{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6066481994459834,
  "eval_steps": 37,
  "global_step": 219,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002770083102493075,
      "grad_norm": 0.9076941366015471,
      "learning_rate": 2.5e-06,
      "loss": 1.1945,
      "step": 1
    },
    {
      "epoch": 0.002770083102493075,
      "eval_loss": 1.0296825170516968,
      "eval_runtime": 104.9654,
      "eval_samples_per_second": 0.953,
      "eval_steps_per_second": 0.238,
      "step": 1
    },
    {
      "epoch": 0.00554016620498615,
      "grad_norm": 1.0344272252302953,
      "learning_rate": 5e-06,
      "loss": 1.3385,
      "step": 2
    },
    {
      "epoch": 0.008310249307479225,
      "grad_norm": 1.0977608192145218,
      "learning_rate": 7.5e-06,
      "loss": 1.3767,
      "step": 3
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.8895382737806115,
      "learning_rate": 1e-05,
      "loss": 1.1881,
      "step": 4
    },
    {
      "epoch": 0.013850415512465374,
      "grad_norm": 0.958710062908987,
      "learning_rate": 1.25e-05,
      "loss": 1.2936,
      "step": 5
    },
    {
      "epoch": 0.01662049861495845,
      "grad_norm": 0.8447951280142822,
      "learning_rate": 1.5e-05,
      "loss": 1.1547,
      "step": 6
    },
    {
      "epoch": 0.019390581717451522,
      "grad_norm": 0.8794765482094637,
      "learning_rate": 1.75e-05,
      "loss": 1.3444,
      "step": 7
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 0.8437125997364887,
      "learning_rate": 2e-05,
      "loss": 1.2765,
      "step": 8
    },
    {
      "epoch": 0.024930747922437674,
      "grad_norm": 0.7276844901691898,
      "learning_rate": 2.25e-05,
      "loss": 1.2031,
      "step": 9
    },
    {
      "epoch": 0.027700831024930747,
      "grad_norm": 0.577477596526854,
      "learning_rate": 2.5e-05,
      "loss": 1.1725,
      "step": 10
    },
    {
      "epoch": 0.030470914127423823,
      "grad_norm": 0.4618405348091677,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 1.1008,
      "step": 11
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 0.3671423964001518,
      "learning_rate": 3e-05,
      "loss": 1.0963,
      "step": 12
    },
    {
      "epoch": 0.036011080332409975,
      "grad_norm": 0.4139651359524478,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 1.2831,
      "step": 13
    },
    {
      "epoch": 0.038781163434903045,
      "grad_norm": 0.4364185358505406,
      "learning_rate": 3.5e-05,
      "loss": 1.0524,
      "step": 14
    },
    {
      "epoch": 0.04155124653739612,
      "grad_norm": 0.5116601253143136,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.1499,
      "step": 15
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 0.5236113301724862,
      "learning_rate": 4e-05,
      "loss": 1.1466,
      "step": 16
    },
    {
      "epoch": 0.04709141274238227,
      "grad_norm": 0.4606756443741647,
      "learning_rate": 4.25e-05,
      "loss": 1.1385,
      "step": 17
    },
    {
      "epoch": 0.04986149584487535,
      "grad_norm": 0.3991457405979455,
      "learning_rate": 4.5e-05,
      "loss": 1.108,
      "step": 18
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 1.8553548238184947,
      "learning_rate": 4.75e-05,
      "loss": 0.9794,
      "step": 19
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.31912881369455715,
      "learning_rate": 5e-05,
      "loss": 1.1583,
      "step": 20
    },
    {
      "epoch": 0.05817174515235457,
      "grad_norm": 0.3315962832679952,
      "learning_rate": 4.999904513837887e-05,
      "loss": 1.1927,
      "step": 21
    },
    {
      "epoch": 0.060941828254847646,
      "grad_norm": 0.3081653717373631,
      "learning_rate": 4.999618063456087e-05,
      "loss": 1.1666,
      "step": 22
    },
    {
      "epoch": 0.06371191135734072,
      "grad_norm": 0.2386753107269311,
      "learning_rate": 4.999140673167533e-05,
      "loss": 1.1517,
      "step": 23
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": 0.20460753812847132,
      "learning_rate": 4.998472383491481e-05,
      "loss": 1.1475,
      "step": 24
    },
    {
      "epoch": 0.06925207756232687,
      "grad_norm": 0.19426749294122878,
      "learning_rate": 4.997613251150082e-05,
      "loss": 1.0427,
      "step": 25
    },
    {
      "epoch": 0.07202216066481995,
      "grad_norm": 0.16821147486362656,
      "learning_rate": 4.996563349063557e-05,
      "loss": 1.1392,
      "step": 26
    },
    {
      "epoch": 0.07479224376731301,
      "grad_norm": 0.16476251779742826,
      "learning_rate": 4.995322766344013e-05,
      "loss": 1.0624,
      "step": 27
    },
    {
      "epoch": 0.07756232686980609,
      "grad_norm": 0.14974022119841934,
      "learning_rate": 4.993891608287879e-05,
      "loss": 1.0357,
      "step": 28
    },
    {
      "epoch": 0.08033240997229917,
