
      "epoch": 0.7224185316058107,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001853743845883865,
      "loss": 4.7032,
      "step": 230
    },
    {
      "epoch": 0.7255594817432274,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0001852445000598966,
      "loss": 4.827,
      "step": 231
    },
    {
      "epoch": 0.7287004318806439,
      "grad_norm": 1.2578125,
      "learning_rate": 0.0001851140872720729,
      "loss": 4.996,
      "step": 232
    },
    {
      "epoch": 0.7318413820180605,
      "grad_norm": 1.7109375,
      "learning_rate": 0.0001849831470330821,
      "loss": 4.7288,
      "step": 233
    },
    {
      "epoch": 0.734982332155477,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018485168015435966,
      "loss": 4.8204,
      "step": 234
    },
    {
      "epoch": 0.7381232822928936,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00018471968745060444,
      "loss": 4.8829,
      "step": 235
    },
    {
      "epoch": 0.7412642324303101,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00018458716973977405,
      "loss": 4.7297,
      "step": 236
    },
    {
      "epoch": 0.7444051825677267,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00018445412784307932,
      "loss": 4.7916,
      "step": 237
    },
    {
      "epoch": 0.7475461327051433,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001843205625849797,
      "loss": 4.5585,
      "step": 238
    },
    {
      "epoch": 0.7506870828425599,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00018418647479317776,
      "loss": 4.9319,
      "step": 239
    },
    {
      "epoch": 0.7538280329799765,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00018405186529861416,
      "loss": 4.9877,
      "step": 240
    },
    {
      "epoch": 0.7538280329799765,
      "eval_loss": 4.841662406921387,
      "eval_runtime": 66.8839,
      "eval_samples_per_second": 38.888,
      "eval_steps_per_second": 38.888,
      "step": 240
    },
    {
      "epoch": 0.756968983117393,
      "grad_norm": 1.375,
      "learning_rate": 0.00018391673493546273,
      "loss": 4.7421,
      "step": 241
    },
    {
      "epoch": 0.7601099332548096,
      "grad_norm": 1.265625,
      "learning_rate": 0.00018378108454112494,
      "loss": 4.6469,
      "step": 242
    },
    {
      "epoch": 0.7632508833922261,
      "grad_norm": 2.109375,
      "learning_rate": 0.00018364491495622497,
      "loss": 4.7609,
      "step": 243
    },
    {
      "epoch": 0.7663918335296427,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00018350822702460444,
      "loss": 4.737,
      "step": 244
    },
    {
      "epoch": 0.7695327836670592,
      "grad_norm": 1.7734375,
      "learning_rate": 0.0001833710215933171,
      "loss": 4.7964,
      "step": 245
    },
    {
      "epoch": 0.7726737338044759,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00018323329951262367,
      "loss": 4.8785,
      "step": 246
    },
    {
      "epoch": 0.7758146839418925,
      "grad_norm": 1.7421875,
      "learning_rate": 0.0001830950616359865,
      "loss": 4.83,
      "step": 247
    },
    {
      "epoch": 0.778955634079309,
      "grad_norm": 1.53125,
      "learning_rate": 0.00018295630882006445,
      "loss": 4.9096,
      "step": 248
    },
    {
      "epoch": 0.7820965842167256,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00018281704192470727,
      "loss": 4.7864,
      "step": 249
    },
    {
      "epoch": 0.7852375343541421,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00018267726181295065,
      "loss": 4.8557,
      "step": 250
    },
    {
      "epoch": 0.7883784844915587,
      "grad_norm": 2.578125,
      "learning_rate": 0.00018253696935101047,
      "loss": 4.8157,
      "step": 251
    },
    {
      "epoch": 0.7915194346289752,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018239616540827782,
      "loss": 4.8016,
      "step": 252
    },
    {
      "epoch": 0.7946603847663918,
      "grad_norm": 1.390625,
      "learning_rate": 0.0001822548508573133,
      "loss": 4.657,
      "step": 253
    },
    {
      "epoch": 0.7978013349038084,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018211302657384186,
      "loss": 4.7423,
      "step": 254
    },
    {
      "epoch": 0.800942285041225,
      "grad_norm": 2.328125,
      "learning_rate": 0.00018197069343674715,
      "loss": 4.8695,
      "step": 255
    },
    {
      "epoch": 0.8040832351786416,
      "grad_norm": 1.7421875,
      "learning_rate": 0.00018182785232806627,
      "loss": 4.9817,
      "step": 256
    },
    {
      "epoch": 0.8072241853160581,
      "grad_norm": 2.125,
      "learning_rate": 0.00018168450413298416,
      "loss": 4.794,
      "step": 257
    },
    {
      "epoch": 0.8103651354534747,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00018154064973982816,
      "loss": 4.9111,
      "step": 258
    },
    {
      "epoch": 0.8135060855908912,
      "grad_norm": 2.0625,
      "learning_rate": 0.0001813962900400626,
      "loss": 4.9169,
      "step": 259
    },
    {
      "epoch": 0.8166470357283078,
      "grad_norm": 1.765625,
      "learning_rate": 0.00018125142592828307,
      "loss": 4.7243,
      "step": 260
    },
    {
      "epoch": 0.8197879858657244,
      "grad_norm": 2.234375,
      "learning_rate": 0.00018110605830221104,
      "loss": 4.8339,
      "step": 261
    },
    {
      "epoch": 0.822928936003141,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00018096018806268834,
      "loss": 4.6423,
      "step": 262
    },
    {
      "epoch": 0.8260698861405575,
      "grad_norm": 1.9453125,
      "learning_rate": 0.00018081381611367134,
      "loss": 4.6603,
      "step": 263
    },
    {
      "epoch": 0.8292108362779741,
      "grad_norm": 2.359375,
      "learning_rate": 0.00018066694336222564,
      "loss": 4.8327,
      "step": 264
    },
    {
      "epoch": 0.8323517864153906,
      "grad_norm": 2.765625,
      "learning_rate": 0.0001805195707185202,
      "loss": 4.7741,
      "step": 265
    },
    {
      "epoch": 0.8354927365528072,
      "grad_norm": 2.453125,
      "learning_rate": 0.00018037169909582192,
      "loss": 4.8735,
      "step": 266
    },
    {
      "epoch": 0.8386336866902238,
      "grad_norm": 1.9375,
      "learning_rate": 0.00018022332941048972,
      "loss": 4.5862,
      "step": 267
    },
    {
      "epoch": 0.8417746368276403,
      "grad_norm": 2.453125,
      "learning_rate": 0.00018007446258196916,
      "loss": 4.6305,
      "step": 268
    },
    {
      "epoch": 0.844915586965057,
      "grad_norm": 1.8046875,
      "learning_rate": 0.00017992509953278644,
      "loss": 4.7259,
      "step": 269
    },
    {
      "epoch": 0.8480565371024735,
      "grad_norm": 1.9765625,
      "learning_rate": 0.000179775241188543,
      "loss": 4.7171,
      "step": 270
    },
    {
      "epoch": 0.8511974872398901,
      "grad_norm": 1.8984375,
      "learning_rate": 0.0001796248884779095,
      "loss": 4.5035,
      "step": 271
    },
    {
      "epoch": 0.8543384373773066,
      "grad_norm": 1.7265625,
      "learning_rate": 0.0001794740423326202,
      "loss": 4.5654,
      "step": 272
    },
    {
      "epoch": 0.8574793875147232,
      "grad_norm": 2.234375,
      "learning_rate": 0.00017932270368746723,
      "loss": 4.7109,
      "step": 273
    },
    {
      "epoch": 0.8606203376521397,
      "grad_norm": 2.09375,
      "learning_rate": 0.00017917087348029464,
      "loss": 4.6446,
      "step": 274
    },
    {
      "epoch": 0.8637612877895563,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001790185526519928,
      "loss": 4.6444,
      "step": 275
    },
    {
      "epoch": 0.866902237926973,
      "grad_norm": 1.8984375,
      "learning_rate": 0.00017886574214649235,
      "loss": 4.6852,
      "step": 276
    },
    {
      "epoch": 0.8700431880643895,
      "grad_norm": 2.09375,
      "learning_rate": 0.0001787124429107585,
      "loss": 4.6116,
      "step": 277
    },
    {
      "epoch": 0.8731841382018061,
      "grad_norm": 1.875,
      "learning_rate": 0.00017855865589478515,
      "loss": 4.7119,
      "step": 278
    },
    {
      "epoch": 0.8763250883392226,
      "grad_norm": 2.0625,
      "learning_rate": 0.00017840438205158891,
      "loss": 4.7154,
      "step": 279
    },
    {
      "epoch": 0.8794660384766392,
      "grad_norm": 2.171875,
      "learning_rate": 0.00017824962233720332,
