{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 40,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 1.934841513633728,
      "learning_rate": 2e-05,
      "loss": 2.149,
      "step": 1
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 2.4779138565063477,
      "learning_rate": 4e-05,
      "loss": 2.7234,
      "step": 2
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 3.3968937397003174,
      "learning_rate": 6e-05,
      "loss": 2.9434,
      "step": 3
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 2.6924426555633545,
      "learning_rate": 8e-05,
      "loss": 2.9018,
      "step": 4
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 2.9207985401153564,
      "learning_rate": 0.0001,
      "loss": 2.8698,
      "step": 5
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.5849769115448,
      "learning_rate": 0.00012,
      "loss": 2.6004,
      "step": 6
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 2.265801191329956,
      "learning_rate": 0.00014,
      "loss": 1.9435,
      "step": 7
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.9821760654449463,
      "learning_rate": 0.00016,
      "loss": 2.3524,
      "step": 8
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 2.209989547729492,
      "learning_rate": 0.00018,
      "loss": 1.7031,
      "step": 9
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.4582831859588623,
      "learning_rate": 0.0002,
      "loss": 1.858,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 2.465235471725464,
      "learning_rate": 0.00019893617021276595,
      "loss": 1.9792,
      "step": 11
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 2.106245756149292,
      "learning_rate": 0.00019787234042553193,
      "loss": 1.6035,
      "step": 12
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 2.0670032501220703,
      "learning_rate": 0.00019680851063829787,
      "loss": 1.4089,
      "step": 13
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.869535207748413,
      "learning_rate": 0.00019574468085106384,
      "loss": 1.5282,
      "step": 14
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 2.4417788982391357,
      "learning_rate": 0.00019468085106382982,
      "loss": 2.0049,
      "step": 15
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 2.03873610496521,
      "learning_rate": 0.00019361702127659576,
      "loss": 1.5979,
      "step": 16
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 2.6959407329559326,
      "learning_rate": 0.0001925531914893617,
      "loss": 1.7192,
      "step": 17
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 2.447222948074341,
      "learning_rate": 0.00019148936170212768,
      "loss": 1.9945,
      "step": 18
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 2.0988619327545166,
      "learning_rate": 0.00019042553191489362,
      "loss": 1.5905,
      "step": 19
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 2.3013782501220703,
      "learning_rate": 0.00018936170212765957,
      "loss": 1.5003,
      "step": 20
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 2.080165147781372,
      "learning_rate": 0.00018829787234042554,
      "loss": 1.4736,
      "step": 21
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 4.3709940910339355,
      "learning_rate": 0.0001872340425531915,
      "loss": 0.9107,
      "step": 22
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 5.782566070556641,
      "learning_rate": 0.00018617021276595746,
      "loss": 1.3649,
      "step": 23
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.43636417388916,
      "learning_rate": 0.0001851063829787234,
      "loss": 1.2051,
      "step": 24
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 2.063096761703491,
      "learning_rate": 0.00018404255319148937,
      "loss": 1.1806,
      "step": 25
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 2.052663564682007,
      "learning_rate": 0.00018297872340425532,
      "loss": 1.1073,
      "step": 26
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 2.293409585952759,
      "learning_rate": 0.0001819148936170213,
      "loss": 1.3441,
      "step": 27
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 2.016857147216797,
      "learning_rate": 0.00018085106382978726,
      "loss": 1.1819,
      "step": 28
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 2.0556704998016357,
      "learning_rate": 0.0001797872340425532,
      "loss": 1.2543,
      "step": 29
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 2.157916784286499,
      "learning_rate": 0.00017872340425531915,
      "loss": 1.1889,
      "step": 30
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 2.284308671951294,
