{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 26,
  "global_step": 253,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003952569169960474,
      "grad_norm": 3.0407819747924805,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.3652,
      "step": 1
    },
    {
      "epoch": 0.007905138339920948,
      "grad_norm": 3.093733310699463,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.1458,
      "step": 2
    },
    {
      "epoch": 0.011857707509881422,
      "grad_norm": 3.0263988971710205,
      "learning_rate": 1e-05,
      "loss": 2.2628,
      "step": 3
    },
    {
      "epoch": 0.015810276679841896,
      "grad_norm": 2.6713979244232178,
      "learning_rate": 9.999605221019082e-06,
      "loss": 2.0308,
      "step": 4
    },
    {
      "epoch": 0.019762845849802372,
      "grad_norm": 2.4664857387542725,
      "learning_rate": 9.9984209464165e-06,
      "loss": 1.6917,
      "step": 5
    },
    {
      "epoch": 0.023715415019762844,
      "grad_norm": 2.100984811782837,
      "learning_rate": 9.996447363202947e-06,
      "loss": 1.8489,
      "step": 6
    },
    {
      "epoch": 0.02766798418972332,
      "grad_norm": 1.7837852239608765,
      "learning_rate": 9.99368478303009e-06,
      "loss": 1.9894,
      "step": 7
    },
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 1.6338787078857422,
      "learning_rate": 9.990133642141359e-06,
      "loss": 1.8366,
      "step": 8
    },
    {
      "epoch": 0.03557312252964427,
      "grad_norm": 1.7102547883987427,
      "learning_rate": 9.98579450130307e-06,
      "loss": 1.9013,
      "step": 9
    },
    {
      "epoch": 0.039525691699604744,
      "grad_norm": 1.8172574043273926,
      "learning_rate": 9.980668045715864e-06,
      "loss": 2.034,
      "step": 10
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 1.7970800399780273,
      "learning_rate": 9.974755084906503e-06,
      "loss": 1.8565,
      "step": 11
    },
    {
      "epoch": 0.04743083003952569,
      "grad_norm": 1.9662507772445679,
      "learning_rate": 9.968056552600043e-06,
      "loss": 1.8154,
      "step": 12
    },
    {
      "epoch": 0.05138339920948617,
      "grad_norm": 1.6226023435592651,
      "learning_rate": 9.960573506572391e-06,
      "loss": 1.7205,
      "step": 13
    },
    {
      "epoch": 0.05533596837944664,
      "grad_norm": 1.4996356964111328,
      "learning_rate": 9.952307128483257e-06,
      "loss": 1.8481,
      "step": 14
    },
    {
      "epoch": 0.05928853754940711,
      "grad_norm": 1.2719931602478027,
      "learning_rate": 9.94325872368957e-06,
      "loss": 1.5792,
      "step": 15
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 1.2413394451141357,
      "learning_rate": 9.93342972103934e-06,
      "loss": 1.6527,
      "step": 16
    },
    {
      "epoch": 0.06719367588932806,
      "grad_norm": 1.1712374687194824,
      "learning_rate": 9.922821672646028e-06,
      "loss": 1.3883,
      "step": 17
    },
    {
      "epoch": 0.07114624505928854,
      "grad_norm": 1.1695728302001953,
      "learning_rate": 9.911436253643445e-06,
      "loss": 1.5297,
      "step": 18
    },
    {
      "epoch": 0.07509881422924901,
      "grad_norm": 1.1794648170471191,
      "learning_rate": 9.899275261921236e-06,
      "loss": 1.5525,
      "step": 19
    },
    {
      "epoch": 0.07905138339920949,
      "grad_norm": 1.131502628326416,
      "learning_rate": 9.886340617840968e-06,
      "loss": 1.5752,
      "step": 20
    },
    {
      "epoch": 0.08300395256916997,
      "grad_norm": 1.1554540395736694,
      "learning_rate": 9.872634363932887e-06,
      "loss": 1.5944,
      "step": 21
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 1.1099374294281006,
      "learning_rate": 9.85815866457337e-06,
      "loss": 1.4019,
      "step": 22
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.2356349229812622,
      "learning_rate": 9.842915805643156e-06,
      "loss": 1.706,
      "step": 23
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 1.1689324378967285,
      "learning_rate": 9.82690819416637e-06,
      "loss": 1.6249,
      "step": 24
    },
    {
      "epoch": 0.09881422924901186,
      "grad_norm": 1.2375783920288086,
      "learning_rate": 9.81013835793043e-06,
      "loss": 1.8374,
      "step": 25
    },
    {
      "epoch": 0.10276679841897234,
      "grad_norm": 1.1797913312911987,
      "learning_rate": 9.79260894508688e-06,
      "loss": 1.6161,
      "step": 26
    },
    {
      "epoch": 0.10276679841897234,
      "eval_loss": 1.4920315742492676,
      "eval_runtime": 0.6276,
      "eval_samples_per_second": 33.462,
      "eval_steps_per_second": 4.78,
      "step": 26
    },
    {
      "epoch": 0.1067193675889328,
      "grad_norm": 1.1279163360595703,
      "learning_rate": 9.774322723733216e-06,
      "loss": 1.6593,
      "step": 27
    },
    {
      "epoch": 0.11067193675889328,
      "grad_norm": 1.1455029249191284,
      "learning_rate": 9.755282581475769e-06,
      "loss": 1.6982,
      "step": 28
    },
    {
      "epoch": 0.11462450592885376,
      "grad_norm": 1.0429457426071167,
      "learning_rate": 9.735491524973723e-06,
      "loss": 1.4423,
      "step": 29
    },
    {
      "epoch": 0.11857707509881422,
      "grad_norm": 0.9471132755279541,
      "learning_rate": 9.714952679464324e-06,
      "loss": 1.3055,
      "step": 30
    },
    {
      "epoch": 0.1225296442687747,
      "grad_norm": 1.0985954999923706,
      "learning_rate": 9.693669288269371e-06,
      "loss": 1.6302,
      "step": 31
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": 1.11372709274292,
      "learning_rate": 9.671644712283061e-06,
      "loss": 1.7975,