      "loss": 4.7945,
      "step": 280
    },
    {
      "epoch": 0.8826069886140557,
      "grad_norm": 2.828125,
      "learning_rate": 0.00017809437771067272,
      "loss": 4.7312,
      "step": 281
    },
    {
      "epoch": 0.8857479387514723,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017793864913404663,
      "loss": 4.5674,
      "step": 282
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.203125,
      "learning_rate": 0.00017778243757237352,
      "loss": 4.6855,
      "step": 283
    },
    {
      "epoch": 0.8920298390263055,
      "grad_norm": 2.40625,
      "learning_rate": 0.00017762574399369485,
      "loss": 4.7105,
      "step": 284
    },
    {
      "epoch": 0.8951707891637221,
      "grad_norm": 2.171875,
      "learning_rate": 0.00017746856936903926,
      "loss": 4.7111,
      "step": 285
    },
    {
      "epoch": 0.8983117393011386,
      "grad_norm": 1.984375,
      "learning_rate": 0.0001773109146724163,
      "loss": 4.7511,
      "step": 286
    },
    {
      "epoch": 0.9014526894385552,
      "grad_norm": 2.34375,
      "learning_rate": 0.00017715278088081062,
      "loss": 4.7156,
      "step": 287
    },
    {
      "epoch": 0.9045936395759717,
      "grad_norm": 2.796875,
      "learning_rate": 0.0001769941689741758,
      "loss": 4.7225,
      "step": 288
    },
    {
      "epoch": 0.9077345897133883,
      "grad_norm": 2.703125,
      "learning_rate": 0.00017683507993542825,
      "loss": 4.7426,
      "step": 289
    },
    {
      "epoch": 0.9108755398508048,
      "grad_norm": 2.4375,
      "learning_rate": 0.0001766755147504412,
      "loss": 4.8524,
      "step": 290
    },
    {
      "epoch": 0.9140164899882215,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017651547440803851,
      "loss": 4.6249,
      "step": 291
    },
    {
      "epoch": 0.917157440125638,
      "grad_norm": 3.125,
      "learning_rate": 0.00017635495989998864,
      "loss": 4.8815,
      "step": 292
    },
    {
      "epoch": 0.9202983902630546,
      "grad_norm": 2.71875,
      "learning_rate": 0.00017619397222099848,
      "loss": 4.7107,
      "step": 293
    },
    {
      "epoch": 0.9234393404004712,
      "grad_norm": 2.53125,
      "learning_rate": 0.00017603251236870702,
      "loss": 4.5988,
      "step": 294
    },
    {
      "epoch": 0.9265802905378877,
      "grad_norm": 2.703125,
      "learning_rate": 0.0001758705813436794,
      "loss": 4.43,
      "step": 295
    },
    {
      "epoch": 0.9297212406753043,
      "grad_norm": 2.84375,
      "learning_rate": 0.00017570818014940064,
      "loss": 4.8238,
      "step": 296
    },
    {
      "epoch": 0.9328621908127208,
      "grad_norm": 2.578125,
      "learning_rate": 0.00017554530979226933,
      "loss": 4.7022,
      "step": 297
    },
    {
      "epoch": 0.9360031409501374,
      "grad_norm": 2.96875,
      "learning_rate": 0.00017538197128159148,
      "loss": 4.8184,
      "step": 298
    },
    {
      "epoch": 0.939144091087554,
      "grad_norm": 2.609375,
      "learning_rate": 0.00017521816562957428,
      "loss": 4.4714,
      "step": 299
    },
    {
      "epoch": 0.9422850412249706,
      "grad_norm": 2.40625,
      "learning_rate": 0.00017505389385131972,
      "loss": 4.4407,
      "step": 300
    },
    {
      "epoch": 0.9454259913623871,
      "grad_norm": 3.25,
      "learning_rate": 0.00017488915696481838,
      "loss": 4.6623,
      "step": 301
    },
    {
      "epoch": 0.9485669414998037,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017472395599094317,
      "loss": 4.6181,
      "step": 302
    },
    {
      "epoch": 0.9517078916372202,
      "grad_norm": 2.890625,
      "learning_rate": 0.00017455829195344293,
      "loss": 4.6449,
      "step": 303
    },
    {
      "epoch": 0.9548488417746368,
      "grad_norm": 6.84375,
      "learning_rate": 0.00017439216587893604,
      "loss": 4.538,
      "step": 304
    },
    {
      "epoch": 0.9579897919120534,
      "grad_norm": 3.5625,
      "learning_rate": 0.0001742255787969042,
      "loss": 4.7436,
      "step": 305
    },
    {
      "epoch": 0.9611307420494699,
      "grad_norm": 2.234375,
      "learning_rate": 0.00017405853173968589,
      "loss": 4.7237,
      "step": 306
    },
    {
      "epoch": 0.9642716921868866,
      "grad_norm": 2.3125,
      "learning_rate": 0.0001738910257424701,
      "loss": 4.5708,
      "step": 307
    },
    {
      "epoch": 0.9674126423243031,
      "grad_norm": 2.78125,
      "learning_rate": 0.00017372306184328985,
      "loss": 4.4765,
      "step": 308
    },
    {
      "epoch": 0.9705535924617197,
      "grad_norm": 2.109375,
      "learning_rate": 0.00017355464108301585,
      "loss": 4.6697,
      "step": 309
    },
    {
      "epoch": 0.9736945425991362,
      "grad_norm": 2.421875,
      "learning_rate": 0.00017338576450534984,
      "loss": 4.5376,
      "step": 310
    },
    {
      "epoch": 0.9768354927365528,
      "grad_norm": 2.671875,
      "learning_rate": 0.00017321643315681832,
      "loss": 4.7185,
      "step": 311
    },
    {
      "epoch": 0.9799764428739693,
      "grad_norm": 2.421875,
      "learning_rate": 0.000173046648086766,
      "loss": 4.6617,
      "step": 312
    },
    {
      "epoch": 0.9831173930113859,
      "grad_norm": 3.1875,
      "learning_rate": 0.00017287641034734934,
      "loss": 4.7403,
      "step": 313
    },
    {
      "epoch": 0.9862583431488026,
      "grad_norm": 2.21875,
      "learning_rate": 0.00017270572099352993,
      "loss": 4.5652,
      "step": 314
    },
    {
      "epoch": 0.9893992932862191,
      "grad_norm": 2.765625,
      "learning_rate": 0.000172534581083068,
      "loss": 4.5723,
      "step": 315
    },
    {
      "epoch": 0.9925402434236357,
      "grad_norm": 2.9375,
      "learning_rate": 0.00017236299167651593,
      "loss": 4.6485,
      "step": 316
    },
    {
      "epoch": 0.9956811935610522,
      "grad_norm": 3.109375,
      "learning_rate": 0.0001721909538372116,
      "loss": 4.5751,
      "step": 317
    },
    {
      "epoch": 0.9988221436984688,
      "grad_norm": 3.046875,
      "learning_rate": 0.0001720184686312718,
      "loss": 4.5623,
      "step": 318
    },
    {
      "epoch": 1.0019630938358854,
      "grad_norm": 2.578125,
      "learning_rate": 0.0001718455371275857,
      "loss": 4.5953,
      "step": 319
    },
    {
      "epoch": 1.0051040439733019,
      "grad_norm": 2.765625,
      "learning_rate": 0.00017167216039780812,
      "loss": 4.7408,
      "step": 320
    },
    {
      "epoch": 1.0051040439733019,
      "eval_loss": 4.618032932281494,
      "eval_runtime": 67.0802,
      "eval_samples_per_second": 38.774,
      "eval_steps_per_second": 38.774,
      "step": 320
    },
    {
      "epoch": 1.0082449941107186,
      "grad_norm": 2.6875,
      "learning_rate": 0.00017149833951635293,
      "loss": 4.804,
      "step": 321
    },
    {
      "epoch": 1.011385944248135,
      "grad_norm": 2.984375,
      "learning_rate": 0.00017132407556038644,
      "loss": 4.5474,
      "step": 322
    },
    {
      "epoch": 1.0023557126030624,
      "grad_norm": 3.15625,
      "learning_rate": 0.00017114936960982072,
      "loss": 4.5475,
      "step": 323
    },
    {
      "epoch": 1.0054966627404789,
      "grad_norm": 2.625,
      "learning_rate": 0.0001709742227473068,
      "loss": 4.8615,
      "step": 324
    },
    {
      "epoch": 1.0086376128778956,
      "grad_norm": 2.890625,
      "learning_rate": 0.00017079863605822811,
      "loss": 4.5709,
      "step": 325
    },
    {
      "epoch": 1.0117785630153122,
      "grad_norm": 2.90625,
      "learning_rate": 0.00017062261063069365,
      "loss": 4.7747,
      "step": 326
    },
    {
      "epoch": 1.0149195131527287,
      "grad_norm": 2.453125,
      "learning_rate": 0.00017044614755553123,
      "loss": 4.5197,
      "step": 327
    },
    {
      "epoch": 1.0180604632901453,
      "grad_norm": 2.96875,
      "learning_rate": 0.00017026924792628082,
      "loss": 4.5271,
      "step": 328
    },
    {
      "epoch": 1.0212014134275618,
      "grad_norm": 3.015625,
      "learning_rate": 0.00017009191283918774,
      "loss": 4.4289,
      "step": 329
    },
    {
      "epoch": 1.0243423635649784,
      "grad_norm": 2.484375,
      "learning_rate": 0.00016991414339319571,
      "loss": 4.446,
      "step": 330
    },
    {
      "epoch": 1.0274833137023949,