      "learning_rate": 0.00017765957446808512,
      "loss": 1.3205,
      "step": 31
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 2.55147123336792,
      "learning_rate": 0.00017659574468085107,
      "loss": 1.1276,
      "step": 32
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.595245599746704,
      "learning_rate": 0.000175531914893617,
      "loss": 1.2703,
      "step": 33
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 2.480912685394287,
      "learning_rate": 0.00017446808510638298,
      "loss": 0.9982,
      "step": 34
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 2.379316806793213,
      "learning_rate": 0.00017340425531914896,
      "loss": 1.1423,
      "step": 35
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 2.62664794921875,
      "learning_rate": 0.0001723404255319149,
      "loss": 1.1058,
      "step": 36
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 3.0421292781829834,
      "learning_rate": 0.00017127659574468087,
      "loss": 1.3554,
      "step": 37
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 2.338921308517456,
      "learning_rate": 0.00017021276595744682,
      "loss": 1.0576,
      "step": 38
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 2.2380709648132324,
      "learning_rate": 0.00016914893617021276,
      "loss": 0.96,
      "step": 39
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 2.5871872901916504,
      "learning_rate": 0.00016808510638297873,
      "loss": 1.1717,
      "step": 40
    },
    {
      "epoch": 0.20202020202020202,
      "eval_loss": 1.2117999792099,
      "eval_runtime": 35.7116,
      "eval_samples_per_second": 2.8,
      "eval_steps_per_second": 2.8,
      "step": 40
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 3.1568801403045654,
      "learning_rate": 0.00016702127659574468,
      "loss": 1.2266,
      "step": 41
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 2.2659265995025635,
      "learning_rate": 0.00016595744680851065,
      "loss": 0.9661,
      "step": 42
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 2.648207664489746,
      "learning_rate": 0.00016489361702127662,
      "loss": 1.4721,
      "step": 43
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.391132116317749,
      "learning_rate": 0.00016382978723404257,
      "loss": 1.1877,
      "step": 44
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 2.216590166091919,
      "learning_rate": 0.0001627659574468085,
      "loss": 1.1156,
      "step": 45
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 2.7304837703704834,
      "learning_rate": 0.00016170212765957446,
      "loss": 1.0745,
      "step": 46
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 2.449009418487549,
      "learning_rate": 0.00016063829787234043,
      "loss": 0.8261,
      "step": 47
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.8799259662628174,
      "learning_rate": 0.00015957446808510637,
      "loss": 1.3139,
      "step": 48
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 3.0433382987976074,
      "learning_rate": 0.00015851063829787235,
      "loss": 0.8179,
      "step": 49
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 1.923201322555542,
      "learning_rate": 0.00015744680851063832,
      "loss": 1.3833,
      "step": 50
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 2.040708303451538,
      "learning_rate": 0.00015638297872340426,
      "loss": 1.7501,
      "step": 51
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 1.4778690338134766,
      "learning_rate": 0.0001553191489361702,
      "loss": 0.9487,
      "step": 52
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 1.7248860597610474,
      "learning_rate": 0.00015425531914893618,
      "loss": 1.0579,
      "step": 53
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.6652686595916748,
      "learning_rate": 0.00015319148936170213,
      "loss": 0.9751,
      "step": 54
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.6558713912963867,
      "learning_rate": 0.0001521276595744681,
      "loss": 1.0705,
      "step": 55
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 2.045135259628296,
      "learning_rate": 0.00015106382978723407,
      "loss": 1.4438,
      "step": 56
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 2.0178723335266113,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1453,
      "step": 57
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 1.7096202373504639,
      "learning_rate": 0.00014893617021276596,
      "loss": 1.0412,
      "step": 58
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 2.039254665374756,
      "learning_rate": 0.00014787234042553193,