      "grad_norm": 0.18664906507712956,
      "learning_rate": 4.992269996366969e-05,
      "loss": 1.0724,
      "step": 29
    },
    {
      "epoch": 0.08310249307479224,
      "grad_norm": 0.1850945977027583,
      "learning_rate": 4.990458068218171e-05,
      "loss": 1.1334,
      "step": 30
    },
    {
      "epoch": 0.08587257617728532,
      "grad_norm": 0.18423955915331258,
      "learning_rate": 4.9884559776317644e-05,
      "loss": 1.1707,
      "step": 31
    },
    {
      "epoch": 0.0886426592797784,
      "grad_norm": 0.17778624557198042,
      "learning_rate": 4.9862638945383674e-05,
      "loss": 1.0923,
      "step": 32
    },
    {
      "epoch": 0.09141274238227147,
      "grad_norm": 0.18753159302589986,
      "learning_rate": 4.983882004994517e-05,
      "loss": 1.0743,
      "step": 33
    },
    {
      "epoch": 0.09418282548476455,
      "grad_norm": 0.16951133250798278,
      "learning_rate": 4.98131051116687e-05,
      "loss": 1.0776,
      "step": 34
    },
    {
      "epoch": 0.09695290858725762,
      "grad_norm": 0.15767321847790128,
      "learning_rate": 4.9785496313150515e-05,
      "loss": 1.0987,
      "step": 35
    },
    {
      "epoch": 0.0997229916897507,
      "grad_norm": 0.162961453637477,
      "learning_rate": 4.975599599773124e-05,
      "loss": 1.2561,
      "step": 36
    },
    {
      "epoch": 0.10249307479224377,
      "grad_norm": 0.15327784219657248,
      "learning_rate": 4.972460666929699e-05,
      "loss": 1.1456,
      "step": 37
    },
    {
      "epoch": 0.10249307479224377,
      "eval_loss": 0.7954654693603516,
      "eval_runtime": 105.8629,
      "eval_samples_per_second": 0.945,
      "eval_steps_per_second": 0.236,
      "step": 37
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.17503484326795066,
      "learning_rate": 4.969133099206691e-05,
      "loss": 1.1647,
      "step": 38
    },
    {
      "epoch": 0.10803324099722991,
      "grad_norm": 0.1616243718822839,
      "learning_rate": 4.965617179036695e-05,
      "loss": 1.0552,
      "step": 39
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.14651727257725808,
      "learning_rate": 4.96191320483902e-05,
      "loss": 0.9286,
      "step": 40
    },
    {
      "epoch": 0.11357340720221606,
      "grad_norm": 0.16761163260684342,
      "learning_rate": 4.958021490994361e-05,
      "loss": 1.0554,
      "step": 41
    },
    {
      "epoch": 0.11634349030470914,
      "grad_norm": 0.18422943695103963,
      "learning_rate": 4.953942367818113e-05,
      "loss": 1.1106,
      "step": 42
    },
    {
      "epoch": 0.11911357340720222,
      "grad_norm": 0.1473247570248768,
      "learning_rate": 4.9496761815323344e-05,
      "loss": 1.2059,
      "step": 43
    },
    {
      "epoch": 0.12188365650969529,
      "grad_norm": 0.14787258143002216,
      "learning_rate": 4.9452232942363634e-05,
      "loss": 1.1916,
      "step": 44
    },
    {
      "epoch": 0.12465373961218837,
      "grad_norm": 0.13340848225076712,
      "learning_rate": 4.940584083876084e-05,
      "loss": 1.0421,
      "step": 45
    },
    {
      "epoch": 0.12742382271468145,
      "grad_norm": 0.15834348128625553,
      "learning_rate": 4.935758944211844e-05,
      "loss": 1.0782,
      "step": 46
    },
    {
      "epoch": 0.13019390581717452,
      "grad_norm": 0.14100327469205548,
      "learning_rate": 4.9307482847850374e-05,
      "loss": 1.03,
      "step": 47
    },
    {
      "epoch": 0.1329639889196676,
      "grad_norm": 0.18919634141556568,
      "learning_rate": 4.925552530883343e-05,
      "loss": 1.0422,
      "step": 48
    },
    {
      "epoch": 0.13573407202216067,
      "grad_norm": 0.15121560590293795,
      "learning_rate": 4.9201721235046274e-05,
      "loss": 0.9852,
      "step": 49
    },
    {
      "epoch": 0.13850415512465375,
      "grad_norm": 0.14628904242090288,
      "learning_rate": 4.914607519319512e-05,
      "loss": 1.1146,
      "step": 50
    },
    {
      "epoch": 0.14127423822714683,
      "grad_norm": 0.13794163183547553,
      "learning_rate": 4.90885919063262e-05,
      "loss": 1.0787,
      "step": 51
    },
    {
      "epoch": 0.1440443213296399,
      "grad_norm": 0.13302301409932443,
      "learning_rate": 4.902927625342476e-05,
      "loss": 1.0993,
      "step": 52
    },
    {
      "epoch": 0.14681440443213298,
      "grad_norm": 0.14124480977262469,
      "learning_rate": 4.8968133269001096e-05,
      "loss": 1.0137,
      "step": 53
    },
    {
      "epoch": 0.14958448753462603,
      "grad_norm": 0.14791504265910085,
      "learning_rate": 4.890516814266314e-05,
      "loss": 1.1663,
      "step": 54
    },
    {
      "epoch": 0.1523545706371191,
      "grad_norm": 0.13506987447877156,
      "learning_rate": 4.884038621867599e-05,
      "loss": 0.9941,
      "step": 55
    },
    {
      "epoch": 0.15512465373961218,
      "grad_norm": 0.14611198065865885,