      "grad_norm": 3.328125,
      "learning_rate": 0.0001697359406899403,
      "loss": 4.5457,
      "step": 331
    },
    {
      "epoch": 1.0306242638398115,
      "grad_norm": 3.3125,
      "learning_rate": 0.0001695573058337419,
      "loss": 4.5233,
      "step": 332
    },
    {
      "epoch": 1.0337652139772282,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00016937823993159903,
      "loss": 4.3562,
      "step": 333
    },
    {
      "epoch": 1.0369061641146446,
      "grad_norm": 2.109375,
      "learning_rate": 0.00016919874409318126,
      "loss": 4.5259,
      "step": 334
    },
    {
      "epoch": 1.0400471142520613,
      "grad_norm": 2.8125,
      "learning_rate": 0.00016901881943082254,
      "loss": 4.6123,
      "step": 335
    },
    {
      "epoch": 1.0431880643894778,
      "grad_norm": 2.34375,
      "learning_rate": 0.0001688384670595143,
      "loss": 4.4088,
      "step": 336
    },
    {
      "epoch": 1.0463290145268944,
      "grad_norm": 2.9375,
      "learning_rate": 0.00016865768809689842,
      "loss": 4.5822,
      "step": 337
    },
    {
      "epoch": 1.0494699646643109,
      "grad_norm": 2.171875,
      "learning_rate": 0.00016847648366326033,
      "loss": 4.5317,
      "step": 338
    },
    {
      "epoch": 1.0526109148017275,
      "grad_norm": 3.078125,
      "learning_rate": 0.00016829485488152214,
      "loss": 4.5681,
      "step": 339
    },
    {
      "epoch": 1.0557518649391442,
      "grad_norm": 2.484375,
      "learning_rate": 0.00016811280287723563,
      "loss": 4.5301,
      "step": 340
    },
    {
      "epoch": 1.0588928150765606,
      "grad_norm": 1.96875,
      "learning_rate": 0.00016793032877857536,
      "loss": 4.5032,
      "step": 341
    },
    {
      "epoch": 1.0620337652139773,
      "grad_norm": 2.328125,
      "learning_rate": 0.00016774743371633145,
      "loss": 4.4028,
      "step": 342
    },
    {
      "epoch": 1.0651747153513937,
      "grad_norm": 3.671875,
      "learning_rate": 0.00016756411882390282,
      "loss": 4.4828,
      "step": 343
    },
    {
      "epoch": 1.0683156654888104,
      "grad_norm": 3.109375,
      "learning_rate": 0.0001673803852372901,
      "loss": 4.3682,
      "step": 344
    },
    {
      "epoch": 1.0714566156262268,
      "grad_norm": 2.53125,
      "learning_rate": 0.00016719623409508855,
      "loss": 4.317,
      "step": 345
    },
    {
      "epoch": 1.0745975657636435,
      "grad_norm": 2.6875,
      "learning_rate": 0.00016701166653848096,
      "loss": 4.5604,
      "step": 346
    },
    {
      "epoch": 1.0777385159010602,
      "grad_norm": 2.546875,
      "learning_rate": 0.0001668266837112307,
      "loss": 4.401,
      "step": 347
    },
    {
      "epoch": 1.0808794660384766,
      "grad_norm": 2.265625,
      "learning_rate": 0.0001666412867596745,
      "loss": 4.4679,
      "step": 348
    },
    {
      "epoch": 1.0840204161758933,
      "grad_norm": 2.71875,
      "learning_rate": 0.00016645547683271552,
      "loss": 4.5537,
      "step": 349
    },
    {
      "epoch": 1.0871613663133097,
      "grad_norm": 2.453125,
      "learning_rate": 0.000166269255081816,
      "loss": 4.3402,
      "step": 350
    },
    {
      "epoch": 1.0903023164507264,
      "grad_norm": 2.515625,
      "learning_rate": 0.00016608262266099035,
      "loss": 4.3527,
      "step": 351
    },
    {
      "epoch": 1.0934432665881428,
      "grad_norm": 2.28125,
      "learning_rate": 0.00016589558072679786,
      "loss": 4.6239,
      "step": 352
    },
    {
      "epoch": 1.0965842167255595,
      "grad_norm": 2.484375,
      "learning_rate": 0.00016570813043833554,
      "loss": 4.5686,
      "step": 353
    },
    {
      "epoch": 1.0997251668629762,
      "grad_norm": 2.96875,
      "learning_rate": 0.000165520272957231,
      "loss": 4.6111,
      "step": 354
    },
    {
      "epoch": 1.1028661170003926,
      "grad_norm": 3.0625,
      "learning_rate": 0.00016533200944763524,
      "loss": 4.5757,
      "step": 355
    },
    {
      "epoch": 1.1060070671378093,
      "grad_norm": 2.203125,
      "learning_rate": 0.00016514334107621537,
      "loss": 4.5229,
      "step": 356
    },
    {
      "epoch": 1.1091480172752257,
      "grad_norm": 2.890625,
      "learning_rate": 0.00016495426901214744,
      "loss": 4.5219,
      "step": 357
    },
    {
      "epoch": 1.1122889674126424,
      "grad_norm": 2.390625,
      "learning_rate": 0.00016476479442710922,
      "loss": 4.527,
      "step": 358
    },
    {
      "epoch": 1.1154299175500588,
      "grad_norm": 2.25,
      "learning_rate": 0.0001645749184952728,
      "loss": 4.6095,
      "step": 359
    },
    {
      "epoch": 1.1185708676874755,
      "grad_norm": 2.609375,
      "learning_rate": 0.00016438464239329755,
      "loss": 4.3415,
      "step": 360
    },
    {
      "epoch": 1.121711817824892,
      "grad_norm": 2.921875,
      "learning_rate": 0.00016419396730032253,
      "loss": 4.6057,
      "step": 361
    },
    {
      "epoch": 1.1248527679623086,
      "grad_norm": 2.765625,
      "learning_rate": 0.00016400289439795948,
      "loss": 4.4129,
      "step": 362
    },
    {
      "epoch": 1.1279937180997253,
      "grad_norm": 3.296875,
      "learning_rate": 0.0001638114248702853,
      "loss": 4.4874,
      "step": 363
    },
    {
      "epoch": 1.1311346682371417,
      "grad_norm": 2.90625,
      "learning_rate": 0.00016361955990383477,
      "loss": 4.3538,
      "step": 364
    },
    {
      "epoch": 1.1342756183745584,
      "grad_norm": 2.921875,
      "learning_rate": 0.00016342730068759327,
      "loss": 4.472,
      "step": 365
    },
    {
      "epoch": 1.1374165685119748,
      "grad_norm": 2.5625,
      "learning_rate": 0.00016323464841298918,
      "loss": 4.1759,
      "step": 366
    },
    {
      "epoch": 1.1405575186493915,
      "grad_norm": 2.609375,
      "learning_rate": 0.00016304160427388684,
      "loss": 4.5234,
      "step": 367
    },
    {
      "epoch": 1.143698468786808,
      "grad_norm": 2.65625,
      "learning_rate": 0.0001628481694665789,
      "loss": 4.3641,
      "step": 368
    },
    {
      "epoch": 1.1468394189242246,
      "grad_norm": 2.28125,
      "learning_rate": 0.00016265434518977892,
      "loss": 4.5628,
      "step": 369
    },
    {
      "epoch": 1.149980369061641,
      "grad_norm": 2.4375,
      "learning_rate": 0.00016246013264461406,
      "loss": 4.4381,
      "step": 370
    },
    {
      "epoch": 1.1531213191990577,
      "grad_norm": 2.671875,
      "learning_rate": 0.00016226553303461762,
      "loss": 4.5478,
      "step": 371
    },
    {
      "epoch": 1.1562622693364744,
      "grad_norm": 2.875,
      "learning_rate": 0.00016207054756572141,
      "loss": 4.4431,
      "step": 372
    },
    {
      "epoch": 1.1594032194738908,
      "grad_norm": 2.5,
      "learning_rate": 0.0001618751774462485,
      "loss": 4.5903,
      "step": 373
    },
    {
      "epoch": 1.1625441696113075,
      "grad_norm": 2.578125,
      "learning_rate": 0.00016167942388690563,
      "loss": 4.5634,
      "step": 374
    },
    {
      "epoch": 1.165685119748724,
      "grad_norm": 2.5625,
      "learning_rate": 0.00016148328810077568,
      "loss": 4.4181,
      "step": 375
    },
    {
      "epoch": 1.1688260698861406,
      "grad_norm": 2.53125,
      "learning_rate": 0.0001612867713033102,
      "loss": 4.3018,
      "step": 376
    },
    {
      "epoch": 1.171967020023557,
      "grad_norm": 3.40625,
      "learning_rate": 0.00016108987471232184,
      "loss": 4.6465,
      "step": 377
    },
    {
      "epoch": 1.1751079701609737,
      "grad_norm": 2.484375,
      "learning_rate": 0.0001608925995479769,
      "loss": 4.3892,
      "step": 378
    },
    {
      "epoch": 1.1782489202983903,
      "grad_norm": 2.828125,
      "learning_rate": 0.0001606949470327876,
      "loss": 4.5286,
      "step": 379
    },
    {
      "epoch": 1.1813898704358068,
      "grad_norm": 3.28125,
      "learning_rate": 0.0001604969183916047,
      "loss": 4.4929,
      "step": 380
    },
    {
      "epoch": 1.1845308205732235,
      "grad_norm": 2.203125,
      "learning_rate": 0.00016029851485160966,
      "loss": 4.4002,
      "step": 381
    },
    {
      "epoch": 1.18767177071064,
      "grad_norm": 2.984375,
      "learning_rate": 0.00016009973764230742,
      "loss": 4.4586,
      "step": 382