      "loss": 1.3789,
      "step": 59
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.7002921104431152,
      "learning_rate": 0.00014680851063829788,
      "loss": 1.9902,
      "step": 60
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 2.1051278114318848,
      "learning_rate": 0.00014574468085106382,
      "loss": 1.2287,
      "step": 61
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 2.6454594135284424,
      "learning_rate": 0.0001446808510638298,
      "loss": 1.3612,
      "step": 62
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.9458284378051758,
      "learning_rate": 0.00014361702127659576,
      "loss": 1.1879,
      "step": 63
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 2.09489369392395,
      "learning_rate": 0.0001425531914893617,
      "loss": 1.1563,
      "step": 64
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 1.8626444339752197,
      "learning_rate": 0.00014148936170212768,
      "loss": 0.8783,
      "step": 65
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.056874990463257,
      "learning_rate": 0.00014042553191489363,
      "loss": 1.1404,
      "step": 66
    },
    {
      "epoch": 0.3383838383838384,
      "grad_norm": 2.202636241912842,
      "learning_rate": 0.00013936170212765957,
      "loss": 1.2132,
      "step": 67
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 2.452498197555542,
      "learning_rate": 0.00013829787234042554,
      "loss": 1.451,
      "step": 68
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 3.745300769805908,
      "learning_rate": 0.0001372340425531915,
      "loss": 1.4522,
      "step": 69
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 2.425330638885498,
      "learning_rate": 0.00013617021276595746,
      "loss": 1.1973,
      "step": 70
    },
    {
      "epoch": 0.35858585858585856,
      "grad_norm": 3.9445061683654785,
      "learning_rate": 0.0001351063829787234,
      "loss": 0.6733,
      "step": 71
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.9044334888458252,
      "learning_rate": 0.00013404255319148938,
      "loss": 0.9999,
      "step": 72
    },
    {
      "epoch": 0.3686868686868687,
      "grad_norm": 2.4740421772003174,
      "learning_rate": 0.00013297872340425532,
      "loss": 1.2382,
      "step": 73
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 2.201266288757324,
      "learning_rate": 0.00013191489361702127,
      "loss": 0.9838,
      "step": 74
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 1.951281189918518,
      "learning_rate": 0.00013085106382978724,
      "loss": 0.888,
      "step": 75
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 1.6007189750671387,
      "learning_rate": 0.00012978723404255318,
      "loss": 0.7822,
      "step": 76
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 2.144460916519165,
      "learning_rate": 0.00012872340425531915,
      "loss": 0.9619,
      "step": 77
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 2.2907423973083496,
      "learning_rate": 0.00012765957446808513,
      "loss": 1.1213,
      "step": 78
    },
    {
      "epoch": 0.398989898989899,
      "grad_norm": 2.3168041706085205,
      "learning_rate": 0.00012659574468085107,
      "loss": 1.0892,
      "step": 79
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 2.5245144367218018,
      "learning_rate": 0.00012553191489361702,
      "loss": 1.1852,
      "step": 80
    },
    {
      "epoch": 0.40404040404040403,
      "eval_loss": 1.081834077835083,
      "eval_runtime": 35.7648,
      "eval_samples_per_second": 2.796,
      "eval_steps_per_second": 2.796,
      "step": 80
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 3.342719316482544,
      "learning_rate": 0.000124468085106383,
      "loss": 1.5945,
      "step": 81
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 1.9120285511016846,
      "learning_rate": 0.00012340425531914893,
      "loss": 0.8123,
      "step": 82
    },
    {
      "epoch": 0.41919191919191917,
      "grad_norm": 2.2346291542053223,
      "learning_rate": 0.0001223404255319149,
      "loss": 0.7541,
      "step": 83
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 2.395176649093628,
      "learning_rate": 0.00012127659574468086,
      "loss": 1.2209,
      "step": 84
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 2.275162696838379,
      "learning_rate": 0.00012021276595744682,
      "loss": 1.06,
      "step": 85
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 2.27367901802063,
      "learning_rate": 0.00011914893617021277,
      "loss": 1.0375,
      "step": 86
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 2.6139156818389893,
