{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9974025974025974,
  "eval_steps": 500,
  "global_step": 192,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005194805194805195,
      "grad_norm": 0.7348681092262268,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1176,
      "step": 1
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 1.1035295724868774,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1321,
      "step": 2
    },
    {
      "epoch": 0.015584415584415584,
      "grad_norm": 1.2580022811889648,
      "learning_rate": 3e-06,
      "loss": 0.175,
      "step": 3
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 1.3372018337249756,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1719,
      "step": 4
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 1.0590356588363647,
      "learning_rate": 5e-06,
      "loss": 0.1417,
      "step": 5
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 1.2326946258544922,
      "learning_rate": 6e-06,
      "loss": 0.1663,
      "step": 6
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 1.2802666425704956,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.1627,
      "step": 7
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 1.7023444175720215,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2033,
      "step": 8
    },
    {
      "epoch": 0.046753246753246755,
      "grad_norm": 1.865265130996704,
      "learning_rate": 9e-06,
      "loss": 0.2245,
      "step": 9
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 1.4213303327560425,
      "learning_rate": 1e-05,
      "loss": 0.204,
      "step": 10
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.4797700643539429,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.2106,
      "step": 11
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 1.4369184970855713,
      "learning_rate": 1.2e-05,
      "loss": 0.2318,
      "step": 12
    },
    {
      "epoch": 0.06753246753246753,
      "grad_norm": 1.5280572175979614,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.2091,
      "step": 13
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 1.4684967994689941,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.2221,
      "step": 14
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 1.455448865890503,
      "learning_rate": 1.5e-05,
      "loss": 0.2013,
      "step": 15
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 1.1584417819976807,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1724,
      "step": 16
    },
    {
      "epoch": 0.08831168831168831,
      "grad_norm": 1.0573651790618896,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.1652,
      "step": 17
    },
    {
      "epoch": 0.09350649350649351,
      "grad_norm": 1.371899127960205,
      "learning_rate": 1.8e-05,
      "loss": 0.1725,
      "step": 18
    },
    {
      "epoch": 0.0987012987012987,
      "grad_norm": 1.510654330253601,
      "learning_rate": 1.9e-05,
      "loss": 0.154,
      "step": 19
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 1.5230462551116943,
      "learning_rate": 2e-05,
      "loss": 0.1627,
      "step": 20
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.4010649919509888,
      "learning_rate": 2.1e-05,
      "loss": 0.1222,
      "step": 21
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.6453959941864014,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1658,
      "step": 22
    },
    {
      "epoch": 0.11948051948051948,
      "grad_norm": 1.567714810371399,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.1472,
      "step": 23
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 1.2120919227600098,
      "learning_rate": 2.4e-05,
      "loss": 0.1255,
      "step": 24
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 1.0383350849151611,
      "learning_rate": 2.5e-05,
      "loss": 0.1011,
      "step": 25
    },
    {
      "epoch": 0.13506493506493505,
      "grad_norm": 1.0396440029144287,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0869,
      "step": 26
    },
    {
      "epoch": 0.14025974025974025,
      "grad_norm": 0.9570748209953308,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.1285,
      "step": 27
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 1.2089506387710571,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.1664,
      "step": 28
    },
    {
      "epoch": 0.15064935064935064,
      "grad_norm": 1.1845204830169678,
      "learning_rate": 2.9e-05,
      "loss": 0.1443,
      "step": 29
