{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 140,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.04437721520662308,
      "learning_rate": 0.0001,
      "loss": 2.9182,
      "step": 1
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.043723102658987045,
      "learning_rate": 9.998741174712533e-05,
      "loss": 3.0496,
      "step": 2
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.05327531322836876,
      "learning_rate": 9.994965332706573e-05,
      "loss": 2.9637,
      "step": 3
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.0456581711769104,
      "learning_rate": 9.98867437523228e-05,
      "loss": 3.028,
      "step": 4
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.06097229942679405,
      "learning_rate": 9.979871469976196e-05,
      "loss": 3.1738,
      "step": 5
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.054630689322948456,
      "learning_rate": 9.968561049466214e-05,
      "loss": 2.9675,
      "step": 6
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.04048009216785431,
      "learning_rate": 9.954748808839674e-05,
      "loss": 2.7819,
      "step": 7
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.0496661476790905,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.9271,
      "step": 8
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.04144083708524704,
      "learning_rate": 9.919647942993148e-05,
      "loss": 2.9659,
      "step": 9
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.05908624827861786,
      "learning_rate": 9.898376992116179e-05,
      "loss": 3.0879,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.039516329765319824,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.948,
      "step": 11
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.06166892871260643,
      "learning_rate": 9.848447601883435e-05,
      "loss": 3.1836,
      "step": 12
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.05398089811205864,
      "learning_rate": 9.819814303479267e-05,
      "loss": 3.1113,
      "step": 13
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.05868612229824066,
      "learning_rate": 9.788754083424652e-05,
      "loss": 3.0408,
      "step": 14
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.0467713288962841,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.9203,
      "step": 15
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.027636295184493065,
      "learning_rate": 9.719416651541839e-05,
      "loss": 2.7886,
      "step": 16
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 0.056903958320617676,
      "learning_rate": 9.681174353198687e-05,
      "loss": 2.8364,
      "step": 17
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.049529753625392914,
      "learning_rate": 9.640574942595196e-05,
      "loss": 2.7925,
      "step": 18
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 0.050446752458810806,
      "learning_rate": 9.597638862757255e-05,
      "loss": 2.9225,
      "step": 19
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.05019264668226242,
      "learning_rate": 9.552387733294081e-05,
      "loss": 2.7881,
      "step": 20
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.049757473170757294,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.7723,
      "step": 21
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.04598463699221611,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.7872,
      "step": 22
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.04541643336415291,
      "learning_rate": 9.40297765928369e-05,
      "loss": 2.7633,
      "step": 23
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.04832007735967636,
      "learning_rate": 9.348705665778478e-05,
      "loss": 2.709,
      "step": 24
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.07004053145647049,
      "learning_rate": 9.292243968009331e-05,
      "loss": 2.986,
      "step": 25
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.05622578784823418,
      "learning_rate": 9.233620996141421e-05,
      "loss": 2.8992,
      "step": 26
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.05483135208487511,
      "learning_rate": 9.172866268606513e-05,
      "loss": 2.6659,
      "step": 27
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.08639640361070633,
      "learning_rate": 9.110010377239551e-05,
      "loss": 2.7209,
      "step": 28
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.053235579282045364,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6965,
      "step": 29
    },
    {
      "epoch": 1.0727272727272728,
      "grad_norm": 0.05548636242747307,