      "learning_rate": 4.877379299550838e-05,
      "loss": 0.9958,
      "step": 56
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.16481726483113354,
      "learning_rate": 4.8705394125365884e-05,
      "loss": 1.1329,
      "step": 57
    },
    {
      "epoch": 0.16066481994459833,
      "grad_norm": 0.1498291481940627,
      "learning_rate": 4.8635195413711286e-05,
      "loss": 1.058,
      "step": 58
    },
    {
      "epoch": 0.1634349030470914,
      "grad_norm": 0.15057001184388058,
      "learning_rate": 4.8563202818771735e-05,
      "loss": 1.1062,
      "step": 59
    },
    {
      "epoch": 0.16620498614958448,
      "grad_norm": 0.12916512409429184,
      "learning_rate": 4.84894224510331e-05,
      "loss": 1.0769,
      "step": 60
    },
    {
      "epoch": 0.16897506925207756,
      "grad_norm": 0.13775185913237034,
      "learning_rate": 4.841386057272129e-05,
      "loss": 0.9624,
      "step": 61
    },
    {
      "epoch": 0.17174515235457063,
      "grad_norm": 0.1447222703266104,
      "learning_rate": 4.8336523597270765e-05,
      "loss": 0.9653,
      "step": 62
    },
    {
      "epoch": 0.1745152354570637,
      "grad_norm": 0.20538147828946965,
      "learning_rate": 4.825741808878017e-05,
      "loss": 0.9674,
      "step": 63
    },
    {
      "epoch": 0.1772853185595568,
      "grad_norm": 0.15455976822474854,
      "learning_rate": 4.8176550761455195e-05,
      "loss": 1.1488,
      "step": 64
    },
    {
      "epoch": 0.18005540166204986,
      "grad_norm": 0.14123106112442296,
      "learning_rate": 4.8093928479038704e-05,
      "loss": 1.0781,
      "step": 65
    },
    {
      "epoch": 0.18282548476454294,
      "grad_norm": 0.153605912426132,
      "learning_rate": 4.8009558254228185e-05,
      "loss": 1.0193,
      "step": 66
    },
    {
      "epoch": 0.18559556786703602,
      "grad_norm": 0.170305518682767,
      "learning_rate": 4.792344724808048e-05,
      "loss": 1.1249,
      "step": 67
    },
    {
      "epoch": 0.1883656509695291,
      "grad_norm": 0.15808161680481964,
      "learning_rate": 4.783560276940402e-05,
      "loss": 0.9227,
      "step": 68
    },
    {
      "epoch": 0.19113573407202217,
      "grad_norm": 0.13584733997983103,
      "learning_rate": 4.7746032274138494e-05,
      "loss": 1.0205,
      "step": 69
    },
    {
      "epoch": 0.19390581717451524,
      "grad_norm": 0.152754335402458,
      "learning_rate": 4.765474336472197e-05,
      "loss": 1.1152,
      "step": 70
    },
    {
      "epoch": 0.19667590027700832,
      "grad_norm": 0.1559364062645901,
      "learning_rate": 4.7561743789445644e-05,
      "loss": 1.004,
      "step": 71
    },
    {
      "epoch": 0.1994459833795014,
      "grad_norm": 0.1601485375057651,
      "learning_rate": 4.7467041441796214e-05,
      "loss": 1.0463,
      "step": 72
    },
    {
      "epoch": 0.20221606648199447,
      "grad_norm": 0.14468865075681345,
      "learning_rate": 4.737064435978586e-05,
      "loss": 0.9536,
      "step": 73
    },
    {
      "epoch": 0.20498614958448755,
      "grad_norm": 0.32356482070883336,
      "learning_rate": 4.727256072527006e-05,
      "loss": 1.0037,
      "step": 74
    },
    {
      "epoch": 0.20498614958448755,
      "eval_loss": 0.7582282423973083,
      "eval_runtime": 105.298,
      "eval_samples_per_second": 0.95,
      "eval_steps_per_second": 0.237,
      "step": 74
    },
    {
      "epoch": 0.2077562326869806,
      "grad_norm": 0.15635524181898305,
      "learning_rate": 4.71727988632531e-05,
      "loss": 1.0651,
      "step": 75
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.15219977997190004,
      "learning_rate": 4.70713672411815e-05,
      "loss": 1.0337,
      "step": 76
    },
    {
      "epoch": 0.21329639889196675,
      "grad_norm": 0.15563741812103743,
      "learning_rate": 4.6968274468225296e-05,
      "loss": 1.0671,
      "step": 77
    },
    {
      "epoch": 0.21606648199445982,
      "grad_norm": 0.15558142374206219,
      "learning_rate": 4.686352929454739e-05,
      "loss": 1.0429,
      "step": 78
    },
    {
      "epoch": 0.2188365650969529,
      "grad_norm": 0.21330774901341568,
      "learning_rate": 4.6757140610560765e-05,
      "loss": 1.1399,
      "step": 79
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 0.15688008638487674,
      "learning_rate": 4.664911744617398e-05,
      "loss": 0.9371,
      "step": 80
    },
    {
      "epoch": 0.22437673130193905,
      "grad_norm": 0.1763095699279512,
      "learning_rate": 4.653946897002472e-05,
      "loss": 1.1098,
      "step": 81
    },
    {
      "epoch": 0.22714681440443213,
      "grad_norm": 0.1678442035216426,
      "learning_rate": 4.6428204488701576e-05,
      "loss": 1.068,
      "step": 82
    },
    {
      "epoch": 0.2299168975069252,
      "grad_norm": 0.17911858466627326,
      "learning_rate": 4.631533344595416e-05,