      "learning_rate": 0.00011808510638297874,
      "loss": 1.1906,
      "step": 87
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.0727851390838623,
      "learning_rate": 0.00011702127659574468,
      "loss": 0.9182,
      "step": 88
    },
    {
      "epoch": 0.4494949494949495,
      "grad_norm": 2.6906633377075195,
      "learning_rate": 0.00011595744680851064,
      "loss": 1.0941,
      "step": 89
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.9968316555023193,
      "learning_rate": 0.00011489361702127661,
      "loss": 0.9502,
      "step": 90
    },
    {
      "epoch": 0.4595959595959596,
      "grad_norm": 1.800660490989685,
      "learning_rate": 0.00011382978723404256,
      "loss": 0.7118,
      "step": 91
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 1.7916479110717773,
      "learning_rate": 0.00011276595744680852,
      "loss": 0.5925,
      "step": 92
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 2.894232988357544,
      "learning_rate": 0.00011170212765957446,
      "loss": 1.1137,
      "step": 93
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 2.5062479972839355,
      "learning_rate": 0.00011063829787234043,
      "loss": 0.9837,
      "step": 94
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 2.5845303535461426,
      "learning_rate": 0.00010957446808510638,
      "loss": 1.1791,
      "step": 95
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 2.2351789474487305,
      "learning_rate": 0.00010851063829787234,
      "loss": 0.7262,
      "step": 96
    },
    {
      "epoch": 0.4898989898989899,
      "grad_norm": 2.842940330505371,
      "learning_rate": 0.00010744680851063831,
      "loss": 1.115,
      "step": 97
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 2.390490770339966,
      "learning_rate": 0.00010638297872340425,
      "loss": 0.7784,
      "step": 98
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.5551937818527222,
      "learning_rate": 0.00010531914893617021,
      "loss": 1.323,
      "step": 99
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 1.6265314817428589,
      "learning_rate": 0.00010425531914893618,
      "loss": 0.9718,
      "step": 100
    },
    {
      "epoch": 0.51010101010101,
      "grad_norm": 1.7489873170852661,
      "learning_rate": 0.00010319148936170213,
      "loss": 1.1333,
      "step": 101
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 1.857285737991333,
      "learning_rate": 0.00010212765957446809,
      "loss": 1.2764,
      "step": 102
    },
    {
      "epoch": 0.5202020202020202,
      "grad_norm": 1.7422451972961426,
      "learning_rate": 0.00010106382978723406,
      "loss": 1.3637,
      "step": 103
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 1.1181117296218872,
      "learning_rate": 0.0001,
      "loss": 0.8533,
      "step": 104
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 1.7180590629577637,
      "learning_rate": 9.893617021276596e-05,
      "loss": 1.231,
      "step": 105
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 1.6332601308822632,
      "learning_rate": 9.787234042553192e-05,
      "loss": 1.1621,
      "step": 106
    },
    {
      "epoch": 0.5404040404040404,
      "grad_norm": 2.0528311729431152,
      "learning_rate": 9.680851063829788e-05,
      "loss": 1.3896,
      "step": 107
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.4702327251434326,
      "learning_rate": 9.574468085106384e-05,
      "loss": 0.9355,
      "step": 108
    },
    {
      "epoch": 0.5505050505050505,
      "grad_norm": 1.9625461101531982,
      "learning_rate": 9.468085106382978e-05,
      "loss": 1.5606,
      "step": 109
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.784745693206787,
      "learning_rate": 9.361702127659576e-05,
      "loss": 1.1102,
      "step": 110
    },
    {
      "epoch": 0.5606060606060606,
      "grad_norm": 2.0343940258026123,
      "learning_rate": 9.25531914893617e-05,
      "loss": 1.2201,
      "step": 111
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 1.4346604347229004,
      "learning_rate": 9.148936170212766e-05,
      "loss": 0.7823,
      "step": 112
    },
    {
      "epoch": 0.5707070707070707,
      "grad_norm": 1.9893382787704468,
      "learning_rate": 9.042553191489363e-05,
      "loss": 1.0692,
      "step": 113
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 2.1041550636291504,
      "learning_rate": 8.936170212765958e-05,
      "loss": 1.4054,
      "step": 114
    },
    {
      "epoch": 0.5808080808080808,
      "grad_norm": 2.3176534175872803,
      "learning_rate": 8.829787234042553e-05,
      "loss": 1.4864,
      "step": 115