      "step": 32
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.9115369915962219,
      "learning_rate": 9.648882429441258e-06,
      "loss": 1.2709,
      "step": 33
    },
    {
      "epoch": 0.13438735177865613,
      "grad_norm": 1.0038697719573975,
      "learning_rate": 9.62538603417229e-06,
      "loss": 1.4833,
      "step": 34
    },
    {
      "epoch": 0.1383399209486166,
      "grad_norm": 1.0109611749649048,
      "learning_rate": 9.601159236829353e-06,
      "loss": 1.2978,
      "step": 35
    },
    {
      "epoch": 0.1422924901185771,
      "grad_norm": 0.966667115688324,
      "learning_rate": 9.576205863104588e-06,
      "loss": 1.5622,
      "step": 36
    },
    {
      "epoch": 0.14624505928853754,
      "grad_norm": 1.0922729969024658,
      "learning_rate": 9.550529853424979e-06,
      "loss": 1.7766,
      "step": 37
    },
    {
      "epoch": 0.15019762845849802,
      "grad_norm": 1.010776162147522,
      "learning_rate": 9.524135262330098e-06,
      "loss": 1.5206,
      "step": 38
    },
    {
      "epoch": 0.1541501976284585,
      "grad_norm": 0.9982693791389465,
      "learning_rate": 9.497026257831856e-06,
      "loss": 1.5341,
      "step": 39
    },
    {
      "epoch": 0.15810276679841898,
      "grad_norm": 0.9735735058784485,
      "learning_rate": 9.46920712075632e-06,
      "loss": 1.4157,
      "step": 40
    },
    {
      "epoch": 0.16205533596837945,
      "grad_norm": 0.9151104092597961,
      "learning_rate": 9.440682244067724e-06,
      "loss": 1.2846,
      "step": 41
    },
    {
      "epoch": 0.16600790513833993,
      "grad_norm": 0.9795275330543518,
      "learning_rate": 9.411456132174768e-06,
      "loss": 1.4727,
      "step": 42
    },
    {
      "epoch": 0.16996047430830039,
      "grad_norm": 1.1112526655197144,
      "learning_rate": 9.381533400219319e-06,
      "loss": 1.6619,
      "step": 43
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.9755843877792358,
      "learning_rate": 9.35091877334763e-06,
      "loss": 1.4687,
      "step": 44
    },
    {
      "epoch": 0.17786561264822134,
      "grad_norm": 0.9589361548423767,
      "learning_rate": 9.319617085964177e-06,
      "loss": 1.4871,
      "step": 45
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.105637788772583,
      "learning_rate": 9.287633280968263e-06,
      "loss": 1.2694,
      "step": 46
    },
    {
      "epoch": 0.1857707509881423,
      "grad_norm": 0.9662937521934509,
      "learning_rate": 9.25497240897346e-06,
      "loss": 1.2148,
      "step": 47
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": 1.0539385080337524,
      "learning_rate": 9.221639627510076e-06,
      "loss": 1.5932,
      "step": 48
    },
    {
      "epoch": 0.19367588932806323,
      "grad_norm": 0.9249448180198669,
      "learning_rate": 9.18764020021071e-06,
      "loss": 1.3074,
      "step": 49
    },
    {
      "epoch": 0.1976284584980237,
      "grad_norm": 1.0217876434326172,
      "learning_rate": 9.152979495979064e-06,
      "loss": 1.5327,
      "step": 50
    },
    {
      "epoch": 0.2015810276679842,
      "grad_norm": 1.070178747177124,
      "learning_rate": 9.117662988142138e-06,
      "loss": 1.6561,
      "step": 51
    },
    {
      "epoch": 0.20553359683794467,
      "grad_norm": 0.9971439242362976,
      "learning_rate": 9.08169625358592e-06,
      "loss": 1.3683,
      "step": 52
    },
    {
      "epoch": 0.20553359683794467,
      "eval_loss": 1.325599193572998,
      "eval_runtime": 0.6316,
      "eval_samples_per_second": 33.25,
      "eval_steps_per_second": 4.75,
      "step": 52
    },
    {
      "epoch": 0.20948616600790515,
      "grad_norm": 0.9724494814872742,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.5192,
      "step": 53
    },
    {
      "epoch": 0.2134387351778656,
      "grad_norm": 0.9346773624420166,
      "learning_rate": 9.007834924354384e-06,
      "loss": 1.4107,
      "step": 54
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.9584831595420837,
      "learning_rate": 8.969951993239177e-06,
      "loss": 1.392,
      "step": 55
    },
    {
      "epoch": 0.22134387351778656,
      "grad_norm": 0.8788594603538513,
      "learning_rate": 8.931442160683094e-06,
      "loss": 1.2833,
      "step": 56
    },
    {
      "epoch": 0.22529644268774704,
      "grad_norm": 0.9413896203041077,
      "learning_rate": 8.892311507835118e-06,
      "loss": 1.26,
      "step": 57
    },
    {
      "epoch": 0.22924901185770752,
      "grad_norm": 0.944340169429779,
      "learning_rate": 8.852566213878947e-06,
      "loss": 1.3223,
      "step": 58
    },
    {
      "epoch": 0.233201581027668,
      "grad_norm": 0.8935737609863281,
      "learning_rate": 8.81221255505724e-06,
      "loss": 1.3826,
      "step": 59
    },
    {
      "epoch": 0.23715415019762845,
      "grad_norm": 0.9506601095199585,
      "learning_rate": 8.77125690368052e-06,
      "loss": 1.4478,
      "step": 60
    },
    {
      "epoch": 0.24110671936758893,
      "grad_norm": 0.9523410201072693,
      "learning_rate": 8.729705727120911e-06,
      "loss": 1.3503,
      "step": 61
    },
    {
      "epoch": 0.2450592885375494,
      "grad_norm": 0.8316011428833008,
      "learning_rate": 8.68756558679087e-06,
      "loss": 1.041,
      "step": 62
    },
    {
      "epoch": 0.2490118577075099,
      "grad_norm": 0.9092923998832703,
      "learning_rate": 8.644843137107058e-06,
      "loss": 1.323,
      "step": 63
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": 0.9320958852767944,
      "learning_rate": 8.601545124439535e-06,
      "loss": 1.3562,
      "step": 64
    },
    {
      "epoch": 0.25691699604743085,