      "loss": 1.0096,
      "step": 83
    },
    {
      "epoch": 0.23268698060941828,
      "grad_norm": 0.23891003796307586,
      "learning_rate": 4.6200865421891496e-05,
      "loss": 1.1138,
      "step": 84
    },
    {
      "epoch": 0.23545706371191136,
      "grad_norm": 0.18872774327058275,
      "learning_rate": 4.6084810132169e-05,
      "loss": 1.0792,
      "step": 85
    },
    {
      "epoch": 0.23822714681440443,
      "grad_norm": 0.1692018308326617,
      "learning_rate": 4.596717742716372e-05,
      "loss": 0.9956,
      "step": 86
    },
    {
      "epoch": 0.2409972299168975,
      "grad_norm": 0.18114487653466307,
      "learning_rate": 4.5847977291138366e-05,
      "loss": 1.0282,
      "step": 87
    },
    {
      "epoch": 0.24376731301939059,
      "grad_norm": 0.1874960678295754,
      "learning_rate": 4.5727219841393846e-05,
      "loss": 0.9019,
      "step": 88
    },
    {
      "epoch": 0.24653739612188366,
      "grad_norm": 0.15508335823487335,
      "learning_rate": 4.560491532741053e-05,
      "loss": 0.7839,
      "step": 89
    },
    {
      "epoch": 0.24930747922437674,
      "grad_norm": 0.17507231249024333,
      "learning_rate": 4.548107412997833e-05,
      "loss": 0.9396,
      "step": 90
    },
    {
      "epoch": 0.2520775623268698,
      "grad_norm": 0.18664452466447212,
      "learning_rate": 4.53557067603156e-05,
      "loss": 0.9874,
      "step": 91
    },
    {
      "epoch": 0.2548476454293629,
      "grad_norm": 0.19573327857302514,
      "learning_rate": 4.522882385917699e-05,
      "loss": 1.0442,
      "step": 92
    },
    {
      "epoch": 0.25761772853185594,
      "grad_norm": 0.20160586348422904,
      "learning_rate": 4.510043619595031e-05,
      "loss": 1.0648,
      "step": 93
    },
    {
      "epoch": 0.26038781163434904,
      "grad_norm": 0.18066141120205173,
      "learning_rate": 4.49705546677424e-05,
      "loss": 0.9018,
      "step": 94
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.21418534715858012,
      "learning_rate": 4.483919029845431e-05,
      "loss": 0.9509,
      "step": 95
    },
    {
      "epoch": 0.2659279778393352,
      "grad_norm": 0.17573567089277978,
      "learning_rate": 4.470635423784556e-05,
      "loss": 0.9513,
      "step": 96
    },
    {
      "epoch": 0.26869806094182824,
      "grad_norm": 0.17774724005874368,
      "learning_rate": 4.4572057760587796e-05,
      "loss": 0.8852,
      "step": 97
    },
    {
      "epoch": 0.27146814404432135,
      "grad_norm": 0.18965686235959792,
      "learning_rate": 4.4436312265307876e-05,
      "loss": 0.9826,
      "step": 98
    },
    {
      "epoch": 0.2742382271468144,
      "grad_norm": 0.1982451843435613,
      "learning_rate": 4.429912927362035e-05,
      "loss": 0.9473,
      "step": 99
    },
    {
      "epoch": 0.2770083102493075,
      "grad_norm": 0.19613124811118365,
      "learning_rate": 4.416052042914954e-05,
      "loss": 0.9648,
      "step": 100
    },
    {
      "epoch": 0.27977839335180055,
      "grad_norm": 0.17148361064681392,
      "learning_rate": 4.402049749654133e-05,
      "loss": 0.9262,
      "step": 101
    },
    {
      "epoch": 0.28254847645429365,
      "grad_norm": 0.18346018130558348,
      "learning_rate": 4.387907236046455e-05,
      "loss": 0.9295,
      "step": 102
    },
    {
      "epoch": 0.2853185595567867,
      "grad_norm": 0.2092097295306342,
      "learning_rate": 4.3736257024602274e-05,
      "loss": 0.9108,
      "step": 103
    },
    {
      "epoch": 0.2880886426592798,
      "grad_norm": 0.21514609527308398,
      "learning_rate": 4.359206361063302e-05,
      "loss": 0.9358,
      "step": 104
    },
    {
      "epoch": 0.29085872576177285,
      "grad_norm": 0.2109170892352583,
      "learning_rate": 4.344650435720184e-05,
      "loss": 0.9258,
      "step": 105
    },
    {
      "epoch": 0.29362880886426596,
      "grad_norm": 0.20927017505540593,
      "learning_rate": 4.3299591618881604e-05,
      "loss": 1.0129,
      "step": 106
    },
    {
      "epoch": 0.296398891966759,
      "grad_norm": 0.2044744893718055,
      "learning_rate": 4.3151337865124354e-05,
      "loss": 0.9501,
      "step": 107
    },
    {
      "epoch": 0.29916897506925205,
      "grad_norm": 0.23366539469114328,
      "learning_rate": 4.3001755679202946e-05,
      "loss": 1.0061,
      "step": 108
    },
    {
      "epoch": 0.30193905817174516,
      "grad_norm": 0.28332040666616826,
      "learning_rate": 4.2850857757143035e-05,
      "loss": 1.0622,
      "step": 109
    },
    {
      "epoch": 0.3047091412742382,
      "grad_norm": 0.22750850899455075,
      "learning_rate": 4.269865690664546e-05,
      "loss": 0.9932,
      "step": 110
    },
    {
      "epoch": 0.3074792243767313,
      "grad_norm": 0.2919596477328322,
      "learning_rate": 4.2545166045999175e-05,
      "loss": 0.9947,