    },
    {
      "epoch": 1.1908127208480566,
      "grad_norm": 3.421875,
      "learning_rate": 0.00015990058799551825,
      "loss": 4.6185,
      "step": 383
    },
    {
      "epoch": 1.193953670985473,
      "grad_norm": 2.453125,
      "learning_rate": 0.00015970106714537067,
      "loss": 4.4776,
      "step": 384
    },
    {
      "epoch": 1.1970946211228897,
      "grad_norm": 2.765625,
      "learning_rate": 0.00015950117632829337,
      "loss": 4.5512,
      "step": 385
    },
    {
      "epoch": 1.2002355712603063,
      "grad_norm": 2.5625,
      "learning_rate": 0.00015930091678300788,
      "loss": 4.5065,
      "step": 386
    },
    {
      "epoch": 1.2033765213977228,
      "grad_norm": 2.78125,
      "learning_rate": 0.00015910028975052052,
      "loss": 4.6741,
      "step": 387
    },
    {
      "epoch": 1.2065174715351394,
      "grad_norm": 2.609375,
      "learning_rate": 0.0001588992964741152,
      "loss": 4.5716,
      "step": 388
    },
    {
      "epoch": 1.2096584216725559,
      "grad_norm": 3.171875,
      "learning_rate": 0.00015869793819934516,
      "loss": 4.5801,
      "step": 389
    },
    {
      "epoch": 1.2127993718099725,
      "grad_norm": 2.609375,
      "learning_rate": 0.00015849621617402572,
      "loss": 4.4056,
      "step": 390
    },
    {
      "epoch": 1.215940321947389,
      "grad_norm": 2.5,
      "learning_rate": 0.00015829413164822627,
      "loss": 4.4631,
      "step": 391
    },
    {
      "epoch": 1.2190812720848057,
      "grad_norm": 2.359375,
      "learning_rate": 0.00015809168587426267,
      "loss": 4.4807,
      "step": 392
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 10.25,
      "learning_rate": 0.00015788888010668942,
      "loss": 4.4483,
      "step": 393
    },
    {
      "epoch": 1.2253631723596388,
      "grad_norm": 3.0625,
      "learning_rate": 0.00015768571560229185,
      "loss": 4.3158,
      "step": 394
    },
    {
      "epoch": 1.2285041224970554,
      "grad_norm": 5.0625,
      "learning_rate": 0.00015748219362007838,
      "loss": 4.5948,
      "step": 395
    },
    {
      "epoch": 1.2316450726344719,
      "grad_norm": 3.40625,
      "learning_rate": 0.0001572783154212728,
      "loss": 4.503,
      "step": 396
    },
    {
      "epoch": 1.2347860227718885,
      "grad_norm": 2.1875,
      "learning_rate": 0.0001570740822693063,
      "loss": 4.6138,
      "step": 397
    },
    {
      "epoch": 1.237926972909305,
      "grad_norm": 3.328125,
      "learning_rate": 0.00015686949542980972,
      "loss": 4.4918,
      "step": 398
    },
    {
      "epoch": 1.2410679230467216,
      "grad_norm": 2.90625,
      "learning_rate": 0.00015666455617060568,
      "loss": 4.5328,
      "step": 399
    },
    {
      "epoch": 1.2442088731841383,
      "grad_norm": 2.484375,
      "learning_rate": 0.0001564592657617008,
      "loss": 4.5097,
      "step": 400
    },
    {
      "epoch": 1.2442088731841383,
      "eval_loss": 4.506556510925293,
      "eval_runtime": 67.1701,
      "eval_samples_per_second": 38.723,
      "eval_steps_per_second": 38.723,
      "step": 400
    },
    {
      "epoch": 1.2473498233215548,
      "grad_norm": 2.171875,
      "learning_rate": 0.00015625362547527774,
      "loss": 4.2176,
      "step": 401
    },
    {
      "epoch": 1.2504907734589714,
      "grad_norm": 2.265625,
      "learning_rate": 0.00015604763658568733,
      "loss": 4.5224,
      "step": 402
    },
    {
      "epoch": 1.2536317235963879,
      "grad_norm": 1.7890625,
      "learning_rate": 0.0001558413003694407,
      "loss": 4.4113,
      "step": 403
    },
    {
      "epoch": 1.2567726737338045,
      "grad_norm": 2.1875,
      "learning_rate": 0.0001556346181052014,
      "loss": 4.4202,
      "step": 404
    },
    {
      "epoch": 1.259913623871221,
      "grad_norm": 2.875,
      "learning_rate": 0.00015542759107377738,
      "loss": 4.3784,
      "step": 405
    },
    {
      "epoch": 1.2630545740086376,
      "grad_norm": 3.03125,
      "learning_rate": 0.00015522022055811308,
      "loss": 4.5884,
      "step": 406
    },
    {
      "epoch": 1.2661955241460543,
      "grad_norm": 2.75,
      "learning_rate": 0.00015501250784328167,
      "loss": 4.506,
      "step": 407
    },
    {
      "epoch": 1.2693364742834707,
      "grad_norm": 2.828125,
      "learning_rate": 0.00015480445421647674,
      "loss": 4.4045,
      "step": 408
    },
    {
      "epoch": 1.2724774244208872,
      "grad_norm": 3.0625,
      "learning_rate": 0.00015459606096700457,
      "loss": 4.4833,
      "step": 409
    },
    {
      "epoch": 1.2756183745583038,
      "grad_norm": 2.609375,
      "learning_rate": 0.00015438732938627612,
      "loss": 4.1899,
      "step": 410
    },
    {
      "epoch": 1.2787593246957205,
      "grad_norm": 2.96875,
      "learning_rate": 0.00015417826076779894,
      "loss": 4.4343,
      "step": 411
    },
    {
      "epoch": 1.281900274833137,
      "grad_norm": 2.8125,
      "learning_rate": 0.00015396885640716926,
      "loss": 4.3997,
      "step": 412
    },
    {
      "epoch": 1.2850412249705536,
      "grad_norm": 2.671875,
      "learning_rate": 0.0001537591176020638,
      "loss": 4.3977,
      "step": 413
    },
    {
      "epoch": 1.2881821751079703,
      "grad_norm": 1.921875,
      "learning_rate": 0.0001535490456522319,
      "loss": 4.3571,
      "step": 414
    },
    {
      "epoch": 1.2913231252453867,
      "grad_norm": 2.40625,
      "learning_rate": 0.0001533386418594874,
      "loss": 4.37,
      "step": 415
    },
    {
      "epoch": 1.2944640753828032,
      "grad_norm": 2.828125,
      "learning_rate": 0.00015312790752770053,
      "loss": 4.3312,
      "step": 416
    },
    {
      "epoch": 1.2976050255202198,
      "grad_norm": 2.5625,
      "learning_rate": 0.00015291684396278988,
      "loss": 4.5376,
      "step": 417
    },
    {
      "epoch": 1.3007459756576365,
      "grad_norm": 2.25,
      "learning_rate": 0.00015270545247271432,
      "loss": 4.2349,
      "step": 418
    },
    {
      "epoch": 1.303886925795053,
      "grad_norm": 2.78125,
      "learning_rate": 0.00015249373436746483,
      "loss": 4.5092,
      "step": 419
    },
    {
      "epoch": 1.3070278759324696,
      "grad_norm": 3.015625,
      "learning_rate": 0.00015228169095905648,
      "loss": 4.4942,
      "step": 420
    },
    {
      "epoch": 1.3101688260698863,
      "grad_norm": 2.21875,
      "learning_rate": 0.00015206932356152012,
      "loss": 4.3255,
      "step": 421
    },
    {
      "epoch": 1.3133097762073027,
      "grad_norm": 2.375,
      "learning_rate": 0.00015185663349089455,
      "loss": 4.3089,
      "step": 422
    },
    {
      "epoch": 1.3164507263447192,
      "grad_norm": 2.4375,
      "learning_rate": 0.00015164362206521794,
      "loss": 4.2816,
      "step": 423
    },
    {
      "epoch": 1.3195916764821358,
      "grad_norm": 3.359375,
      "learning_rate": 0.00015143029060452008,
      "loss": 4.4565,
      "step": 424
    },
    {
      "epoch": 1.3227326266195525,
      "grad_norm": 2.828125,
      "learning_rate": 0.00015121664043081393,
      "loss": 4.1987,
      "step": 425
    },
    {
      "epoch": 1.325873576756969,
      "grad_norm": 3.1875,
      "learning_rate": 0.00015100267286808754,
      "loss": 4.5203,
      "step": 426
    },
    {
      "epoch": 1.3290145268943856,
      "grad_norm": 4.09375,
      "learning_rate": 0.0001507883892422958,
      "loss": 4.3488,
      "step": 427
    },
    {
      "epoch": 1.332155477031802,
      "grad_norm": 2.625,
      "learning_rate": 0.00015057379088135223,
      "loss": 4.3254,
      "step": 428
    },
    {
      "epoch": 1.3352964271692187,
      "grad_norm": 2.765625,
      "learning_rate": 0.0001503588791151208,
      "loss": 4.3639,
      "step": 429
    },
    {
      "epoch": 1.3384373773066351,
      "grad_norm": 3.28125,
      "learning_rate": 0.00015014365527540763,
      "loss": 4.5418,
      "step": 430
    },
    {
      "epoch": 1.3415783274440518,
      "grad_norm": 3.53125,
      "learning_rate": 0.0001499281206959527,
      "loss": 4.4342,
      "step": 431
    },
    {
      "epoch": 1.3447192775814685,
      "grad_norm": 2.25,
      "learning_rate": 0.00014971227671242175,
      "loss": 4.4551,
      "step": 432
    },
    {
      "epoch": 1.347860227718885,
      "grad_norm": 2.59375,
      "learning_rate": 0.0001494961246623978,