      "grad_norm": 0.9427369832992554,
      "learning_rate": 8.557678386046429e-06,
      "loss": 1.5575,
      "step": 65
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.9649813175201416,
      "learning_rate": 8.513249848994248e-06,
      "loss": 1.2068,
      "step": 66
    },
    {
      "epoch": 0.2648221343873518,
      "grad_norm": 0.9272534251213074,
      "learning_rate": 8.468266529064025e-06,
      "loss": 1.2409,
      "step": 67
    },
    {
      "epoch": 0.26877470355731226,
      "grad_norm": 0.952318549156189,
      "learning_rate": 8.422735529643445e-06,
      "loss": 1.4648,
      "step": 68
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.7945717573165894,
      "learning_rate": 8.376664040605122e-06,
      "loss": 1.142,
      "step": 69
    },
    {
      "epoch": 0.2766798418972332,
      "grad_norm": 0.8417496085166931,
      "learning_rate": 8.33005933717126e-06,
      "loss": 1.179,
      "step": 70
    },
    {
      "epoch": 0.28063241106719367,
      "grad_norm": 0.8613891005516052,
      "learning_rate": 8.282928778764783e-06,
      "loss": 1.258,
      "step": 71
    },
    {
      "epoch": 0.2845849802371542,
      "grad_norm": 0.8771772980690002,
      "learning_rate": 8.235279807847223e-06,
      "loss": 1.3277,
      "step": 72
    },
    {
      "epoch": 0.2885375494071146,
      "grad_norm": 0.9778826832771301,
      "learning_rate": 8.18711994874345e-06,
      "loss": 1.1869,
      "step": 73
    },
    {
      "epoch": 0.2924901185770751,
      "grad_norm": 0.9443055391311646,
      "learning_rate": 8.138456806453503e-06,
      "loss": 1.37,
      "step": 74
    },
    {
      "epoch": 0.2964426877470356,
      "grad_norm": 0.8966163992881775,
      "learning_rate": 8.089298065451673e-06,
      "loss": 1.2171,
      "step": 75
    },
    {
      "epoch": 0.30039525691699603,
      "grad_norm": 0.9195836782455444,
      "learning_rate": 8.039651488473028e-06,
      "loss": 1.3983,
      "step": 76
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.952008843421936,
      "learning_rate": 7.989524915287595e-06,
      "loss": 1.4224,
      "step": 77
    },
    {
      "epoch": 0.308300395256917,
      "grad_norm": 1.0114339590072632,
      "learning_rate": 7.938926261462366e-06,
      "loss": 1.409,
      "step": 78
    },
    {
      "epoch": 0.308300395256917,
      "eval_loss": 1.2486090660095215,
      "eval_runtime": 0.6312,
      "eval_samples_per_second": 33.269,
      "eval_steps_per_second": 4.753,
      "step": 78
    },
    {
      "epoch": 0.31225296442687744,
      "grad_norm": 0.8975977301597595,
      "learning_rate": 7.887863517111337e-06,
      "loss": 1.3565,
      "step": 79
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": 0.9322842955589294,
      "learning_rate": 7.836344745633785e-06,
      "loss": 1.336,
      "step": 80
    },
    {
      "epoch": 0.3201581027667984,
      "grad_norm": 0.934016227722168,
      "learning_rate": 7.78437808244094e-06,
      "loss": 1.318,
      "step": 81
    },
    {
      "epoch": 0.3241106719367589,
      "grad_norm": 0.8984368443489075,
      "learning_rate": 7.731971733671347e-06,
      "loss": 1.264,
      "step": 82
    },
    {
      "epoch": 0.32806324110671936,
      "grad_norm": 0.9175249338150024,
      "learning_rate": 7.679133974894984e-06,
      "loss": 1.2758,
      "step": 83
    },
    {
      "epoch": 0.33201581027667987,
      "grad_norm": 1.0880227088928223,
      "learning_rate": 7.6258731498064796e-06,
      "loss": 1.1448,
      "step": 84
    },
    {
      "epoch": 0.3359683794466403,
      "grad_norm": 0.8632190823554993,
      "learning_rate": 7.572197668907533e-06,
      "loss": 1.2644,
      "step": 85
    },
    {
      "epoch": 0.33992094861660077,
      "grad_norm": 0.8895804286003113,
      "learning_rate": 7.518116008178805e-06,
      "loss": 1.2656,
      "step": 86
    },
    {
      "epoch": 0.3438735177865613,
      "grad_norm": 0.9582334756851196,
      "learning_rate": 7.463636707741458e-06,
      "loss": 1.2453,
      "step": 87
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.8999531865119934,
      "learning_rate": 7.408768370508577e-06,
      "loss": 1.1815,
      "step": 88
    },
    {
      "epoch": 0.35177865612648224,
      "grad_norm": 0.8813087940216064,
      "learning_rate": 7.353519660826665e-06,
      "loss": 1.2232,
      "step": 89
    },
    {
      "epoch": 0.3557312252964427,
      "grad_norm": 0.8202010989189148,
      "learning_rate": 7.297899303107441e-06,
      "loss": 1.1386,
      "step": 90
    },
    {
      "epoch": 0.35968379446640314,
      "grad_norm": 0.9317258596420288,
      "learning_rate": 7.241916080450163e-06,
      "loss": 1.2962,
      "step": 91
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.8814587593078613,
      "learning_rate": 7.185578833254665e-06,
      "loss": 1.3109,
      "step": 92
    },
    {
      "epoch": 0.3675889328063241,
      "grad_norm": 0.9203696846961975,
      "learning_rate": 7.128896457825364e-06,
      "loss": 1.4728,
      "step": 93
    },
    {
      "epoch": 0.3715415019762846,
      "grad_norm": 0.842402994632721,
      "learning_rate": 7.071877904966422e-06,
      "loss": 1.2597,
      "step": 94
    },
    {
      "epoch": 0.37549407114624506,
      "grad_norm": 0.8974599838256836,
      "learning_rate": 7.014532178568314e-06,
      "loss": 1.2041,
      "step": 95
    },
    {
      "epoch": 0.3794466403162055,
      "grad_norm": 0.8709033727645874,
      "learning_rate": 6.9568683341860135e-06,
      "loss": 1.1369,
      "step": 96
    },
    {
      "epoch": 0.383399209486166,
      "grad_norm": 0.8162269592285156,