      "step": 111
    },
    {
      "epoch": 0.3074792243767313,
      "eval_loss": 0.7285755276679993,
      "eval_runtime": 105.4908,
      "eval_samples_per_second": 0.948,
      "eval_steps_per_second": 0.237,
      "step": 111
    },
    {
      "epoch": 0.31024930747922436,
      "grad_norm": 0.22650943562204162,
      "learning_rate": 4.239039820298482e-05,
      "loss": 0.9006,
      "step": 112
    },
    {
      "epoch": 0.31301939058171746,
      "grad_norm": 0.31497879982021704,
      "learning_rate": 4.223436651376892e-05,
      "loss": 0.9833,
      "step": 113
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.22217961036727576,
      "learning_rate": 4.207708422178896e-05,
      "loss": 0.9329,
      "step": 114
    },
    {
      "epoch": 0.3185595567867036,
      "grad_norm": 0.29069944659837527,
      "learning_rate": 4.1918564676629316e-05,
      "loss": 1.005,
      "step": 115
    },
    {
      "epoch": 0.32132963988919666,
      "grad_norm": 0.25740135929728936,
      "learning_rate": 4.1758821332888205e-05,
      "loss": 0.9289,
      "step": 116
    },
    {
      "epoch": 0.32409972299168976,
      "grad_norm": 0.20735884986652237,
      "learning_rate": 4.159786774903569e-05,
      "loss": 0.7929,
      "step": 117
    },
    {
      "epoch": 0.3268698060941828,
      "grad_norm": 0.2734473995424548,
      "learning_rate": 4.143571758626288e-05,
      "loss": 0.9545,
      "step": 118
    },
    {
      "epoch": 0.3296398891966759,
      "grad_norm": 0.2819033324098223,
      "learning_rate": 4.127238460732242e-05,
      "loss": 0.9095,
      "step": 119
    },
    {
      "epoch": 0.33240997229916897,
      "grad_norm": 0.21720763820121466,
      "learning_rate": 4.110788267536036e-05,
      "loss": 0.8727,
      "step": 120
    },
    {
      "epoch": 0.33518005540166207,
      "grad_norm": 0.3603455449135715,
      "learning_rate": 4.0942225752739496e-05,
      "loss": 0.9487,
      "step": 121
    },
    {
      "epoch": 0.3379501385041551,
      "grad_norm": 0.26959993038866503,
      "learning_rate": 4.077542789985429e-05,
      "loss": 0.9707,
      "step": 122
    },
    {
      "epoch": 0.3407202216066482,
      "grad_norm": 0.2918507118523375,
      "learning_rate": 4.0607503273937464e-05,
      "loss": 0.9828,
      "step": 123
    },
    {
      "epoch": 0.34349030470914127,
      "grad_norm": 0.34593468652257114,
      "learning_rate": 4.0438466127858407e-05,
      "loss": 0.9309,
      "step": 124
    },
    {
      "epoch": 0.3462603878116344,
      "grad_norm": 0.2328074759683285,
      "learning_rate": 4.026833080891342e-05,
      "loss": 0.95,
      "step": 125
    },
    {
      "epoch": 0.3490304709141274,
      "grad_norm": 0.28764735207874204,
      "learning_rate": 4.0097111757607955e-05,
      "loss": 0.9819,
      "step": 126
    },
    {
      "epoch": 0.3518005540166205,
      "grad_norm": 0.4004054092669033,
      "learning_rate": 3.9924823506430974e-05,
      "loss": 0.9405,
      "step": 127
    },
    {
      "epoch": 0.3545706371191136,
      "grad_norm": 0.2645217010449881,
      "learning_rate": 3.9751480678621505e-05,
      "loss": 0.9705,
      "step": 128
    },
    {
      "epoch": 0.3573407202216066,
      "grad_norm": 0.2940771458015333,
      "learning_rate": 3.957709798692741e-05,
      "loss": 0.9053,
      "step": 129
    },
    {
      "epoch": 0.3601108033240997,
      "grad_norm": 0.33343898482348633,
      "learning_rate": 3.9401690232356654e-05,
      "loss": 0.9337,
      "step": 130
    },
    {
      "epoch": 0.3628808864265928,
      "grad_norm": 0.3818512479727835,
      "learning_rate": 3.922527230292107e-05,
      "loss": 0.9639,
      "step": 131
    },
    {
      "epoch": 0.3656509695290859,
      "grad_norm": 0.3278779554370676,
      "learning_rate": 3.904785917237264e-05,
      "loss": 1.0459,
      "step": 132
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.34049121712960123,
      "learning_rate": 3.8869465898932664e-05,
      "loss": 0.898,
      "step": 133
    },
    {
      "epoch": 0.37119113573407203,
      "grad_norm": 0.39663817614396785,
      "learning_rate": 3.8690107624013614e-05,
      "loss": 0.8741,
      "step": 134
    },
    {
      "epoch": 0.3739612188365651,
      "grad_norm": 0.3157982406853401,
      "learning_rate": 3.8509799570933985e-05,
      "loss": 1.0399,
      "step": 135
    },
    {
      "epoch": 0.3767313019390582,
      "grad_norm": 0.5076584455774723,
      "learning_rate": 3.832855704362621e-05,
      "loss": 0.9597,
      "step": 136
    },
    {
      "epoch": 0.37950138504155123,
      "grad_norm": 0.31376263297051804,
      "learning_rate": 3.814639542533771e-05,
      "loss": 0.9315,
      "step": 137
    },
    {
      "epoch": 0.38227146814404434,
      "grad_norm": 0.3400455584385456,
      "learning_rate": 3.796333017732519e-05,
      "loss": 0.8829,