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 1.7559845447540283,
      "learning_rate": 8.723404255319149e-05,
      "loss": 0.8039,
      "step": 116
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 1.7945481538772583,
      "learning_rate": 8.617021276595745e-05,
      "loss": 0.9355,
      "step": 117
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 1.5018421411514282,
      "learning_rate": 8.510638297872341e-05,
      "loss": 0.8087,
      "step": 118
    },
    {
      "epoch": 0.601010101010101,
      "grad_norm": 1.6970769166946411,
      "learning_rate": 8.404255319148937e-05,
      "loss": 0.8562,
      "step": 119
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.8440420627593994,
      "learning_rate": 8.297872340425533e-05,
      "loss": 1.2596,
      "step": 120
    },
    {
      "epoch": 0.6060606060606061,
      "eval_loss": 1.025399088859558,
      "eval_runtime": 35.717,
      "eval_samples_per_second": 2.8,
      "eval_steps_per_second": 2.8,
      "step": 120
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 2.990412712097168,
      "learning_rate": 8.191489361702128e-05,
      "loss": 1.1597,
      "step": 121
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 1.3564014434814453,
      "learning_rate": 8.085106382978723e-05,
      "loss": 0.7068,
      "step": 122
    },
    {
      "epoch": 0.6212121212121212,
      "grad_norm": 2.5022084712982178,
      "learning_rate": 7.978723404255319e-05,
      "loss": 1.6883,
      "step": 123
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 1.8736674785614014,
      "learning_rate": 7.872340425531916e-05,
      "loss": 0.6924,
      "step": 124
    },
    {
      "epoch": 0.6313131313131313,
      "grad_norm": 2.2267813682556152,
      "learning_rate": 7.76595744680851e-05,
      "loss": 1.1193,
      "step": 125
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.134420156478882,
      "learning_rate": 7.659574468085106e-05,
      "loss": 0.9352,
      "step": 126
    },
    {
      "epoch": 0.6414141414141414,
      "grad_norm": 1.9499320983886719,
      "learning_rate": 7.553191489361703e-05,
      "loss": 0.8882,
      "step": 127
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 2.1963298320770264,
      "learning_rate": 7.446808510638298e-05,
      "loss": 0.8756,
      "step": 128
    },
    {
      "epoch": 0.6515151515151515,
      "grad_norm": 2.303020715713501,
      "learning_rate": 7.340425531914894e-05,
      "loss": 0.903,
      "step": 129
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 2.4283013343811035,
      "learning_rate": 7.23404255319149e-05,
      "loss": 1.2209,
      "step": 130
    },
    {
      "epoch": 0.6616161616161617,
      "grad_norm": 1.8416250944137573,
      "learning_rate": 7.127659574468085e-05,
      "loss": 0.8485,
      "step": 131
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.958123803138733,
      "learning_rate": 7.021276595744681e-05,
      "loss": 0.955,
      "step": 132
    },
    {
      "epoch": 0.6717171717171717,
      "grad_norm": 2.2823963165283203,
      "learning_rate": 6.914893617021277e-05,
      "loss": 0.9205,
      "step": 133
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 2.2370712757110596,
      "learning_rate": 6.808510638297873e-05,
      "loss": 0.7799,
      "step": 134
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 2.6467502117156982,
      "learning_rate": 6.702127659574469e-05,
      "loss": 1.0801,
      "step": 135
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 2.9221208095550537,
      "learning_rate": 6.595744680851063e-05,
      "loss": 1.2855,
      "step": 136
    },
    {
      "epoch": 0.6919191919191919,
      "grad_norm": 2.024229049682617,
      "learning_rate": 6.489361702127659e-05,
      "loss": 0.7463,
      "step": 137
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 2.125941276550293,
      "learning_rate": 6.382978723404256e-05,
      "loss": 0.8951,
      "step": 138
    },
    {
      "epoch": 0.702020202020202,
      "grad_norm": 2.9005520343780518,
      "learning_rate": 6.276595744680851e-05,
      "loss": 0.7212,
      "step": 139
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 2.088212251663208,
      "learning_rate": 6.170212765957447e-05,
      "loss": 0.6987,
      "step": 140
    },
    {
      "epoch": 0.7121212121212122,
      "grad_norm": 2.779832124710083,
      "learning_rate": 6.063829787234043e-05,
      "loss": 1.2843,
      "step": 141
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 1.8998260498046875,
      "learning_rate": 5.9574468085106384e-05,
      "loss": 0.7472,
      "step": 142
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 2.266793727874756,