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 1.1316490173339844,
      "learning_rate": 3e-05,
      "loss": 0.1171,
      "step": 30
    },
    {
      "epoch": 0.16103896103896104,
      "grad_norm": 1.1125231981277466,
      "learning_rate": 3.1e-05,
      "loss": 0.1114,
      "step": 31
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 1.0736544132232666,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1364,
      "step": 32
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.2718521356582642,
      "learning_rate": 3.3e-05,
      "loss": 0.1248,
      "step": 33
    },
    {
      "epoch": 0.17662337662337663,
      "grad_norm": 1.044920563697815,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.1599,
      "step": 34
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.048309326171875,
      "learning_rate": 3.5e-05,
      "loss": 0.1018,
      "step": 35
    },
    {
      "epoch": 0.18701298701298702,
      "grad_norm": 1.188143253326416,
      "learning_rate": 3.6e-05,
      "loss": 0.1066,
      "step": 36
    },
    {
      "epoch": 0.19220779220779222,
      "grad_norm": 1.1182760000228882,
      "learning_rate": 3.7e-05,
      "loss": 0.1144,
      "step": 37
    },
    {
      "epoch": 0.1974025974025974,
      "grad_norm": 1.3745020627975464,
      "learning_rate": 3.8e-05,
      "loss": 0.1151,
      "step": 38
    },
    {
      "epoch": 0.2025974025974026,
      "grad_norm": 1.270022988319397,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.105,
      "step": 39
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 1.127374529838562,
      "learning_rate": 4e-05,
      "loss": 0.0753,
      "step": 40
    },
    {
      "epoch": 0.21298701298701297,
      "grad_norm": 1.534313440322876,
      "learning_rate": 4.1e-05,
      "loss": 0.1033,
      "step": 41
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.275597095489502,
      "learning_rate": 4.2e-05,
      "loss": 0.0934,
      "step": 42
    },
    {
      "epoch": 0.22337662337662337,
      "grad_norm": 1.3352851867675781,
      "learning_rate": 4.3e-05,
      "loss": 0.0799,
      "step": 43
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.0107558965682983,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.051,
      "step": 44
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 1.5169721841812134,
      "learning_rate": 4.5e-05,
      "loss": 0.0851,
      "step": 45
    },
    {
      "epoch": 0.23896103896103896,
      "grad_norm": 1.3949077129364014,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.056,
      "step": 46
    },
    {
      "epoch": 0.24415584415584415,
      "grad_norm": 2.4606387615203857,
      "learning_rate": 4.7e-05,
      "loss": 0.0908,
      "step": 47
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 1.214357852935791,
      "learning_rate": 4.8e-05,
      "loss": 0.0666,
      "step": 48
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.6610214710235596,
      "learning_rate": 4.9e-05,
      "loss": 0.1052,
      "step": 49
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.5138863325119019,
      "learning_rate": 5e-05,
      "loss": 0.0637,
      "step": 50
    },
    {
      "epoch": 0.2649350649350649,
      "grad_norm": 0.5497398972511292,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 0.067,
      "step": 51
    },
    {
      "epoch": 0.2701298701298701,
      "grad_norm": 0.42988669872283936,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0731,
      "step": 52
    },
    {
      "epoch": 0.2753246753246753,
      "grad_norm": 0.6532320380210876,
      "learning_rate": 5.300000000000001e-05,
      "loss": 0.0801,
      "step": 53
    },
    {
      "epoch": 0.2805194805194805,
      "grad_norm": 0.42246320843696594,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.072,
      "step": 54
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.5593151450157166,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0853,
      "step": 55
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.5805220603942871,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.081,
      "step": 56
    },
    {
      "epoch": 0.2961038961038961,
      "grad_norm": 0.37391534447669983,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.0729,
      "step": 57
    },
    {
      "epoch": 0.3012987012987013,
      "grad_norm": 0.49738189578056335,
      "learning_rate": 5.8e-05,
      "loss": 0.0819,
      "step": 58
    },
    {
      "epoch": 0.3064935064935065,
      "grad_norm": 0.5514347553253174,
      "learning_rate": 5.9e-05,