      "step": 138
    },
    {
      "epoch": 0.3850415512465374,
      "grad_norm": 0.3541184588730341,
      "learning_rate": 3.777937683754242e-05,
      "loss": 0.8097,
      "step": 139
    },
    {
      "epoch": 0.3878116343490305,
      "grad_norm": 0.3333594677616915,
      "learning_rate": 3.75945510193213e-05,
      "loss": 0.9865,
      "step": 140
    },
    {
      "epoch": 0.39058171745152354,
      "grad_norm": 0.3650263368887469,
      "learning_rate": 3.740886841004678e-05,
      "loss": 0.9889,
      "step": 141
    },
    {
      "epoch": 0.39335180055401664,
      "grad_norm": 0.3586705478546664,
      "learning_rate": 3.7222344769825255e-05,
      "loss": 0.9119,
      "step": 142
    },
    {
      "epoch": 0.3961218836565097,
      "grad_norm": 0.2968031141643322,
      "learning_rate": 3.703499593014702e-05,
      "loss": 0.837,
      "step": 143
    },
    {
      "epoch": 0.3988919667590028,
      "grad_norm": 0.28911701684318286,
      "learning_rate": 3.6846837792542446e-05,
      "loss": 0.849,
      "step": 144
    },
    {
      "epoch": 0.40166204986149584,
      "grad_norm": 0.3428834579431544,
      "learning_rate": 3.6657886327232357e-05,
      "loss": 0.813,
      "step": 145
    },
    {
      "epoch": 0.40443213296398894,
      "grad_norm": 0.3390660834271031,
      "learning_rate": 3.6468157571772535e-05,
      "loss": 1.014,
      "step": 146
    },
    {
      "epoch": 0.407202216066482,
      "grad_norm": 0.29842989483876114,
      "learning_rate": 3.6277667629692475e-05,
      "loss": 0.9415,
      "step": 147
    },
    {
      "epoch": 0.4099722991689751,
      "grad_norm": 0.40347234769657353,
      "learning_rate": 3.608643266912863e-05,
      "loss": 0.8513,
      "step": 148
    },
    {
      "epoch": 0.4099722991689751,
      "eval_loss": 0.6967936754226685,
      "eval_runtime": 105.0327,
      "eval_samples_per_second": 0.952,
      "eval_steps_per_second": 0.238,
      "step": 148
    },
    {
      "epoch": 0.41274238227146814,
      "grad_norm": 0.293058789027836,
      "learning_rate": 3.5894468921452055e-05,
      "loss": 0.8557,
      "step": 149
    },
    {
      "epoch": 0.4155124653739612,
      "grad_norm": 0.5025689623712035,
      "learning_rate": 3.570179267989079e-05,
      "loss": 0.9919,
      "step": 150
    },
    {
      "epoch": 0.4182825484764543,
      "grad_norm": 0.34207048547694535,
      "learning_rate": 3.550842029814689e-05,
      "loss": 0.9175,
      "step": 151
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.3442929194276912,
      "learning_rate": 3.531436818900846e-05,
      "loss": 0.9258,
      "step": 152
    },
    {
      "epoch": 0.42382271468144045,
      "grad_norm": 0.3397465751123524,
      "learning_rate": 3.511965282295651e-05,
      "loss": 0.8444,
      "step": 153
    },
    {
      "epoch": 0.4265927977839335,
      "grad_norm": 0.4164754708763866,
      "learning_rate": 3.492429072676704e-05,
      "loss": 0.7808,
      "step": 154
    },
    {
      "epoch": 0.4293628808864266,
      "grad_norm": 0.3970020903838321,
      "learning_rate": 3.472829848210833e-05,
      "loss": 0.8346,
      "step": 155
    },
    {
      "epoch": 0.43213296398891965,
      "grad_norm": 0.35193376832006673,
      "learning_rate": 3.453169272413347e-05,
      "loss": 0.8341,
      "step": 156
    },
    {
      "epoch": 0.43490304709141275,
      "grad_norm": 0.3786418049677514,
      "learning_rate": 3.433449014006849e-05,
      "loss": 0.8282,
      "step": 157
    },
    {
      "epoch": 0.4376731301939058,
      "grad_norm": 0.3841329093851364,
      "learning_rate": 3.4136707467795975e-05,
      "loss": 0.8553,
      "step": 158
    },
    {
      "epoch": 0.4404432132963989,
      "grad_norm": 0.3672502229739841,
      "learning_rate": 3.3938361494434416e-05,
      "loss": 0.8543,
      "step": 159
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": 0.35006854344753147,
      "learning_rate": 3.3739469054913396e-05,
      "loss": 0.9272,
      "step": 160
    },
    {
      "epoch": 0.44598337950138506,
      "grad_norm": 0.37656118751084383,
      "learning_rate": 3.354004703054466e-05,
      "loss": 0.8156,
      "step": 161
    },
    {
      "epoch": 0.4487534626038781,
      "grad_norm": 0.41484594703372124,
      "learning_rate": 3.334011234758933e-05,
      "loss": 0.9283,
      "step": 162
    },
    {
      "epoch": 0.4515235457063712,
      "grad_norm": 0.36059722487577023,
      "learning_rate": 3.3139681975821215e-05,
      "loss": 0.9589,
      "step": 163
    },
    {
      "epoch": 0.45429362880886426,
      "grad_norm": 0.49096051315762496,
      "learning_rate": 3.2938772927086506e-05,
      "loss": 0.8572,
      "step": 164
    },
    {
      "epoch": 0.45706371191135736,
      "grad_norm": 0.3657461189986915,
      "learning_rate": 3.273740225385988e-05,
      "loss": 0.8634,