      "learning_rate": 8.978122744408906e-05,
      "loss": 2.7943,
      "step": 30
    },
    {
      "epoch": 1.1090909090909091,
      "grad_norm": 0.05852334201335907,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.7014,
      "step": 31
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.06862631440162659,
      "learning_rate": 8.838223701790055e-05,
      "loss": 2.6548,
      "step": 32
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.07998227328062057,
      "learning_rate": 8.765357330018056e-05,
      "loss": 2.7957,
      "step": 33
    },
    {
      "epoch": 1.2181818181818183,
      "grad_norm": 0.05929108336567879,
      "learning_rate": 8.690594987436704e-05,
      "loss": 2.7065,
      "step": 34
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.056504398584365845,
      "learning_rate": 8.613974319136958e-05,
      "loss": 2.5714,
      "step": 35
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 0.0636766105890274,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6873,
      "step": 36
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 0.05943327024579048,
      "learning_rate": 8.455313244934324e-05,
      "loss": 2.7659,
      "step": 37
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.07448691874742508,
      "learning_rate": 8.373352729660373e-05,
      "loss": 2.7479,
      "step": 38
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.051619142293930054,
      "learning_rate": 8.289693629698564e-05,
      "loss": 2.7637,
      "step": 39
    },
    {
      "epoch": 1.4363636363636363,
      "grad_norm": 0.08066663146018982,
      "learning_rate": 8.20437806992512e-05,
      "loss": 2.8169,
      "step": 40
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 0.07334642857313156,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.8457,
      "step": 41
    },
    {
      "epoch": 1.509090909090909,
      "grad_norm": 0.06760259717702866,
      "learning_rate": 8.0289502192041e-05,
      "loss": 2.781,
      "step": 42
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.06140042468905449,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.6957,
      "step": 43
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 0.05024508014321327,
      "learning_rate": 7.84742246584226e-05,
      "loss": 2.6953,
      "step": 44
    },
    {
      "epoch": 1.6181818181818182,
      "grad_norm": 0.07060069590806961,
      "learning_rate": 7.754484907260513e-05,
      "loss": 2.5912,
      "step": 45
    },
    {
      "epoch": 1.6545454545454545,
      "grad_norm": 0.2308979332447052,
      "learning_rate": 7.660160382576683e-05,
      "loss": 2.5778,
      "step": 46
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.062225863337516785,
      "learning_rate": 7.564496387029532e-05,
      "loss": 2.7804,
      "step": 47
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.0672062411904335,
      "learning_rate": 7.467541090321735e-05,
      "loss": 2.6002,
      "step": 48
    },
    {
      "epoch": 1.7636363636363637,
      "grad_norm": 0.06851445138454437,
      "learning_rate": 7.369343312364993e-05,
      "loss": 2.5963,
      "step": 49
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.061497125774621964,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.6389,
      "step": 50
    },
    {
      "epoch": 1.8363636363636364,
      "grad_norm": 0.05956913158297539,
      "learning_rate": 7.169418695587791e-05,
      "loss": 2.6499,
      "step": 51
    },
    {
      "epoch": 1.8727272727272726,
      "grad_norm": 0.0681229904294014,
      "learning_rate": 7.067792524832604e-05,
      "loss": 2.579,
      "step": 52
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.08703067153692245,
      "learning_rate": 6.965125158269619e-05,
      "loss": 2.8107,
      "step": 53
    },
    {
      "epoch": 1.9454545454545453,
      "grad_norm": 0.06779715418815613,
      "learning_rate": 6.861468292009727e-05,
      "loss": 2.7762,
      "step": 54
    },
    {
      "epoch": 1.981818181818182,
      "grad_norm": 0.06822039186954498,
      "learning_rate": 6.756874120406714e-05,
      "loss": 2.5568,
      "step": 55
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.11132216453552246,
      "learning_rate": 6.651395309775837e-05,
      "loss": 2.5516,
      "step": 56
    },
    {
      "epoch": 2.036363636363636,
      "grad_norm": 0.06783980131149292,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5994,
      "step": 57
    },
    {
      "epoch": 2.0727272727272728,
      "grad_norm": 0.07067389786243439,
      "learning_rate": 6.437996637160087e-05,
      "loss": 2.6891,
      "step": 58