      "learning_rate": 5.851063829787234e-05,
      "loss": 0.7037,
      "step": 143
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.3124566078186035,
      "learning_rate": 5.744680851063831e-05,
      "loss": 1.0372,
      "step": 144
    },
    {
      "epoch": 0.7323232323232324,
      "grad_norm": 3.8273227214813232,
      "learning_rate": 5.638297872340426e-05,
      "loss": 1.1066,
      "step": 145
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 1.7611407041549683,
      "learning_rate": 5.531914893617022e-05,
      "loss": 0.5528,
      "step": 146
    },
    {
      "epoch": 0.7424242424242424,
      "grad_norm": 1.3345385789871216,
      "learning_rate": 5.425531914893617e-05,
      "loss": 0.533,
      "step": 147
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 1.5304288864135742,
      "learning_rate": 5.319148936170213e-05,
      "loss": 1.1614,
      "step": 148
    },
    {
      "epoch": 0.7525252525252525,
      "grad_norm": 2.2307026386260986,
      "learning_rate": 5.212765957446809e-05,
      "loss": 1.7027,
      "step": 149
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 2.0783305168151855,
      "learning_rate": 5.1063829787234044e-05,
      "loss": 1.5548,
      "step": 150
    },
    {
      "epoch": 0.7626262626262627,
      "grad_norm": 1.9879854917526245,
      "learning_rate": 5e-05,
      "loss": 1.3791,
      "step": 151
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 1.6240109205245972,
      "learning_rate": 4.893617021276596e-05,
      "loss": 1.0744,
      "step": 152
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 2.711182117462158,
      "learning_rate": 4.787234042553192e-05,
      "loss": 1.5953,
      "step": 153
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.7542715072631836,
      "learning_rate": 4.680851063829788e-05,
      "loss": 0.8801,
      "step": 154
    },
    {
      "epoch": 0.7828282828282829,
      "grad_norm": 2.7338082790374756,
      "learning_rate": 4.574468085106383e-05,
      "loss": 2.0285,
      "step": 155
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 1.4537471532821655,
      "learning_rate": 4.468085106382979e-05,
      "loss": 0.7417,
      "step": 156
    },
    {
      "epoch": 0.7929292929292929,
      "grad_norm": 1.9007015228271484,
      "learning_rate": 4.3617021276595746e-05,
      "loss": 1.1665,
      "step": 157
    },
    {
      "epoch": 0.797979797979798,
      "grad_norm": 1.6936357021331787,
      "learning_rate": 4.2553191489361704e-05,
      "loss": 0.9482,
      "step": 158
    },
    {
      "epoch": 0.803030303030303,
      "grad_norm": 1.923112392425537,
      "learning_rate": 4.148936170212766e-05,
      "loss": 1.1103,
      "step": 159
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 1.7348624467849731,
      "learning_rate": 4.0425531914893614e-05,
      "loss": 0.785,
      "step": 160
    },
    {
      "epoch": 0.8080808080808081,
      "eval_loss": 1.0044422149658203,
      "eval_runtime": 35.7191,
      "eval_samples_per_second": 2.8,
      "eval_steps_per_second": 2.8,
      "step": 160
    },
    {
      "epoch": 0.8131313131313131,
      "grad_norm": 2.3853325843811035,
      "learning_rate": 3.936170212765958e-05,
      "loss": 1.2953,
      "step": 161
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.5539531707763672,
      "learning_rate": 3.829787234042553e-05,
      "loss": 0.7532,
      "step": 162
    },
    {
      "epoch": 0.8232323232323232,
      "grad_norm": 2.0018396377563477,
      "learning_rate": 3.723404255319149e-05,
      "loss": 1.0277,
      "step": 163
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 1.8975419998168945,
      "learning_rate": 3.617021276595745e-05,
      "loss": 0.84,
      "step": 164
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.150519847869873,
      "learning_rate": 3.5106382978723407e-05,
      "loss": 0.9874,
      "step": 165
    },
    {
      "epoch": 0.8383838383838383,
      "grad_norm": 2.172685384750366,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 1.1271,
      "step": 166
    },
    {
      "epoch": 0.8434343434343434,
      "grad_norm": 2.1147804260253906,
      "learning_rate": 3.2978723404255317e-05,
      "loss": 0.8757,
      "step": 167
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 2.024099588394165,
      "learning_rate": 3.191489361702128e-05,
      "loss": 1.2143,
      "step": 168
    },
    {
      "epoch": 0.8535353535353535,
      "grad_norm": 2.0407485961914062,
      "learning_rate": 3.085106382978723e-05,
      "loss": 1.0318,
      "step": 169
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 2.056114435195923,
      "learning_rate": 2.9787234042553192e-05,