      "step": 165
    },
    {
      "epoch": 0.4598337950138504,
      "grad_norm": 0.4619952678802632,
      "learning_rate": 3.253558704779711e-05,
      "loss": 0.8531,
      "step": 166
    },
    {
      "epoch": 0.4626038781163435,
      "grad_norm": 0.38029424915243915,
      "learning_rate": 3.2333344438284396e-05,
      "loss": 0.8544,
      "step": 167
    },
    {
      "epoch": 0.46537396121883656,
      "grad_norm": 0.41328982224991867,
      "learning_rate": 3.21306915909845e-05,
      "loss": 0.8833,
      "step": 168
    },
    {
      "epoch": 0.46814404432132967,
      "grad_norm": 0.3923589316746721,
      "learning_rate": 3.1927645706379764e-05,
      "loss": 0.9791,
      "step": 169
    },
    {
      "epoch": 0.4709141274238227,
      "grad_norm": 0.3424277457752046,
      "learning_rate": 3.1724224018312184e-05,
      "loss": 0.9123,
      "step": 170
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.46781422059203653,
      "learning_rate": 3.152044379252067e-05,
      "loss": 0.8154,
      "step": 171
    },
    {
      "epoch": 0.47645429362880887,
      "grad_norm": 0.3469918706960392,
      "learning_rate": 3.131632232517562e-05,
      "loss": 0.7862,
      "step": 172
    },
    {
      "epoch": 0.4792243767313019,
      "grad_norm": 0.3826762775779829,
      "learning_rate": 3.111187694141082e-05,
      "loss": 0.9544,
      "step": 173
    },
    {
      "epoch": 0.481994459833795,
      "grad_norm": 0.35177402551860143,
      "learning_rate": 3.0907124993852976e-05,
      "loss": 0.7952,
      "step": 174
    },
    {
      "epoch": 0.48476454293628807,
      "grad_norm": 0.32900068971172497,
      "learning_rate": 3.070208386114892e-05,
      "loss": 0.7085,
      "step": 175
    },
    {
      "epoch": 0.48753462603878117,
      "grad_norm": 0.7811598278937018,
      "learning_rate": 3.0496770946490492e-05,
      "loss": 0.7872,
      "step": 176
    },
    {
      "epoch": 0.4903047091412742,
      "grad_norm": 0.39312070018511214,
      "learning_rate": 3.029120367613747e-05,
      "loss": 0.8672,
      "step": 177
    },
    {
      "epoch": 0.4930747922437673,
      "grad_norm": 0.4140927363443536,
      "learning_rate": 3.0085399497938488e-05,
      "loss": 0.8214,
      "step": 178
    },
    {
      "epoch": 0.49584487534626037,
      "grad_norm": 0.616509191319175,
      "learning_rate": 2.9879375879850103e-05,
      "loss": 0.8303,
      "step": 179
    },
    {
      "epoch": 0.4986149584487535,
      "grad_norm": 0.429366430219185,
      "learning_rate": 2.967315030845415e-05,
      "loss": 0.9848,
      "step": 180
    },
    {
      "epoch": 0.5013850415512465,
      "grad_norm": 0.5293488318623817,
      "learning_rate": 2.9466740287473638e-05,
      "loss": 0.8849,
      "step": 181
    },
    {
      "epoch": 0.5041551246537396,
      "grad_norm": 0.4983497133183736,
      "learning_rate": 2.9260163336286968e-05,
      "loss": 0.8088,
      "step": 182
    },
    {
      "epoch": 0.5069252077562327,
      "grad_norm": 0.476254468852299,
      "learning_rate": 2.905343698844103e-05,
      "loss": 0.8621,
      "step": 183
    },
    {
      "epoch": 0.5096952908587258,
      "grad_norm": 0.4786974943663476,
      "learning_rate": 2.884657879016299e-05,
      "loss": 0.8227,
      "step": 184
    },
    {
      "epoch": 0.5124653739612188,
      "grad_norm": 0.4653172688884986,
      "learning_rate": 2.863960629887104e-05,
      "loss": 0.8095,
      "step": 185
    },
    {
      "epoch": 0.5124653739612188,
      "eval_loss": 0.6681232452392578,
      "eval_runtime": 104.7731,
      "eval_samples_per_second": 0.954,
      "eval_steps_per_second": 0.239,
      "step": 185
    },
    {
      "epoch": 0.5152354570637119,
      "grad_norm": 0.4046344642446634,
      "learning_rate": 2.843253708168415e-05,
      "loss": 0.8669,
      "step": 186
    },
    {
      "epoch": 0.518005540166205,
      "grad_norm": 0.39837130351678596,
      "learning_rate": 2.8225388713931077e-05,
      "loss": 0.7931,
      "step": 187
    },
    {
      "epoch": 0.5207756232686981,
      "grad_norm": 0.5213280111204851,
      "learning_rate": 2.8018178777658606e-05,
      "loss": 0.8635,
      "step": 188
    },
    {
      "epoch": 0.5235457063711911,
      "grad_norm": 0.597198365618595,
      "learning_rate": 2.781092486013922e-05,
      "loss": 0.8894,
      "step": 189
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5240535623325078,
      "learning_rate": 2.7603644552378416e-05,
      "loss": 0.8702,
      "step": 190
    },
    {
      "epoch": 0.5290858725761773,
      "grad_norm": 0.6138846789060535,
      "learning_rate": 2.7396355447621592e-05,
      "loss": 0.8119,
      "step": 191
    },
    {
      "epoch": 0.5318559556786704,
      "grad_norm": 0.366272122964379,
      "learning_rate": 2.718907513986078e-05,
      "loss": 0.7842,
      "step": 192
    },