    },
    {
      "epoch": 2.109090909090909,
      "grad_norm": 0.06793996691703796,
      "learning_rate": 6.330184227833376e-05,
      "loss": 2.5964,
      "step": 59
    },
    {
      "epoch": 2.1454545454545455,
      "grad_norm": 0.08635850995779037,
      "learning_rate": 6.22170203068947e-05,
      "loss": 2.5186,
      "step": 60
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.09051436930894852,
      "learning_rate": 6.112604669781572e-05,
      "loss": 2.6482,
      "step": 61
    },
    {
      "epoch": 2.2181818181818183,
      "grad_norm": 0.0771794319152832,
      "learning_rate": 6.0029470789163646e-05,
      "loss": 2.6177,
      "step": 62
    },
    {
      "epoch": 2.2545454545454544,
      "grad_norm": 0.06822357326745987,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 2.4996,
      "step": 63
    },
    {
      "epoch": 2.290909090909091,
      "grad_norm": 0.07269691675901413,
      "learning_rate": 5.782172325201155e-05,
      "loss": 2.6046,
      "step": 64
    },
    {
      "epoch": 2.327272727272727,
      "grad_norm": 0.06602519750595093,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 2.7001,
      "step": 65
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.10055851191282272,
      "learning_rate": 5.559822380516539e-05,
      "loss": 2.6308,
      "step": 66
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.06516829878091812,
      "learning_rate": 5.448196544517168e-05,
      "loss": 2.7021,
      "step": 67
    },
    {
      "epoch": 2.4363636363636365,
      "grad_norm": 0.10851520299911499,
      "learning_rate": 5.336345028060199e-05,
      "loss": 2.6942,
      "step": 68
    },
    {
      "epoch": 2.4727272727272727,
      "grad_norm": 0.0966155081987381,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 2.7561,
      "step": 69
    },
    {
      "epoch": 2.509090909090909,
      "grad_norm": 0.09414198249578476,
      "learning_rate": 5.112190321479026e-05,
      "loss": 2.6951,
      "step": 70
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.0773131474852562,
      "learning_rate": 5e-05,
      "loss": 2.6132,
      "step": 71
    },
    {
      "epoch": 2.581818181818182,
      "grad_norm": 0.06048035994172096,
      "learning_rate": 4.887809678520976e-05,
      "loss": 2.6578,
      "step": 72
    },
    {
      "epoch": 2.618181818181818,
      "grad_norm": 0.09242013096809387,
      "learning_rate": 4.775675848247427e-05,
      "loss": 2.518,
      "step": 73
    },
    {
      "epoch": 2.6545454545454543,
      "grad_norm": 0.080746591091156,
      "learning_rate": 4.663654971939802e-05,
      "loss": 2.5037,
      "step": 74
    },
    {
      "epoch": 2.690909090909091,
      "grad_norm": 0.07520557194948196,
      "learning_rate": 4.551803455482833e-05,
      "loss": 2.7234,
      "step": 75
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.08398128300905228,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 2.5442,
      "step": 76
    },
    {
      "epoch": 2.7636363636363637,
      "grad_norm": 0.08525212109088898,
      "learning_rate": 4.328833670911724e-05,
      "loss": 2.5266,
      "step": 77
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.07664482295513153,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.5812,
      "step": 78
    },
    {
      "epoch": 2.8363636363636364,
      "grad_norm": 0.0694664865732193,
      "learning_rate": 4.107215526006817e-05,
      "loss": 2.5948,
      "step": 79
    },
    {
      "epoch": 2.8727272727272726,
      "grad_norm": 0.07536519318819046,
      "learning_rate": 3.9970529210836366e-05,
      "loss": 2.5289,
      "step": 80
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.10434147715568542,
      "learning_rate": 3.887395330218429e-05,
      "loss": 2.729,
      "step": 81
    },
    {
      "epoch": 2.9454545454545453,
      "grad_norm": 0.08390311896800995,
      "learning_rate": 3.778297969310529e-05,
      "loss": 2.7243,
      "step": 82
    },
    {
      "epoch": 2.981818181818182,
      "grad_norm": 0.07909922301769257,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 2.512,
      "step": 83
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.13165485858917236,
      "learning_rate": 3.562003362839914e-05,
      "loss": 2.4427,
      "step": 84
    },
    {
      "epoch": 3.036363636363636,
      "grad_norm": 0.08213932812213898,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.5448,
      "step": 85
    },
    {
      "epoch": 3.0727272727272728,
      "grad_norm": 0.08873779326677322,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 2.6455,
      "step": 86
    },
    {