      "loss": 4.4315,
      "step": 433
    },
    {
      "epoch": 1.3510011778563016,
      "grad_norm": 2.203125,
      "learning_rate": 0.000149279665885373,
      "loss": 4.376,
      "step": 434
    },
    {
      "epoch": 1.354142127993718,
      "grad_norm": 2.390625,
      "learning_rate": 0.00014906290172274033,
      "loss": 4.3836,
      "step": 435
    },
    {
      "epoch": 1.3572830781311347,
      "grad_norm": 2.421875,
      "learning_rate": 0.00014884583351778508,
      "loss": 4.5068,
      "step": 436
    },
    {
      "epoch": 1.3604240282685511,
      "grad_norm": 2.484375,
      "learning_rate": 0.0001486284626156769,
      "loss": 4.3077,
      "step": 437
    },
    {
      "epoch": 1.3635649784059678,
      "grad_norm": 2.15625,
      "learning_rate": 0.00014841079036346106,
      "loss": 4.3722,
      "step": 438
    },
    {
      "epoch": 1.3667059285433845,
      "grad_norm": 2.515625,
      "learning_rate": 0.00014819281811005047,
      "loss": 4.362,
      "step": 439
    },
    {
      "epoch": 1.369846878680801,
      "grad_norm": 2.53125,
      "learning_rate": 0.00014797454720621696,
      "loss": 4.3888,
      "step": 440
    },
    {
      "epoch": 1.3729878288182176,
      "grad_norm": 16.625,
      "learning_rate": 0.00014775597900458325,
      "loss": 4.1893,
      "step": 441
    },
    {
      "epoch": 1.376128778955634,
      "grad_norm": 2.796875,
      "learning_rate": 0.00014753711485961435,
      "loss": 4.4122,
      "step": 442
    },
    {
      "epoch": 1.3792697290930507,
      "grad_norm": 2.78125,
      "learning_rate": 0.00014731795612760916,
      "loss": 4.4664,
      "step": 443
    },
    {
      "epoch": 1.3824106792304671,
      "grad_norm": 2.515625,
      "learning_rate": 0.00014709850416669227,
      "loss": 4.384,
      "step": 444
    },
    {
      "epoch": 1.3855516293678838,
      "grad_norm": 2.171875,
      "learning_rate": 0.00014687876033680537,
      "loss": 4.3617,
      "step": 445
    },
    {
      "epoch": 1.3886925795053005,
      "grad_norm": 2.78125,
      "learning_rate": 0.00014665872599969873,
      "loss": 4.4573,
      "step": 446
    },
    {
      "epoch": 1.391833529642717,
      "grad_norm": 2.15625,
      "learning_rate": 0.00014643840251892301,
      "loss": 4.5221,
      "step": 447
    },
    {
      "epoch": 1.3949744797801336,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00014621779125982074,
      "loss": 4.2984,
      "step": 448
    },
    {
      "epoch": 1.39811542991755,
      "grad_norm": 2.484375,
      "learning_rate": 0.00014599689358951764,
      "loss": 4.4984,
      "step": 449
    },
    {
      "epoch": 1.4012563800549667,
      "grad_norm": 2.125,
      "learning_rate": 0.0001457757108769145,
      "loss": 4.3669,
      "step": 450
    },
    {
      "epoch": 1.404397330192383,
      "grad_norm": 2.453125,
      "learning_rate": 0.00014555424449267835,
      "loss": 4.3865,
      "step": 451
    },
    {
      "epoch": 1.4075382803297998,
      "grad_norm": 2.546875,
      "learning_rate": 0.00014533249580923427,
      "loss": 4.5054,
      "step": 452
    },
    {
      "epoch": 1.4106792304672164,
      "grad_norm": 2.390625,
      "learning_rate": 0.00014511046620075665,
      "loss": 4.3876,
      "step": 453
    },
    {
      "epoch": 1.4138201806046329,
      "grad_norm": 2.484375,
      "learning_rate": 0.00014488815704316084,
      "loss": 4.508,
      "step": 454
    },
    {
      "epoch": 1.4169611307420495,
      "grad_norm": 2.140625,
      "learning_rate": 0.00014466556971409443,
      "loss": 4.3182,
      "step": 455
    },
    {
      "epoch": 1.420102080879466,
      "grad_norm": 2.421875,
      "learning_rate": 0.00014444270559292905,
      "loss": 4.4394,
      "step": 456
    },
    {
      "epoch": 1.4232430310168827,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001442195660607514,
      "loss": 4.5104,
      "step": 457
    },
    {
      "epoch": 1.426383981154299,
      "grad_norm": 2.59375,
      "learning_rate": 0.00014399615250035498,
      "loss": 4.2292,
      "step": 458
    },
    {
      "epoch": 1.4295249312917158,
      "grad_norm": 2.140625,
      "learning_rate": 0.00014377246629623146,
      "loss": 4.4134,
      "step": 459
    },
    {
      "epoch": 1.4326658814291324,
      "grad_norm": 1.9453125,
      "learning_rate": 0.00014354850883456207,
      "loss": 4.3794,
      "step": 460
    },
    {
      "epoch": 1.4358068315665489,
      "grad_norm": 2.515625,
      "learning_rate": 0.000143324281503209,
      "loss": 4.5643,
      "step": 461
    },
    {
      "epoch": 1.4389477817039653,
      "grad_norm": 2.09375,
      "learning_rate": 0.00014309978569170684,
      "loss": 4.3962,
      "step": 462
    },
    {
      "epoch": 1.442088731841382,
      "grad_norm": 2.5625,
      "learning_rate": 0.0001428750227912539,
      "loss": 4.3906,
      "step": 463
    },
    {
      "epoch": 1.4452296819787986,
      "grad_norm": 2.34375,
      "learning_rate": 0.00014264999419470373,
      "loss": 4.5861,
      "step": 464
    },
    {
      "epoch": 1.448370632116215,
      "grad_norm": 2.390625,
      "learning_rate": 0.0001424247012965563,
      "loss": 4.2325,
      "step": 465
    },
    {
      "epoch": 1.4515115822536317,
      "grad_norm": 2.546875,
      "learning_rate": 0.00014219914549294955,
      "loss": 4.2783,
      "step": 466
    },
    {
      "epoch": 1.4546525323910484,
      "grad_norm": 2.03125,
      "learning_rate": 0.00014197332818165057,
      "loss": 4.4554,
      "step": 467
    },
    {
      "epoch": 1.4577934825284649,
      "grad_norm": 2.6875,
      "learning_rate": 0.000141747250762047,
      "loss": 4.3999,
      "step": 468
    },
    {
      "epoch": 1.4609344326658813,
      "grad_norm": 2.265625,
      "learning_rate": 0.00014152091463513845,
      "loss": 4.3762,
      "step": 469
    },
    {
      "epoch": 1.464075382803298,
      "grad_norm": 2.265625,
      "learning_rate": 0.0001412943212035276,
      "loss": 4.4881,
      "step": 470
    },
    {
      "epoch": 1.4672163329407146,
      "grad_norm": 2.0625,
      "learning_rate": 0.00014106747187141183,
      "loss": 4.3938,
      "step": 471
    },
    {
      "epoch": 1.470357283078131,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001408403680445742,
      "loss": 4.2371,
      "step": 472
    },
    {
      "epoch": 1.4734982332155477,
      "grad_norm": 2.765625,
      "learning_rate": 0.00014061301113037485,
      "loss": 4.3863,
      "step": 473
    },
    {
      "epoch": 1.4766391833529644,
      "grad_norm": 2.0,
      "learning_rate": 0.00014038540253774246,
      "loss": 4.454,
      "step": 474
    },
    {
      "epoch": 1.4797801334903808,
      "grad_norm": 2.140625,
      "learning_rate": 0.00014015754367716518,
      "loss": 4.2719,
      "step": 475
    },
    {
      "epoch": 1.4829210836277973,
      "grad_norm": 2.96875,
      "learning_rate": 0.00013992943596068217,
      "loss": 4.5139,
      "step": 476
    },
    {
      "epoch": 1.486062033765214,
      "grad_norm": 2.53125,
      "learning_rate": 0.00013970108080187474,
      "loss": 4.2512,
      "step": 477
    },
    {
      "epoch": 1.4892029839026306,
      "grad_norm": 2.15625,
      "learning_rate": 0.0001394724796158575,
      "loss": 4.3844,
      "step": 478
    },
    {
      "epoch": 1.492343934040047,
      "grad_norm": 2.609375,
      "learning_rate": 0.00013924363381926985,
      "loss": 4.4204,
      "step": 479
    },
    {
      "epoch": 1.4954848841774637,
      "grad_norm": 2.5625,
      "learning_rate": 0.0001390145448302669,
      "loss": 4.3959,
      "step": 480
    },
    {
      "epoch": 1.4954848841774637,
      "eval_loss": 4.451333522796631,
      "eval_runtime": 66.8189,
      "eval_samples_per_second": 38.926,
      "eval_steps_per_second": 38.926,
      "step": 480
    },
    {
      "epoch": 1.4986258343148804,
      "grad_norm": 2.859375,
      "learning_rate": 0.0001387852140685109,
      "loss": 4.3828,
      "step": 481
    },
    {
      "epoch": 1.5017667844522968,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00013855564295516234,
      "loss": 4.4479,
      "step": 482
    },
    {
      "epoch": 1.5049077345897133,
      "grad_norm": 3.1875,
      "learning_rate": 0.00013832583291287115,
      "loss": 4.4646,
      "step": 483
    },
    {
      "epoch": 1.50804868472713,