      "loss": 0.0855,
      "step": 59
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.48092907667160034,
      "learning_rate": 6e-05,
      "loss": 0.0906,
      "step": 60
    },
    {
      "epoch": 0.3168831168831169,
      "grad_norm": 0.4961753487586975,
      "learning_rate": 6.1e-05,
      "loss": 0.0759,
      "step": 61
    },
    {
      "epoch": 0.3220779220779221,
      "grad_norm": 0.551651120185852,
      "learning_rate": 6.2e-05,
      "loss": 0.0921,
      "step": 62
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.4834372401237488,
      "learning_rate": 6.3e-05,
      "loss": 0.0777,
      "step": 63
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 0.5103281736373901,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.098,
      "step": 64
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 0.6696719527244568,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.116,
      "step": 65
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.6199856400489807,
      "learning_rate": 6.6e-05,
      "loss": 0.0771,
      "step": 66
    },
    {
      "epoch": 0.34805194805194806,
      "grad_norm": 0.6140097975730896,
      "learning_rate": 6.7e-05,
      "loss": 0.0731,
      "step": 67
    },
    {
      "epoch": 0.35324675324675325,
      "grad_norm": 0.5712923407554626,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.1035,
      "step": 68
    },
    {
      "epoch": 0.35844155844155845,
      "grad_norm": 0.589288592338562,
      "learning_rate": 6.9e-05,
      "loss": 0.0751,
      "step": 69
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.5890541672706604,
      "learning_rate": 7e-05,
      "loss": 0.075,
      "step": 70
    },
    {
      "epoch": 0.36883116883116884,
      "grad_norm": 0.45749178528785706,
      "learning_rate": 7.1e-05,
      "loss": 0.0562,
      "step": 71
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 0.6687325239181519,
      "learning_rate": 7.2e-05,
      "loss": 0.0912,
      "step": 72
    },
    {
      "epoch": 0.37922077922077924,
      "grad_norm": 0.7040101289749146,
      "learning_rate": 7.3e-05,
      "loss": 0.0576,
      "step": 73
    },
    {
      "epoch": 0.38441558441558443,
      "grad_norm": 0.6892087459564209,
      "learning_rate": 7.4e-05,
      "loss": 0.1074,
      "step": 74
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.6543079018592834,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0711,
      "step": 75
    },
    {
      "epoch": 0.3948051948051948,
      "grad_norm": 0.5497643947601318,
      "learning_rate": 7.6e-05,
      "loss": 0.07,
      "step": 76
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.032709002494812,
      "learning_rate": 7.7e-05,
      "loss": 0.1112,
      "step": 77
    },
    {
      "epoch": 0.4051948051948052,
      "grad_norm": 0.8282528519630432,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0773,
      "step": 78
    },
    {
      "epoch": 0.4103896103896104,
      "grad_norm": 0.9200804829597473,
      "learning_rate": 7.900000000000001e-05,
      "loss": 0.1168,
      "step": 79
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.8927801251411438,
      "learning_rate": 8e-05,
      "loss": 0.0823,
      "step": 80
    },
    {
      "epoch": 0.42077922077922075,
      "grad_norm": 0.6470887064933777,
      "learning_rate": 8.1e-05,
      "loss": 0.0732,
      "step": 81
    },
    {
      "epoch": 0.42597402597402595,
      "grad_norm": 0.8244249224662781,
      "learning_rate": 8.2e-05,
      "loss": 0.0829,
      "step": 82
    },
    {
      "epoch": 0.43116883116883115,
      "grad_norm": 0.8465301394462585,
      "learning_rate": 8.3e-05,
      "loss": 0.0856,
      "step": 83
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.8131994605064392,
      "learning_rate": 8.4e-05,
      "loss": 0.0749,
      "step": 84
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 0.8314535617828369,
      "learning_rate": 8.5e-05,
      "loss": 0.0825,
      "step": 85
    },
    {
      "epoch": 0.44675324675324674,
      "grad_norm": 0.6636279821395874,
      "learning_rate": 8.6e-05,
      "loss": 0.0521,
      "step": 86
    },
    {
      "epoch": 0.45194805194805193,
      "grad_norm": 0.6932604908943176,
      "learning_rate": 8.7e-05,
      "loss": 0.081,
      "step": 87
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.9526130557060242,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0717,
      "step": 88
    },
    {
      "epoch": 0.4623376623376623,