      "epoch": 3.109090909090909,
      "grad_norm": 0.08198881894350052,
      "learning_rate": 3.243125879593286e-05,
      "loss": 2.5483,
      "step": 87
    },
    {
      "epoch": 3.1454545454545455,
      "grad_norm": 0.10713133960962296,
      "learning_rate": 3.1385317079902745e-05,
      "loss": 2.4592,
      "step": 88
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.10965828597545624,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 2.5872,
      "step": 89
    },
    {
      "epoch": 3.2181818181818183,
      "grad_norm": 0.09284146130084991,
      "learning_rate": 2.932207475167398e-05,
      "loss": 2.5711,
      "step": 90
    },
    {
      "epoch": 3.2545454545454544,
      "grad_norm": 0.08303961902856827,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 2.467,
      "step": 91
    },
    {
      "epoch": 3.290909090909091,
      "grad_norm": 0.0881534293293953,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 2.5634,
      "step": 92
    },
    {
      "epoch": 3.327272727272727,
      "grad_norm": 0.08024799823760986,
      "learning_rate": 2.630656687635007e-05,
      "loss": 2.6654,
      "step": 93
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 0.11957813054323196,
      "learning_rate": 2.5324589096782657e-05,
      "loss": 2.562,
      "step": 94
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.07816164940595627,
      "learning_rate": 2.43550361297047e-05,
      "loss": 2.6734,
      "step": 95
    },
    {
      "epoch": 3.4363636363636365,
      "grad_norm": 0.12103608250617981,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 2.626,
      "step": 96
    },
    {
      "epoch": 3.4727272727272727,
      "grad_norm": 0.11207111179828644,
      "learning_rate": 2.245515092739488e-05,
      "loss": 2.7046,
      "step": 97
    },
    {
      "epoch": 3.509090909090909,
      "grad_norm": 0.10773749649524689,
      "learning_rate": 2.1525775341577405e-05,
      "loss": 2.6429,
      "step": 98
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 0.09073398262262344,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.5697,
      "step": 99
    },
    {
      "epoch": 3.581818181818182,
      "grad_norm": 0.07114943116903305,
      "learning_rate": 1.971049780795901e-05,
      "loss": 2.6358,
      "step": 100
    },
    {
      "epoch": 3.618181818181818,
      "grad_norm": 0.10918023437261581,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 2.4736,
      "step": 101
    },
    {
      "epoch": 3.6545454545454543,
      "grad_norm": 0.09359312802553177,
      "learning_rate": 1.7956219300748793e-05,
      "loss": 2.4592,
      "step": 102
    },
    {
      "epoch": 3.690909090909091,
      "grad_norm": 0.08727962523698807,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 2.6921,
      "step": 103
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.09680318832397461,
      "learning_rate": 1.6266472703396286e-05,
      "loss": 2.5174,
      "step": 104
    },
    {
      "epoch": 3.7636363636363637,
      "grad_norm": 0.09935521334409714,
      "learning_rate": 1.544686755065677e-05,
      "loss": 2.4874,
      "step": 105
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.0881587341427803,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.5488,
      "step": 106
    },
    {
      "epoch": 3.8363636363636364,
      "grad_norm": 0.07887379825115204,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 2.5687,
      "step": 107
    },
    {
      "epoch": 3.8727272727272726,
      "grad_norm": 0.08634869009256363,
      "learning_rate": 1.3094050125632972e-05,
      "loss": 2.5055,
      "step": 108
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 0.11330637335777283,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 2.6842,
      "step": 109
    },
    {
      "epoch": 3.9454545454545453,
      "grad_norm": 0.09345129877328873,
      "learning_rate": 1.1617762982099446e-05,
      "loss": 2.6974,
      "step": 110
    },
    {
      "epoch": 3.981818181818182,
      "grad_norm": 0.08921660482883453,
      "learning_rate": 1.090842587659851e-05,
      "loss": 2.4873,
      "step": 111
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.14685498178005219,
      "learning_rate": 1.0218772555910955e-05,
      "loss": 2.3899,
      "step": 112
    },
    {
      "epoch": 4.036363636363636,
      "grad_norm": 0.09091512113809586,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.5175,
      "step": 113
    },
    {
      "epoch": 4.072727272727272,
      "grad_norm": 0.09832193702459335,
      "learning_rate": 8.899896227604509e-06,
      "loss": 2.619,
      "step": 114