    {
      "epoch": 0.5346260387811634,
      "grad_norm": 0.40094490758320805,
      "learning_rate": 2.6981821222341402e-05,
      "loss": 0.764,
      "step": 193
    },
    {
      "epoch": 0.5373961218836565,
      "grad_norm": 0.5372324207647045,
      "learning_rate": 2.6774611286068925e-05,
      "loss": 0.842,
      "step": 194
    },
    {
      "epoch": 0.5401662049861495,
      "grad_norm": 0.48537277506100157,
      "learning_rate": 2.6567462918315854e-05,
      "loss": 0.8458,
      "step": 195
    },
    {
      "epoch": 0.5429362880886427,
      "grad_norm": 0.34780522923613105,
      "learning_rate": 2.6360393701128968e-05,
      "loss": 0.8072,
      "step": 196
    },
    {
      "epoch": 0.5457063711911357,
      "grad_norm": 0.47774919793354165,
      "learning_rate": 2.6153421209837014e-05,
      "loss": 0.8267,
      "step": 197
    },
    {
      "epoch": 0.5484764542936288,
      "grad_norm": 0.4528933180645613,
      "learning_rate": 2.5946563011558976e-05,
      "loss": 0.7658,
      "step": 198
    },
    {
      "epoch": 0.5512465373961218,
      "grad_norm": 0.36863071919365176,
      "learning_rate": 2.573983666371304e-05,
      "loss": 0.7463,
      "step": 199
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": 0.5401156027855689,
      "learning_rate": 2.5533259712526364e-05,
      "loss": 0.8011,
      "step": 200
    },
    {
      "epoch": 0.556786703601108,
      "grad_norm": 0.38878696385621075,
      "learning_rate": 2.532684969154585e-05,
      "loss": 0.7882,
      "step": 201
    },
    {
      "epoch": 0.5595567867036011,
      "grad_norm": 0.526790961475592,
      "learning_rate": 2.512062412014991e-05,
      "loss": 0.7619,
      "step": 202
    },
    {
      "epoch": 0.5623268698060941,
      "grad_norm": 0.38768035501734327,
      "learning_rate": 2.4914600502061514e-05,
      "loss": 0.8093,
      "step": 203
    },
    {
      "epoch": 0.5650969529085873,
      "grad_norm": 0.5944282601248911,
      "learning_rate": 2.4708796323862538e-05,
      "loss": 0.8492,
      "step": 204
    },
    {
      "epoch": 0.5678670360110804,
      "grad_norm": 0.425756127694364,
      "learning_rate": 2.450322905350952e-05,
      "loss": 0.7968,
      "step": 205
    },
    {
      "epoch": 0.5706371191135734,
      "grad_norm": 0.5587462841529842,
      "learning_rate": 2.429791613885109e-05,
      "loss": 0.8096,
      "step": 206
    },
    {
      "epoch": 0.5734072022160664,
      "grad_norm": 0.46265286926711546,
      "learning_rate": 2.4092875006147033e-05,
      "loss": 0.806,
      "step": 207
    },
    {
      "epoch": 0.5761772853185596,
      "grad_norm": 0.7142931706449129,
      "learning_rate": 2.38881230585892e-05,
      "loss": 0.7939,
      "step": 208
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.3849923319993063,
      "learning_rate": 2.3683677674824395e-05,
      "loss": 0.8323,
      "step": 209
    },
    {
      "epoch": 0.5817174515235457,
      "grad_norm": 0.40510481254312813,
      "learning_rate": 2.3479556207479336e-05,
      "loss": 0.7158,
      "step": 210
    },
    {
      "epoch": 0.5844875346260388,
      "grad_norm": 0.6209266610489942,
      "learning_rate": 2.327577598168783e-05,
      "loss": 0.7779,
      "step": 211
    },
    {
      "epoch": 0.5872576177285319,
      "grad_norm": 0.6177522163632044,
      "learning_rate": 2.3072354293620234e-05,
      "loss": 0.7929,
      "step": 212
    },
    {
      "epoch": 0.590027700831025,
      "grad_norm": 0.6303542857640766,
      "learning_rate": 2.28693084090155e-05,
      "loss": 0.8084,
      "step": 213
    },
    {
      "epoch": 0.592797783933518,
      "grad_norm": 0.4632833158309286,
      "learning_rate": 2.2666655561715606e-05,
      "loss": 0.8703,
      "step": 214
    },
    {
      "epoch": 0.5955678670360111,
      "grad_norm": 0.4375774421144756,
      "learning_rate": 2.246441295220289e-05,
      "loss": 0.7233,
      "step": 215
    },
    {
      "epoch": 0.5983379501385041,
      "grad_norm": 0.43062269722365204,
      "learning_rate": 2.2262597746140123e-05,
      "loss": 0.8269,
      "step": 216
    },
    {
      "epoch": 0.6011080332409973,
      "grad_norm": 0.5563739531634719,
      "learning_rate": 2.2061227072913493e-05,
      "loss": 0.8228,
      "step": 217
    },
    {
      "epoch": 0.6038781163434903,
      "grad_norm": 0.41792823244918276,
      "learning_rate": 2.186031802417879e-05,
      "loss": 0.7883,
      "step": 218
    },
    {
      "epoch": 0.6066481994459834,
      "grad_norm": 1.0052929026225181,
      "learning_rate": 2.165988765241067e-05,
      "loss": 0.7929,
      "step": 219
    }
  ],
  "logging_steps": 1,
  "max_steps": 361,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 73,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 653642013081600.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}