      "grad_norm": 2.4375,
      "learning_rate": 0.00013809578536576797,
      "loss": 4.2876,
      "step": 484
    },
    {
      "epoch": 1.5111896348645466,
      "grad_norm": 2.625,
      "learning_rate": 0.00013786550173945511,
      "loss": 4.2475,
      "step": 485
    },
    {
      "epoch": 1.514330585001963,
      "grad_norm": 2.15625,
      "learning_rate": 0.00013763498346099803,
      "loss": 4.4165,
      "step": 486
    },
    {
      "epoch": 1.5174715351393797,
      "grad_norm": 2.390625,
      "learning_rate": 0.00013740423195891623,
      "loss": 4.3725,
      "step": 487
    },
    {
      "epoch": 1.5206124852767964,
      "grad_norm": 2.5,
      "learning_rate": 0.00013717324866317448,
      "loss": 4.4698,
      "step": 488
    },
    {
      "epoch": 1.5237534354142128,
      "grad_norm": 2.328125,
      "learning_rate": 0.00013694203500517403,
      "loss": 4.31,
      "step": 489
    },
    {
      "epoch": 1.5268943855516293,
      "grad_norm": 2.59375,
      "learning_rate": 0.0001367105924177437,
      "loss": 4.4086,
      "step": 490
    },
    {
      "epoch": 1.530035335689046,
      "grad_norm": 2.421875,
      "learning_rate": 0.0001364789223351309,
      "loss": 4.3244,
      "step": 491
    },
    {
      "epoch": 1.5331762858264626,
      "grad_norm": 2.78125,
      "learning_rate": 0.0001362470261929928,
      "loss": 4.4675,
      "step": 492
    },
    {
      "epoch": 1.536317235963879,
      "grad_norm": 2.328125,
      "learning_rate": 0.00013601490542838765,
      "loss": 4.363,
      "step": 493
    },
    {
      "epoch": 1.5394581861012955,
      "grad_norm": 2.421875,
      "learning_rate": 0.00013578256147976552,
      "loss": 4.6301,
      "step": 494
    },
    {
      "epoch": 1.5425991362387124,
      "grad_norm": 2.453125,
      "learning_rate": 0.00013554999578695956,
      "loss": 4.2604,
      "step": 495
    },
    {
      "epoch": 1.5457400863761288,
      "grad_norm": 2.375,
      "learning_rate": 0.0001353172097911771,
      "loss": 4.4619,
      "step": 496
    },
    {
      "epoch": 1.5488810365135453,
      "grad_norm": 2.015625,
      "learning_rate": 0.00013508420493499069,
      "loss": 4.3473,
      "step": 497
    },
    {
      "epoch": 1.552021986650962,
      "grad_norm": 2.9375,
      "learning_rate": 0.0001348509826623292,
      "loss": 4.5858,
      "step": 498
    },
    {
      "epoch": 1.5551629367883786,
      "grad_norm": 2.375,
      "learning_rate": 0.00013461754441846868,
      "loss": 4.5726,
      "step": 499
    },
    {
      "epoch": 1.558303886925795,
      "grad_norm": 3.015625,
      "learning_rate": 0.00013438389165002366,
      "loss": 4.4859,
      "step": 500
    },
    {
      "epoch": 1.5614448370632115,
      "grad_norm": 3.078125,
      "learning_rate": 0.00013415002580493814,
      "loss": 4.671,
      "step": 501
    },
    {
      "epoch": 1.5645857872006284,
      "grad_norm": 2.984375,
      "learning_rate": 0.00013391594833247642,
      "loss": 4.282,
      "step": 502
    },
    {
      "epoch": 1.5677267373380448,
      "grad_norm": 2.359375,
      "learning_rate": 0.00013368166068321432,
      "loss": 4.0765,
      "step": 503
    },
    {
      "epoch": 1.5708676874754612,
      "grad_norm": 3.109375,
      "learning_rate": 0.00013344716430903014,
      "loss": 4.5436,
      "step": 504
    },
    {
      "epoch": 1.574008637612878,
      "grad_norm": 2.890625,
      "learning_rate": 0.00013321246066309554,
      "loss": 4.3819,
      "step": 505
    },
    {
      "epoch": 1.5771495877502946,
      "grad_norm": 1.6796875,
      "learning_rate": 0.00013297755119986678,
      "loss": 4.2561,
      "step": 506
    },
    {
      "epoch": 1.580290537887711,
      "grad_norm": 2.296875,
      "learning_rate": 0.0001327424373750755,
      "loss": 4.2601,
      "step": 507
    },
    {
      "epoch": 1.5834314880251275,
      "grad_norm": 2.34375,
      "learning_rate": 0.0001325071206457198,
      "loss": 4.4291,
      "step": 508
    },
    {
      "epoch": 1.5865724381625441,
      "grad_norm": 2.25,
      "learning_rate": 0.00013227160247005512,
      "loss": 4.2262,
      "step": 509
    },
    {
      "epoch": 1.5897133882999608,
      "grad_norm": 2.546875,
      "learning_rate": 0.00013203588430758532,
      "loss": 4.5678,
      "step": 510
    },
    {
      "epoch": 1.5928543384373772,
      "grad_norm": 2.703125,
      "learning_rate": 0.0001317999676190535,
      "loss": 4.197,
      "step": 511
    },
    {
      "epoch": 1.595995288574794,
      "grad_norm": 2.703125,
      "learning_rate": 0.0001315638538664331,
      "loss": 4.4492,
      "step": 512
    },
    {
      "epoch": 1.5991362387122106,
      "grad_norm": 6.21875,
      "learning_rate": 0.00013132754451291876,
      "loss": 4.2175,
      "step": 513
    },
    {
      "epoch": 1.602277188849627,
      "grad_norm": 2.53125,
      "learning_rate": 0.0001310910410229172,
      "loss": 4.343,
      "step": 514
    },
    {
      "epoch": 1.6054181389870434,
      "grad_norm": 3.140625,
      "learning_rate": 0.00013085434486203825,
      "loss": 4.3108,
      "step": 515
    },
    {
      "epoch": 1.60855908912446,
      "grad_norm": 2.0625,
      "learning_rate": 0.0001306174574970857,
      "loss": 4.3422,
      "step": 516
    },
    {
      "epoch": 1.6117000392618768,
      "grad_norm": 2.0,
      "learning_rate": 0.00013038038039604822,
      "loss": 4.4012,
      "step": 517
    },
    {
      "epoch": 1.6148409893992932,
      "grad_norm": 2.265625,
      "learning_rate": 0.00013014311502809037,
      "loss": 4.4995,
      "step": 518
    },
    {
      "epoch": 1.6179819395367099,
      "grad_norm": 2.625,
      "learning_rate": 0.0001299056628635432,
      "loss": 4.3733,
      "step": 519
    },
    {
      "epoch": 1.6211228896741265,
      "grad_norm": 2.3125,
      "learning_rate": 0.00012966802537389555,
      "loss": 4.2762,
      "step": 520
    },
    {
      "epoch": 1.624263839811543,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001294302040317846,
      "loss": 4.2215,
      "step": 521
    },
    {
      "epoch": 1.6274047899489594,
      "grad_norm": 2.265625,
      "learning_rate": 0.0001291922003109868,
      "loss": 4.3246,
      "step": 522
    },
    {
      "epoch": 1.630545740086376,
      "grad_norm": 1.9296875,
      "learning_rate": 0.00012895401568640898,
      "loss": 4.3613,
      "step": 523
    },
    {
      "epoch": 1.6336866902237928,
      "grad_norm": 2.296875,
      "learning_rate": 0.0001287156516340789,
      "loss": 4.3989,
      "step": 524
    },
    {
      "epoch": 1.6368276403612092,
      "grad_norm": 1.953125,
      "learning_rate": 0.00012847710963113625,
      "loss": 4.3381,
      "step": 525
    },
    {
      "epoch": 1.6399685904986259,
      "grad_norm": 2.15625,
      "learning_rate": 0.00012823839115582353,
      "loss": 4.2076,
      "step": 526
    },
    {
      "epoch": 1.6431095406360425,
      "grad_norm": 2.359375,
      "learning_rate": 0.00012799949768747674,
      "loss": 4.4172,
      "step": 527
    },
    {
      "epoch": 1.646250490773459,
      "grad_norm": 2.609375,
      "learning_rate": 0.00012776043070651641,
      "loss": 4.3251,
      "step": 528
    },
    {
      "epoch": 1.6493914409108754,
      "grad_norm": 2.09375,
      "learning_rate": 0.00012752119169443828,
      "loss": 4.4384,
      "step": 529
    },
    {
      "epoch": 1.652532391048292,
      "grad_norm": 2.53125,
      "learning_rate": 0.00012728178213380418,
      "loss": 4.4118,
      "step": 530
    },
    {
      "epoch": 1.6556733411857087,
      "grad_norm": 2.96875,
      "learning_rate": 0.00012704220350823276,
      "loss": 4.4677,
      "step": 531
    },
    {
      "epoch": 1.6588142913231252,
      "grad_norm": 2.28125,
      "learning_rate": 0.00012680245730239048,
      "loss": 4.2893,
      "step": 532
    },
    {
      "epoch": 1.6619552414605419,
      "grad_norm": 2.40625,
      "learning_rate": 0.00012656254500198222,
      "loss": 4.4359,
      "step": 533
    },
    {
      "epoch": 1.6650961915979585,
      "grad_norm": 2.15625,
      "learning_rate": 0.00012632246809374215,
      "loss": 4.2847,
      "step": 534
    },
    {
      "epoch": 1.668237141735375,
      "grad_norm": 2.375,
      "learning_rate": 0.00012608222806542455,
      "loss": 4.4685,
      "step": 535
    },
    {