    },
    {
      "epoch": 4.109090909090909,
      "grad_norm": 0.09012377262115479,
      "learning_rate": 8.271337313934869e-06,
      "loss": 2.5263,
      "step": 115
    },
    {
      "epoch": 4.1454545454545455,
      "grad_norm": 0.11797353625297546,
      "learning_rate": 7.663790038585793e-06,
      "loss": 2.4268,
      "step": 116
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.11839454621076584,
      "learning_rate": 7.077560319906695e-06,
      "loss": 2.5537,
      "step": 117
    },
    {
      "epoch": 4.218181818181818,
      "grad_norm": 0.10103465616703033,
      "learning_rate": 6.5129433422152334e-06,
      "loss": 2.549,
      "step": 118
    },
    {
      "epoch": 4.254545454545455,
      "grad_norm": 0.09063795953989029,
      "learning_rate": 5.9702234071631e-06,
      "loss": 2.4557,
      "step": 119
    },
    {
      "epoch": 4.290909090909091,
      "grad_norm": 0.09372558444738388,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.5464,
      "step": 120
    },
    {
      "epoch": 4.327272727272727,
      "grad_norm": 0.0839313268661499,
      "learning_rate": 4.951556604879048e-06,
      "loss": 2.6524,
      "step": 121
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.1286299079656601,
      "learning_rate": 4.476122667059207e-06,
      "loss": 2.5412,
      "step": 122
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.08285991847515106,
      "learning_rate": 4.023611372427471e-06,
      "loss": 2.662,
      "step": 123
    },
    {
      "epoch": 4.4363636363636365,
      "grad_norm": 0.12856563925743103,
      "learning_rate": 3.5942505740480582e-06,
      "loss": 2.594,
      "step": 124
    },
    {
      "epoch": 4.472727272727273,
      "grad_norm": 0.11814769357442856,
      "learning_rate": 3.18825646801314e-06,
      "loss": 2.686,
      "step": 125
    },
    {
      "epoch": 4.509090909090909,
      "grad_norm": 0.1082761213183403,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 2.6269,
      "step": 126
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.09239254891872406,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.5522,
      "step": 127
    },
    {
      "epoch": 4.581818181818182,
      "grad_norm": 0.07280293852090836,
      "learning_rate": 2.1124591657534774e-06,
      "loss": 2.633,
      "step": 128
    },
    {
      "epoch": 4.618181818181818,
      "grad_norm": 0.1099616065621376,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 2.4609,
      "step": 129
    },
    {
      "epoch": 4.654545454545454,
      "grad_norm": 0.09694980084896088,
      "learning_rate": 1.5155239811656563e-06,
      "loss": 2.4482,
      "step": 130
    },
    {
      "epoch": 4.690909090909091,
      "grad_norm": 0.08924368768930435,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 2.6836,
      "step": 131
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.1000247597694397,
      "learning_rate": 1.016230078838226e-06,
      "loss": 2.5077,
      "step": 132
    },
    {
      "epoch": 4.763636363636364,
      "grad_norm": 0.10147857666015625,
      "learning_rate": 8.035205700685167e-07,
      "loss": 2.4779,
      "step": 133
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.08993665128946304,
      "learning_rate": 6.15582970243117e-07,
      "loss": 2.5392,
      "step": 134
    },
    {
      "epoch": 4.836363636363636,
      "grad_norm": 0.08087967336177826,
      "learning_rate": 4.52511911603265e-07,
      "loss": 2.5568,
      "step": 135
    },
    {
      "epoch": 4.872727272727273,
      "grad_norm": 0.08903863281011581,
      "learning_rate": 3.143895053378698e-07,
      "loss": 2.4965,
      "step": 136
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.11596190929412842,
      "learning_rate": 2.012853002380466e-07,
      "loss": 2.6761,
      "step": 137
    },
    {
      "epoch": 4.945454545454545,
      "grad_norm": 0.09576345235109329,
      "learning_rate": 1.132562476771959e-07,
      "loss": 2.691,
      "step": 138
    },
    {
      "epoch": 4.9818181818181815,
      "grad_norm": 0.08977144956588745,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 2.4818,
      "step": 139
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.15169349312782288,
      "learning_rate": 1.2588252874673468e-08,
      "loss": 2.3727,
      "step": 140
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.75,
      "eval_runtime": 4.0444,
      "eval_samples_per_second": 0.247,
      "eval_steps_per_second": 0.247,
      "step": 140
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.526945098655334e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}