      "learning_rate": 6.898895477609007e-06,
      "loss": 1.2103,
      "step": 97
    },
    {
      "epoch": 0.38735177865612647,
      "grad_norm": 0.8966283798217773,
      "learning_rate": 6.840622763423391e-06,
      "loss": 1.2609,
      "step": 98
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.8919047117233276,
      "learning_rate": 6.782059393566254e-06,
      "loss": 1.1807,
      "step": 99
    },
    {
      "epoch": 0.3952569169960474,
      "grad_norm": 0.9296970367431641,
      "learning_rate": 6.723214615872585e-06,
      "loss": 1.3748,
      "step": 100
    },
    {
      "epoch": 0.39920948616600793,
      "grad_norm": 0.8833282589912415,
      "learning_rate": 6.664097722614934e-06,
      "loss": 1.271,
      "step": 101
    },
    {
      "epoch": 0.4031620553359684,
      "grad_norm": 0.9111071228981018,
      "learning_rate": 6.604718049036047e-06,
      "loss": 1.3016,
      "step": 102
    },
    {
      "epoch": 0.40711462450592883,
      "grad_norm": 0.9141144156455994,
      "learning_rate": 6.545084971874738e-06,
      "loss": 1.3072,
      "step": 103
    },
    {
      "epoch": 0.41106719367588934,
      "grad_norm": 0.8589788675308228,
      "learning_rate": 6.485207907885175e-06,
      "loss": 1.1914,
      "step": 104
    },
    {
      "epoch": 0.41106719367588934,
      "eval_loss": 1.2048839330673218,
      "eval_runtime": 0.6355,
      "eval_samples_per_second": 33.045,
      "eval_steps_per_second": 4.721,
      "step": 104
    },
    {
      "epoch": 0.4150197628458498,
      "grad_norm": 0.9179502725601196,
      "learning_rate": 6.425096312349881e-06,
      "loss": 1.3336,
      "step": 105
    },
    {
      "epoch": 0.4189723320158103,
      "grad_norm": 0.8490063548088074,
      "learning_rate": 6.364759677586627e-06,
      "loss": 1.275,
      "step": 106
    },
    {
      "epoch": 0.42292490118577075,
      "grad_norm": 0.8626274466514587,
      "learning_rate": 6.304207531449486e-06,
      "loss": 1.237,
      "step": 107
    },
    {
      "epoch": 0.4268774703557312,
      "grad_norm": 0.855128824710846,
      "learning_rate": 6.243449435824276e-06,
      "loss": 1.1993,
      "step": 108
    },
    {
      "epoch": 0.4308300395256917,
      "grad_norm": 0.8959077000617981,
      "learning_rate": 6.182494985118625e-06,
      "loss": 1.3898,
      "step": 109
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.9411128163337708,
      "learning_rate": 6.121353804746907e-06,
      "loss": 1.1805,
      "step": 110
    },
    {
      "epoch": 0.43873517786561267,
      "grad_norm": 0.8071564435958862,
      "learning_rate": 6.060035549610275e-06,
      "loss": 0.8793,
      "step": 111
    },
    {
      "epoch": 0.4426877470355731,
      "grad_norm": 0.873630702495575,
      "learning_rate": 5.9985499025720354e-06,
      "loss": 1.3551,
      "step": 112
    },
    {
      "epoch": 0.44664031620553357,
      "grad_norm": 0.7491222620010376,
      "learning_rate": 5.936906572928625e-06,
      "loss": 1.0515,
      "step": 113
    },
    {
      "epoch": 0.4505928853754941,
      "grad_norm": 0.8194934129714966,
      "learning_rate": 5.8751152948763815e-06,
      "loss": 1.0884,
      "step": 114
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.9355419874191284,
      "learning_rate": 5.813185825974419e-06,
      "loss": 1.4432,
      "step": 115
    },
    {
      "epoch": 0.45849802371541504,
      "grad_norm": 0.760794460773468,
      "learning_rate": 5.751127945603786e-06,
      "loss": 1.0239,
      "step": 116
    },
    {
      "epoch": 0.4624505928853755,
      "grad_norm": 0.9574670791625977,
      "learning_rate": 5.68895145342319e-06,
      "loss": 1.5178,
      "step": 117
    },
    {
      "epoch": 0.466403162055336,
      "grad_norm": 0.9131107330322266,
      "learning_rate": 5.626666167821522e-06,
      "loss": 1.3872,
      "step": 118
    },
    {
      "epoch": 0.47035573122529645,
      "grad_norm": 0.9126591682434082,
      "learning_rate": 5.5642819243674085e-06,
      "loss": 1.3254,
      "step": 119
    },
    {
      "epoch": 0.4743083003952569,
      "grad_norm": 0.8607676029205322,
      "learning_rate": 5.5018085742560745e-06,
      "loss": 1.1636,
      "step": 120
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.8300676345825195,
      "learning_rate": 5.439255982753717e-06,
      "loss": 1.0787,
      "step": 121
    },
    {
      "epoch": 0.48221343873517786,
      "grad_norm": 0.8748376965522766,
      "learning_rate": 5.376634027639664e-06,
      "loss": 1.3438,
      "step": 122
    },
    {
      "epoch": 0.48616600790513836,
      "grad_norm": 0.8148254156112671,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 1.2148,
      "step": 123
    },
    {
      "epoch": 0.4901185770750988,
      "grad_norm": 0.7850709557533264,
      "learning_rate": 5.251221590898848e-06,
      "loss": 1.1715,
      "step": 124
    },
    {
      "epoch": 0.49407114624505927,
      "grad_norm": 0.8794577717781067,
      "learning_rate": 5.188450913349674e-06,
      "loss": 1.1467,
      "step": 125
    },
    {
      "epoch": 0.4980237154150198,
      "grad_norm": 0.8375518321990967,
      "learning_rate": 5.1256504772166885e-06,
      "loss": 1.2558,
      "step": 126
    },
    {
      "epoch": 0.5019762845849802,
      "grad_norm": 0.7941477298736572,
      "learning_rate": 5.062830199416764e-06,
      "loss": 1.0128,
      "step": 127
    },
    {
      "epoch": 0.5059288537549407,
      "grad_norm": 0.9250499606132507,
      "learning_rate": 5e-06,
      "loss": 1.2622,
      "step": 128
    },
    {
      "epoch": 0.5098814229249012,
      "grad_norm": 0.9209011793136597,
      "learning_rate": 4.937169800583237e-06,