      "epoch": 1.6713780918727914,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001258418264057945,
      "loss": 4.5453,
      "step": 536
    },
    {
      "epoch": 1.674519042010208,
      "grad_norm": 2.25,
      "learning_rate": 0.00012560126460461877,
      "loss": 4.3264,
      "step": 537
    },
    {
      "epoch": 1.6776599921476247,
      "grad_norm": 2.203125,
      "learning_rate": 0.00012536054415265643,
      "loss": 4.3535,
      "step": 538
    },
    {
      "epoch": 1.6808009422850412,
      "grad_norm": 2.3125,
      "learning_rate": 0.00012511966654164982,
      "loss": 4.2926,
      "step": 539
    },
    {
      "epoch": 1.6839418924224578,
      "grad_norm": 2.46875,
      "learning_rate": 0.00012487863326431512,
      "loss": 4.4511,
      "step": 540
    },
    {
      "epoch": 1.6870828425598745,
      "grad_norm": 1.8359375,
      "learning_rate": 0.00012463744581433324,
      "loss": 4.278,
      "step": 541
    },
    {
      "epoch": 1.690223792697291,
      "grad_norm": 1.828125,
      "learning_rate": 0.00012439610568634038,
      "loss": 4.3352,
      "step": 542
    },
    {
      "epoch": 1.6933647428347074,
      "grad_norm": 2.125,
      "learning_rate": 0.00012415461437591897,
      "loss": 4.4679,
      "step": 543
    },
    {
      "epoch": 1.696505692972124,
      "grad_norm": 2.46875,
      "learning_rate": 0.00012391297337958833,
      "loss": 4.4969,
      "step": 544
    },
    {
      "epoch": 1.6996466431095407,
      "grad_norm": 2.140625,
      "learning_rate": 0.00012367118419479535,
      "loss": 4.2671,
      "step": 545
    },
    {
      "epoch": 1.7027875932469572,
      "grad_norm": 2.375,
      "learning_rate": 0.00012342924831990526,
      "loss": 4.4847,
      "step": 546
    },
    {
      "epoch": 1.7059285433843736,
      "grad_norm": 2.625,
      "learning_rate": 0.00012318716725419224,
      "loss": 4.2947,
      "step": 547
    },
    {
      "epoch": 1.7090694935217905,
      "grad_norm": 2.5,
      "learning_rate": 0.00012294494249783037,
      "loss": 4.174,
      "step": 548
    },
    {
      "epoch": 1.712210443659207,
      "grad_norm": 2.4375,
      "learning_rate": 0.00012270257555188407,
      "loss": 4.4681,
      "step": 549
    },
    {
      "epoch": 1.7153513937966234,
      "grad_norm": 13.3125,
      "learning_rate": 0.0001224600679182989,
      "loss": 4.6303,
      "step": 550
    },
    {
      "epoch": 1.71849234393404,
      "grad_norm": 2.515625,
      "learning_rate": 0.00012221742109989233,
      "loss": 4.5057,
      "step": 551
    },
    {
      "epoch": 1.7216332940714567,
      "grad_norm": 2.4375,
      "learning_rate": 0.00012197463660034433,
      "loss": 4.4893,
      "step": 552
    },
    {
      "epoch": 1.7247742442088732,
      "grad_norm": 2.234375,
      "learning_rate": 0.00012173171592418809,
      "loss": 4.279,
      "step": 553
    },
    {
      "epoch": 1.7279151943462896,
      "grad_norm": 2.265625,
      "learning_rate": 0.00012148866057680058,
      "loss": 4.4123,
      "step": 554
    },
    {
      "epoch": 1.7310561444837065,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001212454720643935,
      "loss": 4.2059,
      "step": 555
    },
    {
      "epoch": 1.734197094621123,
      "grad_norm": 1.890625,
      "learning_rate": 0.00012100215189400363,
      "loss": 4.5014,
      "step": 556
    },
    {
      "epoch": 1.7373380447585394,
      "grad_norm": 2.15625,
      "learning_rate": 0.00012075870157348374,
      "loss": 4.3094,
      "step": 557
    },
    {
      "epoch": 1.740478994895956,
      "grad_norm": 1.984375,
      "learning_rate": 0.00012051512261149304,
      "loss": 4.3979,
      "step": 558
    },
    {
      "epoch": 1.7436199450333727,
      "grad_norm": 2.234375,
      "learning_rate": 0.000120271416517488,
      "loss": 4.3862,
      "step": 559
    },
    {
      "epoch": 1.7467608951707891,
      "grad_norm": 2.03125,
      "learning_rate": 0.0001200275848017129,
      "loss": 4.2488,
      "step": 560
    },
    {
      "epoch": 1.7467608951707891,
      "eval_loss": 4.41070032119751,
      "eval_runtime": 66.8827,
      "eval_samples_per_second": 38.889,
      "eval_steps_per_second": 38.889,
      "step": 560
    },
    {
      "epoch": 1.7499018453082056,
      "grad_norm": 2.6875,
      "learning_rate": 0.00011978362897519048,
      "loss": 4.3708,
      "step": 561
    },
    {
      "epoch": 1.7530427954456222,
      "grad_norm": 2.046875,
      "learning_rate": 0.00011953955054971267,
      "loss": 4.3017,
      "step": 562
    },
    {
      "epoch": 1.756183745583039,
      "grad_norm": 2.78125,
      "learning_rate": 0.00011929535103783102,
      "loss": 4.5012,
      "step": 563
    },
    {
      "epoch": 1.7593246957204554,
      "grad_norm": 2.0,
      "learning_rate": 0.00011905103195284755,
      "loss": 4.2299,
      "step": 564
    },
    {
      "epoch": 1.762465645857872,
      "grad_norm": 2.234375,
      "learning_rate": 0.00011880659480880526,
      "loss": 4.3933,
      "step": 565
    },
    {
      "epoch": 1.7656065959952887,
      "grad_norm": 2.234375,
      "learning_rate": 0.0001185620411204787,
      "loss": 4.2709,
      "step": 566
    },
    {
      "epoch": 1.7687475461327051,
      "grad_norm": 2.390625,
      "learning_rate": 0.00011831737240336474,
      "loss": 4.4057,
      "step": 567
    },
    {
      "epoch": 1.7718884962701216,
      "grad_norm": 2.515625,
      "learning_rate": 0.00011807259017367298,
      "loss": 4.4554,
      "step": 568
    },
    {
      "epoch": 1.7750294464075382,
      "grad_norm": 2.296875,
      "learning_rate": 0.00011782769594831654,
      "loss": 4.3689,
      "step": 569
    },
    {
      "epoch": 1.778170396544955,
      "grad_norm": 2.59375,
      "learning_rate": 0.00011758269124490246,
      "loss": 4.3838,
      "step": 570
    },
    {
      "epoch": 1.7813113466823713,
      "grad_norm": 2.015625,
      "learning_rate": 0.00011733757758172263,
      "loss": 4.3976,
      "step": 571
    },
    {
      "epoch": 1.784452296819788,
      "grad_norm": 2.140625,
      "learning_rate": 0.00011709235647774393,
      "loss": 4.402,
      "step": 572
    },
    {
      "epoch": 1.7875932469572047,
      "grad_norm": 3.015625,
      "learning_rate": 0.00011684702945259917,
      "loss": 4.2222,
      "step": 573
    },
    {
      "epoch": 1.7907341970946211,
      "grad_norm": 2.3125,
      "learning_rate": 0.00011660159802657751,
      "loss": 4.4154,
      "step": 574
    },
    {
      "epoch": 1.7938751472320376,
      "grad_norm": 2.28125,
      "learning_rate": 0.00011635606372061514,
      "loss": 4.4392,
      "step": 575
    },
    {
      "epoch": 1.7970160973694542,
      "grad_norm": 2.109375,
      "learning_rate": 0.00011611042805628569,
      "loss": 4.4036,
      "step": 576
    },
    {
      "epoch": 1.8001570475068709,
      "grad_norm": 2.234375,
      "learning_rate": 0.00011586469255579105,
      "loss": 4.4612,
      "step": 577
    },
    {
      "epoch": 1.8032979976442873,
      "grad_norm": 2.5625,
      "learning_rate": 0.00011561885874195168,
      "loss": 4.4179,
      "step": 578
    },
    {
      "epoch": 1.806438947781704,
      "grad_norm": 2.34375,
      "learning_rate": 0.00011537292813819727,
      "loss": 4.3832,
      "step": 579
    },
    {
      "epoch": 1.8095798979191207,
      "grad_norm": 2.28125,
      "learning_rate": 0.00011512690226855747,
      "loss": 4.418,
      "step": 580
    },
    {
      "epoch": 1.812720848056537,
      "grad_norm": 2.375,
      "learning_rate": 0.00011488078265765209,
      "loss": 4.2513,
      "step": 581
    },
    {
      "epoch": 1.8158617981939535,
      "grad_norm": 2.46875,
      "learning_rate": 0.00011463457083068203,
      "loss": 4.4319,
      "step": 582
    },
    {
      "epoch": 1.8190027483313702,
      "grad_norm": 2.078125,
      "learning_rate": 0.00011438826831341953,
      "loss": 4.1437,
      "step": 583
    },
    {
      "epoch": 1.8221436984687869,
      "grad_norm": 2.125,
      "learning_rate": 0.00011414187663219891,
      "loss": 4.1201,
      "step": 584
    },
    {
      "epoch": 1.8252846486062033,
      "grad_norm": 2.78125,
      "learning_rate": 0.00011389539731390699,
      "loss": 4.4478,
      "step": 585
    },
    {
      "epoch": 1.82842559874362,
      "grad_norm": 2.515625,
      "learning_rate": 0.00011364883188597369,