      "grad_norm": 1.168262004852295,
      "learning_rate": 8.900000000000001e-05,
      "loss": 0.1186,
      "step": 89
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.9426000118255615,
      "learning_rate": 9e-05,
      "loss": 0.061,
      "step": 90
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.9636326432228088,
      "learning_rate": 9.1e-05,
      "loss": 0.0465,
      "step": 91
    },
    {
      "epoch": 0.4779220779220779,
      "grad_norm": 1.1435465812683105,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0582,
      "step": 92
    },
    {
      "epoch": 0.4831168831168831,
      "grad_norm": 1.5965853929519653,
      "learning_rate": 9.300000000000001e-05,
      "loss": 0.0517,
      "step": 93
    },
    {
      "epoch": 0.4883116883116883,
      "grad_norm": 0.8533312678337097,
      "learning_rate": 9.4e-05,
      "loss": 0.0544,
      "step": 94
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 1.580448031425476,
      "learning_rate": 9.5e-05,
      "loss": 0.0856,
      "step": 95
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 2.2591030597686768,
      "learning_rate": 9.6e-05,
      "loss": 0.1286,
      "step": 96
    },
    {
      "epoch": 0.5038961038961038,
      "grad_norm": 0.45918163657188416,
      "learning_rate": 9.7e-05,
      "loss": 0.0554,
      "step": 97
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.5378842353820801,
      "learning_rate": 9.8e-05,
      "loss": 0.0721,
      "step": 98
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.5227073431015015,
      "learning_rate": 9.900000000000001e-05,
      "loss": 0.0765,
      "step": 99
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.36160627007484436,
      "learning_rate": 0.0001,
      "loss": 0.0497,
      "step": 100
    },
    {
      "epoch": 0.5246753246753246,
      "grad_norm": 0.4156610071659088,
      "learning_rate": 9.99708511183087e-05,
      "loss": 0.058,
      "step": 101
    },
    {
      "epoch": 0.5298701298701298,
      "grad_norm": 0.3888299763202667,
      "learning_rate": 9.988343845952697e-05,
      "loss": 0.0546,
      "step": 102
    },
    {
      "epoch": 0.535064935064935,
      "grad_norm": 0.5655276775360107,
      "learning_rate": 9.973786394290474e-05,
      "loss": 0.104,
      "step": 103
    },
    {
      "epoch": 0.5402597402597402,
      "grad_norm": 0.4400051236152649,
      "learning_rate": 9.953429730181653e-05,
      "loss": 0.0481,
      "step": 104
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.47867313027381897,
      "learning_rate": 9.927297588585984e-05,
      "loss": 0.0681,
      "step": 105
    },
    {
      "epoch": 0.5506493506493506,
      "grad_norm": 0.46361789107322693,
      "learning_rate": 9.895420438411616e-05,
      "loss": 0.0613,
      "step": 106
    },
    {
      "epoch": 0.5558441558441558,
      "grad_norm": 0.5095213055610657,
      "learning_rate": 9.857835446989707e-05,
      "loss": 0.0747,
      "step": 107
    },
    {
      "epoch": 0.561038961038961,
      "grad_norm": 0.40775981545448303,
      "learning_rate": 9.814586436738998e-05,
      "loss": 0.0519,
      "step": 108
    },
    {
      "epoch": 0.5662337662337662,
      "grad_norm": 0.5310682654380798,
      "learning_rate": 9.765723834070804e-05,
      "loss": 0.0791,
      "step": 109
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.5329816937446594,
      "learning_rate": 9.711304610594104e-05,
      "loss": 0.0641,
      "step": 110
    },
    {
      "epoch": 0.5766233766233766,
      "grad_norm": 0.5039582252502441,
      "learning_rate": 9.651392216689165e-05,
      "loss": 0.0825,
      "step": 111
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.5031707882881165,
      "learning_rate": 9.586056507527266e-05,
      "loss": 0.081,
      "step": 112
    },
    {
      "epoch": 0.587012987012987,
      "grad_norm": 0.48035717010498047,
      "learning_rate": 9.515373661622664e-05,
      "loss": 0.0663,
      "step": 113
    },
    {
      "epoch": 0.5922077922077922,
      "grad_norm": 0.49094316363334656,
      "learning_rate": 9.439426092011875e-05,
      "loss": 0.0548,
      "step": 114
    },
    {
      "epoch": 0.5974025974025974,
      "grad_norm": 0.5882694721221924,
      "learning_rate": 9.358302350163757e-05,
      "loss": 0.0618,
      "step": 115
    },
    {
      "epoch": 0.6025974025974026,
      "grad_norm": 0.4960368871688843,
      "learning_rate": 9.272097022732443e-05,
      "loss": 0.061,
      "step": 116
    },
    {
      "epoch": 0.6077922077922078,