      "loss": 1.3989,
      "step": 129
    },
    {
      "epoch": 0.5138339920948617,
      "grad_norm": 0.8219020962715149,
      "learning_rate": 4.874349522783313e-06,
      "loss": 1.1264,
      "step": 130
    },
    {
      "epoch": 0.5138339920948617,
      "eval_loss": 1.1763263940811157,
      "eval_runtime": 0.6328,
      "eval_samples_per_second": 33.184,
      "eval_steps_per_second": 4.741,
      "step": 130
    },
    {
      "epoch": 0.5177865612648221,
      "grad_norm": 0.9172279238700867,
      "learning_rate": 4.811549086650327e-06,
      "loss": 1.2868,
      "step": 131
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.8297377228736877,
      "learning_rate": 4.748778409101153e-06,
      "loss": 1.221,
      "step": 132
    },
    {
      "epoch": 0.525691699604743,
      "grad_norm": 0.8089572787284851,
      "learning_rate": 4.686047402353433e-06,
      "loss": 1.2466,
      "step": 133
    },
    {
      "epoch": 0.5296442687747036,
      "grad_norm": 0.8571174144744873,
      "learning_rate": 4.6233659723603374e-06,
      "loss": 1.3095,
      "step": 134
    },
    {
      "epoch": 0.5335968379446641,
      "grad_norm": 0.9645123481750488,
      "learning_rate": 4.560744017246284e-06,
      "loss": 1.4281,
      "step": 135
    },
    {
      "epoch": 0.5375494071146245,
      "grad_norm": 0.8215659856796265,
      "learning_rate": 4.4981914257439254e-06,
      "loss": 1.1636,
      "step": 136
    },
    {
      "epoch": 0.541501976284585,
      "grad_norm": 0.8466573357582092,
      "learning_rate": 4.4357180756325915e-06,
      "loss": 1.2409,
      "step": 137
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.8330338597297668,
      "learning_rate": 4.373333832178478e-06,
      "loss": 1.1857,
      "step": 138
    },
    {
      "epoch": 0.549407114624506,
      "grad_norm": 0.8727869987487793,
      "learning_rate": 4.31104854657681e-06,
      "loss": 1.1947,
      "step": 139
    },
    {
      "epoch": 0.5533596837944664,
      "grad_norm": 0.8822157979011536,
      "learning_rate": 4.248872054396215e-06,
      "loss": 1.1367,
      "step": 140
    },
    {
      "epoch": 0.5573122529644269,
      "grad_norm": 0.876277506351471,
      "learning_rate": 4.186814174025582e-06,
      "loss": 1.1754,
      "step": 141
    },
    {
      "epoch": 0.5612648221343873,
      "grad_norm": 0.8091803789138794,
      "learning_rate": 4.124884705123619e-06,
      "loss": 1.1789,
      "step": 142
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.9175235629081726,
      "learning_rate": 4.063093427071376e-06,
      "loss": 1.2189,
      "step": 143
    },
    {
      "epoch": 0.5691699604743083,
      "grad_norm": 0.8601986765861511,
      "learning_rate": 4.001450097427965e-06,
      "loss": 1.3021,
      "step": 144
    },
    {
      "epoch": 0.5731225296442688,
      "grad_norm": 0.821972668170929,
      "learning_rate": 3.939964450389728e-06,
      "loss": 1.2536,
      "step": 145
    },
    {
      "epoch": 0.5770750988142292,
      "grad_norm": 0.8965577483177185,
      "learning_rate": 3.8786461952530955e-06,
      "loss": 1.2669,
      "step": 146
    },
    {
      "epoch": 0.5810276679841897,
      "grad_norm": 0.8901940584182739,
      "learning_rate": 3.817505014881378e-06,
      "loss": 1.2246,
      "step": 147
    },
    {
      "epoch": 0.5849802371541502,
      "grad_norm": 0.8637762069702148,
      "learning_rate": 3.756550564175727e-06,
      "loss": 1.2705,
      "step": 148
    },
    {
      "epoch": 0.5889328063241107,
      "grad_norm": 0.8907751441001892,
      "learning_rate": 3.695792468550517e-06,
      "loss": 1.3191,
      "step": 149
    },
    {
      "epoch": 0.5928853754940712,
      "grad_norm": 0.9000714421272278,
      "learning_rate": 3.635240322413375e-06,
      "loss": 1.3388,
      "step": 150
    },
    {
      "epoch": 0.5968379446640316,
      "grad_norm": 0.8116331696510315,
      "learning_rate": 3.5749036876501196e-06,
      "loss": 1.2169,
      "step": 151
    },
    {
      "epoch": 0.6007905138339921,
      "grad_norm": 0.9376166462898254,
      "learning_rate": 3.5147920921148267e-06,
      "loss": 1.4159,
      "step": 152
    },
    {
      "epoch": 0.6047430830039525,
      "grad_norm": 0.8815961480140686,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 1.3918,
      "step": 153
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.8155955672264099,
      "learning_rate": 3.3952819509639534e-06,
      "loss": 1.0842,
      "step": 154
    },
    {
      "epoch": 0.6126482213438735,
      "grad_norm": 0.8554919958114624,
      "learning_rate": 3.3359022773850673e-06,
      "loss": 1.3536,
      "step": 155
    },
    {
      "epoch": 0.616600790513834,
      "grad_norm": 0.8661870956420898,
      "learning_rate": 3.2767853841274154e-06,
      "loss": 1.1721,
      "step": 156
    },
    {
      "epoch": 0.616600790513834,
      "eval_loss": 1.1584229469299316,
      "eval_runtime": 0.6329,
      "eval_samples_per_second": 33.182,
      "eval_steps_per_second": 4.74,
      "step": 156
    },
    {
      "epoch": 0.6205533596837944,
      "grad_norm": 0.8114671111106873,
      "learning_rate": 3.217940606433747e-06,
      "loss": 1.0664,
      "step": 157
    },
    {
      "epoch": 0.6245059288537549,
      "grad_norm": 0.863220751285553,
      "learning_rate": 3.1593772365766107e-06,
      "loss": 1.2761,
      "step": 158
    },
    {
      "epoch": 0.6284584980237155,
      "grad_norm": 0.8586646318435669,
      "learning_rate": 3.1011045223909954e-06,
      "loss": 1.2633,
      "step": 159
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 0.8601418137550354,