      "loss": 1.0286,
      "step": 170
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 2.441153049468994,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 1.3128,
      "step": 171
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 2.1208486557006836,
      "learning_rate": 2.765957446808511e-05,
      "loss": 0.7569,
      "step": 172
    },
    {
      "epoch": 0.8737373737373737,
      "grad_norm": 2.4818294048309326,
      "learning_rate": 2.6595744680851064e-05,
      "loss": 1.5236,
      "step": 173
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 1.9016083478927612,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.7904,
      "step": 174
    },
    {
      "epoch": 0.8838383838383839,
      "grad_norm": 2.479365348815918,
      "learning_rate": 2.446808510638298e-05,
      "loss": 1.3812,
      "step": 175
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.3161561489105225,
      "learning_rate": 2.340425531914894e-05,
      "loss": 1.1612,
      "step": 176
    },
    {
      "epoch": 0.8939393939393939,
      "grad_norm": 1.7003121376037598,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.7709,
      "step": 177
    },
    {
      "epoch": 0.898989898989899,
      "grad_norm": 2.0750014781951904,
      "learning_rate": 2.1276595744680852e-05,
      "loss": 1.0438,
      "step": 178
    },
    {
      "epoch": 0.9040404040404041,
      "grad_norm": 1.7369530200958252,
      "learning_rate": 2.0212765957446807e-05,
      "loss": 0.711,
      "step": 179
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.7840030193328857,
      "learning_rate": 1.9148936170212766e-05,
      "loss": 0.7699,
      "step": 180
    },
    {
      "epoch": 0.9141414141414141,
      "grad_norm": 1.9962245225906372,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 1.0592,
      "step": 181
    },
    {
      "epoch": 0.9191919191919192,
      "grad_norm": 1.862483024597168,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 0.855,
      "step": 182
    },
    {
      "epoch": 0.9242424242424242,
      "grad_norm": 1.5625897645950317,
      "learning_rate": 1.595744680851064e-05,
      "loss": 0.6401,
      "step": 183
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 2.1147549152374268,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 0.9002,
      "step": 184
    },
    {
      "epoch": 0.9343434343434344,
      "grad_norm": 1.6960692405700684,
      "learning_rate": 1.3829787234042554e-05,
      "loss": 0.7592,
      "step": 185
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 2.3449957370758057,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 1.1498,
      "step": 186
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 1.868044376373291,
      "learning_rate": 1.170212765957447e-05,
      "loss": 0.8678,
      "step": 187
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 2.05068039894104,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 0.7825,
      "step": 188
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 1.92442786693573,
      "learning_rate": 9.574468085106383e-06,
      "loss": 0.7249,
      "step": 189
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 2.1448285579681396,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.9544,
      "step": 190
    },
    {
      "epoch": 0.9646464646464646,
      "grad_norm": 1.7718862295150757,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.5564,
      "step": 191
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 2.5203495025634766,
      "learning_rate": 6.3829787234042555e-06,
      "loss": 0.9661,
      "step": 192
    },
    {
      "epoch": 0.9747474747474747,
      "grad_norm": 2.2129266262054443,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.9277,
      "step": 193
    },
    {
      "epoch": 0.9797979797979798,
      "grad_norm": 2.0742154121398926,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.8203,
      "step": 194
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 1.7061251401901245,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.4595,
      "step": 195
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.7450275421142578,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.5028,
      "step": 196
    },
    {
      "epoch": 0.9949494949494949,
      "grad_norm": 4.231220245361328,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 1.0582,
      "step": 197
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.37825870513916,
      "learning_rate": 0.0,
      "loss": 0.8417,
      "step": 198
    }
  ],
  "logging_steps": 1,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2341997358425088.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}