      "loss": 4.3716,
      "step": 586
    },
    {
      "epoch": 1.8315665488810366,
      "grad_norm": 2.03125,
      "learning_rate": 0.0001134021818763626,
      "loss": 4.2461,
      "step": 587
    },
    {
      "epoch": 1.834707499018453,
      "grad_norm": 1.9140625,
      "learning_rate": 0.0001131554488135614,
      "loss": 4.3287,
      "step": 588
    },
    {
      "epoch": 1.8378484491558695,
      "grad_norm": 2.3125,
      "learning_rate": 0.00011290863422657241,
      "loss": 4.3955,
      "step": 589
    },
    {
      "epoch": 1.8409893992932862,
      "grad_norm": 1.84375,
      "learning_rate": 0.00011266173964490332,
      "loss": 4.0536,
      "step": 590
    },
    {
      "epoch": 1.8441303494307029,
      "grad_norm": 1.984375,
      "learning_rate": 0.00011241476659855736,
      "loss": 4.3023,
      "step": 591
    },
    {
      "epoch": 1.8472712995681193,
      "grad_norm": 2.1875,
      "learning_rate": 0.00011216771661802412,
      "loss": 4.3013,
      "step": 592
    },
    {
      "epoch": 1.850412249705536,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00011192059123426987,
      "loss": 4.5245,
      "step": 593
    },
    {
      "epoch": 1.8535531998429526,
      "grad_norm": 2.1875,
      "learning_rate": 0.00011167339197872828,
      "loss": 4.4204,
      "step": 594
    },
    {
      "epoch": 1.856694149980369,
      "grad_norm": 1.828125,
      "learning_rate": 0.00011142612038329066,
      "loss": 4.0721,
      "step": 595
    },
    {
      "epoch": 1.8598351001177855,
      "grad_norm": 2.484375,
      "learning_rate": 0.00011117877798029665,
      "loss": 4.2945,
      "step": 596
    },
    {
      "epoch": 1.8629760502552022,
      "grad_norm": 2.203125,
      "learning_rate": 0.00011093136630252477,
      "loss": 4.4501,
      "step": 597
    },
    {
      "epoch": 1.8661170003926189,
      "grad_norm": 1.796875,
      "learning_rate": 0.00011068388688318272,
      "loss": 4.3144,
      "step": 598
    },
    {
      "epoch": 1.8692579505300353,
      "grad_norm": 2.171875,
      "learning_rate": 0.00011043634125589808,
      "loss": 4.1987,
      "step": 599
    },
    {
      "epoch": 1.8723989006674517,
      "grad_norm": 2.15625,
      "learning_rate": 0.00011018873095470865,
      "loss": 4.3245,
      "step": 600
    },
    {
      "epoch": 1.8755398508048686,
      "grad_norm": 2.65625,
      "learning_rate": 0.00010994105751405306,
      "loss": 4.3071,
      "step": 601
    },
    {
      "epoch": 1.878680800942285,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001096933224687612,
      "loss": 4.3158,
      "step": 602
    },
    {
      "epoch": 1.8818217510797015,
      "grad_norm": 2.140625,
      "learning_rate": 0.00010944552735404472,
      "loss": 4.4555,
      "step": 603
    },
    {
      "epoch": 1.8849627012171182,
      "grad_norm": 2.515625,
      "learning_rate": 0.00010919767370548755,
      "loss": 4.2628,
      "step": 604
    },
    {
      "epoch": 1.8881036513545348,
      "grad_norm": 2.53125,
      "learning_rate": 0.00010894976305903633,
      "loss": 4.4439,
      "step": 605
    },
    {
      "epoch": 1.8912446014919513,
      "grad_norm": 2.640625,
      "learning_rate": 0.00010870179695099082,
      "loss": 4.2774,
      "step": 606
    },
    {
      "epoch": 1.8943855516293677,
      "grad_norm": 1.9921875,
      "learning_rate": 0.00010845377691799471,
      "loss": 4.0835,
      "step": 607
    },
    {
      "epoch": 1.8975265017667846,
      "grad_norm": 2.6875,
      "learning_rate": 0.00010820570449702563,
      "loss": 4.3015,
      "step": 608
    },
    {
      "epoch": 1.900667451904201,
      "grad_norm": 2.1875,
      "learning_rate": 0.00010795758122538597,
      "loss": 4.286,
      "step": 609
    },
    {
      "epoch": 1.9038084020416175,
      "grad_norm": 2.4375,
      "learning_rate": 0.0001077094086406932,
      "loss": 4.403,
      "step": 610
    },
    {
      "epoch": 1.9069493521790342,
      "grad_norm": 1.96875,
      "learning_rate": 0.00010746118828087046,
      "loss": 4.3406,
      "step": 611
    },
    {
      "epoch": 1.9100903023164508,
      "grad_norm": 2.421875,
      "learning_rate": 0.00010721292168413685,
      "loss": 4.2346,
      "step": 612
    },
    {
      "epoch": 1.9132312524538673,
      "grad_norm": 2.09375,
      "learning_rate": 0.00010696461038899803,
      "loss": 4.1966,
      "step": 613
    },
    {
      "epoch": 1.9163722025912837,
      "grad_norm": 1.9765625,
      "learning_rate": 0.00010671625593423671,
      "loss": 4.3923,
      "step": 614
    },
    {
      "epoch": 1.9195131527287004,
      "grad_norm": 2.296875,
      "learning_rate": 0.00010646785985890297,
      "loss": 4.5358,
      "step": 615
    },
    {
      "epoch": 1.922654102866117,
      "grad_norm": 2.125,
      "learning_rate": 0.00010621942370230491,
      "loss": 4.268,
      "step": 616
    },
    {
      "epoch": 1.9257950530035335,
      "grad_norm": 2.15625,
      "learning_rate": 0.00010597094900399894,
      "loss": 4.1337,
      "step": 617
    },
    {
      "epoch": 1.9289360031409502,
      "grad_norm": 1.8515625,
      "learning_rate": 0.00010572243730378033,
      "loss": 4.4463,
      "step": 618
    },
    {
      "epoch": 1.9320769532783668,
      "grad_norm": 2.375,
      "learning_rate": 0.00010547389014167368,
      "loss": 4.4137,
      "step": 619
    },
    {
      "epoch": 1.9352179034157833,
      "grad_norm": 1.71875,
      "learning_rate": 0.00010522530905792333,
      "loss": 4.1703,
      "step": 620
    },
    {
      "epoch": 1.9383588535531997,
      "grad_norm": 2.1875,
      "learning_rate": 0.00010497669559298377,
      "loss": 4.4996,
      "step": 621
    },
    {
      "epoch": 1.9414998036906164,
      "grad_norm": 1.84375,
      "learning_rate": 0.00010472805128751028,
      "loss": 4.3086,
      "step": 622
    },
    {
      "epoch": 1.944640753828033,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00010447937768234917,
      "loss": 4.3102,
      "step": 623
    },
    {
      "epoch": 1.9477817039654495,
      "grad_norm": 2.109375,
      "learning_rate": 0.00010423067631852834,
      "loss": 4.2649,
      "step": 624
    },
    {
      "epoch": 1.9509226541028661,
      "grad_norm": 1.890625,
      "learning_rate": 0.00010398194873724766,
      "loss": 4.3634,
      "step": 625
    },
    {
      "epoch": 1.9540636042402828,
      "grad_norm": 2.359375,
      "learning_rate": 0.00010373319647986964,
      "loss": 4.4628,
      "step": 626
    },
    {
      "epoch": 1.9572045543776992,
      "grad_norm": 2.234375,
      "learning_rate": 0.00010348442108790948,
      "loss": 4.1411,
      "step": 627
    },
    {
      "epoch": 1.9603455045151157,
      "grad_norm": 2.234375,
      "learning_rate": 0.00010323562410302587,
      "loss": 4.211,
      "step": 628
    },
    {
      "epoch": 1.9634864546525324,
      "grad_norm": 2.390625,
      "learning_rate": 0.00010298680706701136,
      "loss": 4.3108,
      "step": 629
    },
    {
      "epoch": 1.966627404789949,
      "grad_norm": 2.125,
      "learning_rate": 0.00010273797152178262,
      "loss": 4.4238,
      "step": 630
    },
    {
      "epoch": 1.9697683549273655,
      "grad_norm": 2.5625,
      "learning_rate": 0.00010248911900937112,
      "loss": 4.3534,
      "step": 631
    },
    {
      "epoch": 1.9729093050647821,
      "grad_norm": 1.9453125,
      "learning_rate": 0.00010224025107191342,
      "loss": 4.2111,
      "step": 632
    },
    {
      "epoch": 1.9760502552021988,
      "grad_norm": 2.078125,
      "learning_rate": 0.00010199136925164175,
      "loss": 4.2815,
      "step": 633
    },
    {
      "epoch": 1.9791912053396152,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00010174247509087429,
      "loss": 4.2197,
      "step": 634
    },
    {
      "epoch": 1.9823321554770317,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00010149357013200569,
      "loss": 4.3111,
      "step": 635
    },
    {
      "epoch": 1.9854731056144483,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00010124465591749758,
      "loss": 4.3573,
      "step": 636
    }
  ],
  "logging_steps": 1,
  "max_steps": 1272,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 318,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.471126066169119e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}