      "learning_rate": 3.043131665813988e-06,
      "loss": 1.2919,
      "step": 160
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.8035183548927307,
      "learning_rate": 2.9854678214316875e-06,
      "loss": 1.1463,
      "step": 161
    },
    {
      "epoch": 0.6403162055335968,
      "grad_norm": 0.8140465021133423,
      "learning_rate": 2.92812209503358e-06,
      "loss": 1.0966,
      "step": 162
    },
    {
      "epoch": 0.6442687747035574,
      "grad_norm": 0.8538705706596375,
      "learning_rate": 2.871103542174637e-06,
      "loss": 1.2748,
      "step": 163
    },
    {
      "epoch": 0.6482213438735178,
      "grad_norm": 0.8856031894683838,
      "learning_rate": 2.814421166745337e-06,
      "loss": 1.3632,
      "step": 164
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.8147869110107422,
      "learning_rate": 2.7580839195498397e-06,
      "loss": 1.1984,
      "step": 165
    },
    {
      "epoch": 0.6561264822134387,
      "grad_norm": 0.9556436538696289,
      "learning_rate": 2.7021006968925613e-06,
      "loss": 1.5325,
      "step": 166
    },
    {
      "epoch": 0.6600790513833992,
      "grad_norm": 0.8936392664909363,
      "learning_rate": 2.646480339173337e-06,
      "loss": 1.4192,
      "step": 167
    },
    {
      "epoch": 0.6640316205533597,
      "grad_norm": 0.8458386063575745,
      "learning_rate": 2.5912316294914232e-06,
      "loss": 1.2821,
      "step": 168
    },
    {
      "epoch": 0.6679841897233202,
      "grad_norm": 0.9311079382896423,
      "learning_rate": 2.536363292258543e-06,
      "loss": 1.3371,
      "step": 169
    },
    {
      "epoch": 0.6719367588932806,
      "grad_norm": 0.8807729482650757,
      "learning_rate": 2.4818839918211963e-06,
      "loss": 1.2789,
      "step": 170
    },
    {
      "epoch": 0.6758893280632411,
      "grad_norm": 0.8326642513275146,
      "learning_rate": 2.4278023310924676e-06,
      "loss": 1.2545,
      "step": 171
    },
    {
      "epoch": 0.6798418972332015,
      "grad_norm": 0.7561216950416565,
      "learning_rate": 2.3741268501935212e-06,
      "loss": 0.9872,
      "step": 172
    },
    {
      "epoch": 0.6837944664031621,
      "grad_norm": 0.9049252867698669,
      "learning_rate": 2.320866025105016e-06,
      "loss": 1.0876,
      "step": 173
    },
    {
      "epoch": 0.6877470355731226,
      "grad_norm": 0.8050791621208191,
      "learning_rate": 2.268028266328655e-06,
      "loss": 1.2257,
      "step": 174
    },
    {
      "epoch": 0.691699604743083,
      "grad_norm": 0.7893306016921997,
      "learning_rate": 2.2156219175590623e-06,
      "loss": 1.1499,
      "step": 175
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.8402442336082458,
      "learning_rate": 2.1636552543662187e-06,
      "loss": 1.3324,
      "step": 176
    },
    {
      "epoch": 0.6996047430830039,
      "grad_norm": 0.847458004951477,
      "learning_rate": 2.112136482888663e-06,
      "loss": 1.3478,
      "step": 177
    },
    {
      "epoch": 0.7035573122529645,
      "grad_norm": 0.8522107601165771,
      "learning_rate": 2.061073738537635e-06,
      "loss": 1.2586,
      "step": 178
    },
    {
      "epoch": 0.7075098814229249,
      "grad_norm": 0.8222721219062805,
      "learning_rate": 2.0104750847124075e-06,
      "loss": 1.2455,
      "step": 179
    },
    {
      "epoch": 0.7114624505928854,
      "grad_norm": 0.8545589447021484,
      "learning_rate": 1.9603485115269743e-06,
      "loss": 1.2892,
      "step": 180
    },
    {
      "epoch": 0.7154150197628458,
      "grad_norm": 0.7990689873695374,
      "learning_rate": 1.910701934548329e-06,
      "loss": 1.1216,
      "step": 181
    },
    {
      "epoch": 0.7193675889328063,
      "grad_norm": 0.8381747007369995,
      "learning_rate": 1.8615431935464984e-06,
      "loss": 1.2738,
      "step": 182
    },
    {
      "epoch": 0.7193675889328063,
      "eval_loss": 1.1467477083206177,
      "eval_runtime": 0.6308,
      "eval_samples_per_second": 33.29,
      "eval_steps_per_second": 4.756,
      "step": 182
    },
    {
      "epoch": 0.7233201581027668,
      "grad_norm": 0.8528211712837219,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 1.3237,
      "step": 183
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.8386929035186768,
      "learning_rate": 1.7647201921527802e-06,
      "loss": 1.1454,
      "step": 184
    },
    {
      "epoch": 0.7312252964426877,
      "grad_norm": 0.9228261709213257,
      "learning_rate": 1.7170712212352187e-06,
      "loss": 1.5128,
      "step": 185
    },
    {
      "epoch": 0.7351778656126482,
      "grad_norm": 0.763982892036438,
      "learning_rate": 1.6699406628287423e-06,
      "loss": 0.9779,
      "step": 186
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.9443770051002502,
      "learning_rate": 1.6233359593948777e-06,
      "loss": 0.9658,
      "step": 187
    },
    {
      "epoch": 0.7430830039525692,
      "grad_norm": 0.8337656855583191,
      "learning_rate": 1.5772644703565564e-06,
      "loss": 1.2752,
      "step": 188
    },
    {
      "epoch": 0.7470355731225297,
      "grad_norm": 0.8052669763565063,
      "learning_rate": 1.531733470935976e-06,
      "loss": 1.1755,
      "step": 189
    },
    {
      "epoch": 0.7509881422924901,
      "grad_norm": 0.8237268328666687,
      "learning_rate": 1.4867501510057548e-06,
      "loss": 1.1529,
      "step": 190
    },
    {
      "epoch": 0.7549407114624506,
      "grad_norm": 0.8448726534843445,
      "learning_rate": 1.4423216139535735e-06,
      "loss": 1.2361,
      "step": 191
    },
    {
      "epoch": 0.758893280632411,
      "grad_norm": 0.8243027329444885,
      "learning_rate": 1.3984548755604655e-06,
      "loss": 1.2842,
      "step": 192
    },
    {
      "epoch": 0.7628458498023716,
      "grad_norm": 0.8658849000930786,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 1.256,
      "step": 193
    },
    {
      "epoch": 0.766798418972332,
      "grad_norm": 0.8200253248214722,
      "learning_rate": 1.312434413209131e-06,
      "loss": 1.1356,
      "step": 194
    },
    {
      "epoch": 0.7707509881422925,
      "grad_norm": 0.8177831768989563,
      "learning_rate": 1.2702942728790897e-06,
      "loss": 1.151,
      "step": 195
    },
    {
      "epoch": 0.7747035573122529,
      "grad_norm": 0.8590410351753235,
      "learning_rate": 1.2287430963194807e-06,
      "loss": 1.3267,
      "step": 196
    },
    {
      "epoch": 0.7786561264822134,
      "grad_norm": 0.8247159719467163,
      "learning_rate": 1.18778744494276e-06,
      "loss": 1.1943,
      "step": 197
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.9330562949180603,
      "learning_rate": 1.1474337861210543e-06,
      "loss": 1.4392,
      "step": 198
    },
    {
      "epoch": 0.7865612648221344,
      "grad_norm": 0.8507537841796875,
      "learning_rate": 1.1076884921648834e-06,
      "loss": 1.2678,
      "step": 199
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 0.8290367126464844,
      "learning_rate": 1.0685578393169054e-06,
      "loss": 1.2738,
      "step": 200
    },
    {
      "epoch": 0.7944664031620553,
      "grad_norm": 0.8783449530601501,
      "learning_rate": 1.0300480067608232e-06,
      "loss": 1.4097,
      "step": 201
    },
    {
      "epoch": 0.7984189723320159,
      "grad_norm": 0.8614851236343384,
      "learning_rate": 9.921650756456164e-07,
      "loss": 1.1463,
      "step": 202
    },
    {
      "epoch": 0.8023715415019763,
      "grad_norm": 0.8946048617362976,
      "learning_rate": 9.549150281252633e-07,
      "loss": 1.3288,
      "step": 203
    },
    {
      "epoch": 0.8063241106719368,
      "grad_norm": 0.8253918290138245,
      "learning_rate": 9.183037464140804e-07,
      "loss": 1.1852,
      "step": 204
    },
    {
      "epoch": 0.8102766798418972,
      "grad_norm": 0.8394426107406616,
      "learning_rate": 8.823370118578628e-07,
      "loss": 1.2328,
      "step": 205
    },
    {
      "epoch": 0.8142292490118577,
      "grad_norm": 0.7891396880149841,
      "learning_rate": 8.470205040209362e-07,
      "loss": 1.2409,
      "step": 206
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.8969730138778687,
      "learning_rate": 8.123597997892918e-07,
      "loss": 1.4195,
      "step": 207
    },
    {
      "epoch": 0.8221343873517787,
      "grad_norm": 0.7859252095222473,
      "learning_rate": 7.783603724899258e-07,
      "loss": 1.1729,
      "step": 208
    },
    {
      "epoch": 0.8221343873517787,
      "eval_loss": 1.1414591073989868,
      "eval_runtime": 0.63,
      "eval_samples_per_second": 33.334,
      "eval_steps_per_second": 4.762,
      "step": 208
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.8004709482192993,
      "learning_rate": 7.450275910265415e-07,
      "loss": 1.1787,
      "step": 209
    },
    {
      "epoch": 0.8300395256916996,
      "grad_norm": 0.8863723874092102,
      "learning_rate": 7.123667190317396e-07,
      "loss": 1.3486,
      "step": 210
    },
    {
      "epoch": 0.83399209486166,
      "grad_norm": 0.7677893042564392,
      "learning_rate": 6.803829140358237e-07,
      "loss": 1.2067,
      "step": 211
    },
    {
      "epoch": 0.8379446640316206,
      "grad_norm": 0.7935658097267151,
      "learning_rate": 6.490812266523716e-07,
      "loss": 1.0929,
      "step": 212
    },
    {
      "epoch": 0.841897233201581,
      "grad_norm": 0.7727168798446655,
      "learning_rate": 6.184665997806832e-07,
      "loss": 1.0544,
      "step": 213
    },
    {
      "epoch": 0.8458498023715415,
      "grad_norm": 0.8302650451660156,
      "learning_rate": 5.885438678252342e-07,
      "loss": 1.2409,
      "step": 214
    },
    {
      "epoch": 0.849802371541502,
      "grad_norm": 0.8888508081436157,
      "learning_rate": 5.593177559322776e-07,
      "loss": 1.3816,
      "step": 215
    },
    {
      "epoch": 0.8537549407114624,
      "grad_norm": 0.76105135679245,
      "learning_rate": 5.307928792436812e-07,
      "loss": 1.0972,
      "step": 216
    },
    {
      "epoch": 0.857707509881423,
      "grad_norm": 0.8869984149932861,
      "learning_rate": 5.029737421681446e-07,
      "loss": 1.3786,
      "step": 217
    },
    {
      "epoch": 0.8616600790513834,
      "grad_norm": 0.8762255907058716,
      "learning_rate": 4.758647376699033e-07,
      "loss": 1.3592,
      "step": 218
    },
    {
      "epoch": 0.8656126482213439,
      "grad_norm": 0.8182483911514282,
      "learning_rate": 4.494701465750217e-07,
      "loss": 1.3265,
      "step": 219
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.8035054206848145,
      "learning_rate": 4.237941368954124e-07,
      "loss": 1.1705,
      "step": 220
    },
    {
      "epoch": 0.8735177865612648,
      "grad_norm": 0.8334324359893799,
      "learning_rate": 3.9884076317064813e-07,
      "loss": 1.2725,
      "step": 221
    },
    {
      "epoch": 0.8774703557312253,
      "grad_norm": 0.8486202955245972,
      "learning_rate": 3.7461396582771035e-07,
      "loss": 1.2205,
      "step": 222
    },
    {
      "epoch": 0.8814229249011858,
      "grad_norm": 0.8365004658699036,
      "learning_rate": 3.511175705587433e-07,
      "loss": 1.2246,
      "step": 223
    },
    {
      "epoch": 0.8853754940711462,
      "grad_norm": 0.7247976660728455,
      "learning_rate": 3.283552877169399e-07,
      "loss": 1.0818,
      "step": 224
    },
    {
      "epoch": 0.8893280632411067,
      "grad_norm": 0.9177906513214111,
      "learning_rate": 3.0633071173062966e-07,
      "loss": 1.328,
      "step": 225
    },
    {
      "epoch": 0.8932806324110671,
      "grad_norm": 0.8105781078338623,
      "learning_rate": 2.850473205356774e-07,
      "loss": 1.0848,
      "step": 226
    },
    {
      "epoch": 0.8972332015810277,
      "grad_norm": 0.8612114191055298,
      "learning_rate": 2.6450847502627883e-07,
      "loss": 1.3192,
      "step": 227
    },
    {
      "epoch": 0.9011857707509882,
      "grad_norm": 0.8288993239402771,
      "learning_rate": 2.447174185242324e-07,
      "loss": 1.2458,
      "step": 228
    },
    {
      "epoch": 0.9051383399209486,
      "grad_norm": 0.8506494760513306,
      "learning_rate": 2.2567727626678527e-07,
      "loss": 1.2568,
      "step": 229
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.9084119200706482,
      "learning_rate": 2.0739105491312028e-07,
      "loss": 1.4233,
      "step": 230
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.9303674101829529,
      "learning_rate": 1.8986164206957037e-07,
      "loss": 1.3435,
      "step": 231
    },
    {
      "epoch": 0.9169960474308301,
      "grad_norm": 0.8007397055625916,
      "learning_rate": 1.7309180583363062e-07,
      "loss": 1.1919,
      "step": 232
    },
    {
      "epoch": 0.9209486166007905,
      "grad_norm": 0.7730187177658081,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 1.0833,
      "step": 233
    },
    {
      "epoch": 0.924901185770751,
      "grad_norm": 0.9434295296669006,
      "learning_rate": 1.4184133542663014e-07,
      "loss": 1.4446,
      "step": 234
    },
    {
      "epoch": 0.924901185770751,
      "eval_loss": 1.1398719549179077,
      "eval_runtime": 0.6371,
      "eval_samples_per_second": 32.96,
      "eval_steps_per_second": 4.709,
      "step": 234
    },
    {
      "epoch": 0.9288537549407114,
      "grad_norm": 0.8378840684890747,
      "learning_rate": 1.2736563606711384e-07,
      "loss": 1.3058,
      "step": 235
    },
    {
      "epoch": 0.932806324110672,
      "grad_norm": 0.7894282341003418,
      "learning_rate": 1.136593821590326e-07,
      "loss": 1.1822,
      "step": 236
    },
    {
      "epoch": 0.9367588932806324,
      "grad_norm": 0.8614757657051086,
      "learning_rate": 1.007247380787657e-07,
      "loss": 1.2477,
      "step": 237
    },
    {
      "epoch": 0.9407114624505929,
      "grad_norm": 0.7437376976013184,
      "learning_rate": 8.856374635655696e-08,
      "loss": 0.9579,
      "step": 238
    },
    {
      "epoch": 0.9446640316205533,
      "grad_norm": 0.8177477717399597,
      "learning_rate": 7.717832735397335e-08,
      "loss": 1.2895,
      "step": 239
    },
    {
      "epoch": 0.9486166007905138,
      "grad_norm": 0.8371565937995911,
      "learning_rate": 6.657027896065982e-08,
      "loss": 1.2901,
      "step": 240
    },
    {
      "epoch": 0.9525691699604744,
      "grad_norm": 0.8062224388122559,
      "learning_rate": 5.674127631043025e-08,
      "loss": 1.1185,
      "step": 241
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.782124936580658,
      "learning_rate": 4.769287151674407e-08,
      "loss": 1.1315,
      "step": 242
    },
    {
      "epoch": 0.9604743083003953,
      "grad_norm": 0.8169525265693665,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 1.3511,
      "step": 243
    },
    {
      "epoch": 0.9644268774703557,
      "grad_norm": 0.791191577911377,
      "learning_rate": 3.194344739995803e-08,
      "loss": 1.2501,
      "step": 244
    },
    {
      "epoch": 0.9683794466403162,
      "grad_norm": 0.7813810706138611,
      "learning_rate": 2.5244915093499134e-08,
      "loss": 1.1408,
      "step": 245
    },
    {
      "epoch": 0.9723320158102767,
      "grad_norm": 0.8077353239059448,
      "learning_rate": 1.9331954284137476e-08,
      "loss": 1.2169,
      "step": 246
    },
    {
      "epoch": 0.9762845849802372,
      "grad_norm": 0.8798792362213135,
      "learning_rate": 1.4205498696930332e-08,
      "loss": 1.4156,
      "step": 247
    },
    {
      "epoch": 0.9802371541501976,
      "grad_norm": 0.7928077578544617,
      "learning_rate": 9.866357858642206e-09,
      "loss": 1.1922,
      "step": 248
    },
    {
      "epoch": 0.9841897233201581,
      "grad_norm": 0.8758398294448853,
      "learning_rate": 6.315216969912663e-09,
      "loss": 1.4098,
      "step": 249
    },
    {
      "epoch": 0.9881422924901185,
      "grad_norm": 0.8929165005683899,
      "learning_rate": 3.5526367970539765e-09,
      "loss": 1.3601,
      "step": 250
    },
    {
      "epoch": 0.9920948616600791,
      "grad_norm": 0.9001562595367432,
      "learning_rate": 1.5790535835003006e-09,
      "loss": 1.2039,
      "step": 251
    },
    {
      "epoch": 0.9960474308300395,
      "grad_norm": 0.8405194878578186,
      "learning_rate": 3.9477898091944135e-10,
      "loss": 1.1514,
      "step": 252
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8833491206169128,
      "learning_rate": 0.0,
      "loss": 1.2887,
      "step": 253
    },
    {
      "epoch": 1.0,
      "step": 253,
      "total_flos": 8.443588829301965e+16,
      "train_loss": 1.3333067849219553,
      "train_runtime": 1520.8803,
      "train_samples_per_second": 1.329,
      "train_steps_per_second": 0.166
    }
  ],
  "logging_steps": 1,
  "max_steps": 253,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 253,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.443588829301965e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}