      "grad_norm": 0.5670976042747498,
      "learning_rate": 9.180910621273555e-05,
      "loss": 0.0602,
      "step": 117
    },
    {
      "epoch": 0.612987012987013,
      "grad_norm": 0.6008670926094055,
      "learning_rate": 9.08484946505221e-05,
      "loss": 0.078,
      "step": 118
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 0.5733016133308411,
      "learning_rate": 8.984025557079523e-05,
      "loss": 0.0801,
      "step": 119
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.5101535320281982,
      "learning_rate": 8.8785564535221e-05,
      "loss": 0.0651,
      "step": 120
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.6034821271896362,
      "learning_rate": 8.768565126636806e-05,
      "loss": 0.0639,
      "step": 121
    },
    {
      "epoch": 0.6337662337662338,
      "grad_norm": 0.9439027905464172,
      "learning_rate": 8.654179821390621e-05,
      "loss": 0.0962,
      "step": 122
    },
    {
      "epoch": 0.638961038961039,
      "grad_norm": 3.3555190563201904,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0897,
      "step": 123
    },
    {
      "epoch": 0.6441558441558441,
      "grad_norm": 3.670668840408325,
      "learning_rate": 8.412765716093272e-05,
      "loss": 0.1052,
      "step": 124
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 1.6730693578720093,
      "learning_rate": 8.286018394089863e-05,
      "loss": 0.0675,
      "step": 125
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.7154898643493652,
      "learning_rate": 8.155439721630264e-05,
      "loss": 0.0841,
      "step": 126
    },
    {
      "epoch": 0.6597402597402597,
      "grad_norm": 0.7675151824951172,
      "learning_rate": 8.021181947605473e-05,
      "loss": 0.0622,
      "step": 127
    },
    {
      "epoch": 0.6649350649350649,
      "grad_norm": 0.6096386909484863,
      "learning_rate": 7.883401610574336e-05,
      "loss": 0.0676,
      "step": 128
    },
    {
      "epoch": 0.6701298701298701,
      "grad_norm": 0.5860247611999512,
      "learning_rate": 7.742259356246593e-05,
      "loss": 0.0662,
      "step": 129
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 0.635151207447052,
      "learning_rate": 7.597919750177168e-05,
      "loss": 0.0916,
      "step": 130
    },
    {
      "epoch": 0.6805194805194805,
      "grad_norm": 0.9333595037460327,
      "learning_rate": 7.450551085890087e-05,
      "loss": 0.0933,
      "step": 131
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.0415642261505127,
      "learning_rate": 7.300325188655761e-05,
      "loss": 0.1106,
      "step": 132
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 0.7532351613044739,
      "learning_rate": 7.14741721515041e-05,
      "loss": 0.0842,
      "step": 133
    },
    {
      "epoch": 0.6961038961038961,
      "grad_norm": 0.934203028678894,
      "learning_rate": 6.992005449231208e-05,
      "loss": 0.0683,
      "step": 134
    },
    {
      "epoch": 0.7012987012987013,
      "grad_norm": 0.7582775354385376,
      "learning_rate": 6.834271094065283e-05,
      "loss": 0.0906,
      "step": 135
    },
    {
      "epoch": 0.7064935064935065,
      "grad_norm": 0.8780021667480469,
      "learning_rate": 6.674398060854931e-05,
      "loss": 0.1072,
      "step": 136
    },
    {
      "epoch": 0.7116883116883117,
      "grad_norm": 1.2334891557693481,
      "learning_rate": 6.51257275440538e-05,
      "loss": 0.06,
      "step": 137
    },
    {
      "epoch": 0.7168831168831169,
      "grad_norm": 1.0346972942352295,
      "learning_rate": 6.348983855785121e-05,
      "loss": 0.0651,
      "step": 138
    },
    {
      "epoch": 0.7220779220779221,
      "grad_norm": 2.2124760150909424,
      "learning_rate": 6.183822102332234e-05,
      "loss": 0.0802,
      "step": 139
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.2769863605499268,
      "learning_rate": 6.01728006526317e-05,
      "loss": 0.0768,
      "step": 140
    },
    {
      "epoch": 0.7324675324675325,
      "grad_norm": 1.01767098903656,
      "learning_rate": 5.849551925143334e-05,
      "loss": 0.0528,
      "step": 141
    },
    {
      "epoch": 0.7376623376623377,
      "grad_norm": 1.3435330390930176,
      "learning_rate": 5.680833245481234e-05,
      "loss": 0.0499,
      "step": 142
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.6159822940826416,
      "learning_rate": 5.511320744710171e-05,
      "loss": 0.0492,
      "step": 143
    },
    {
      "epoch": 0.7480519480519481,
      "grad_norm": 2.217693567276001,
      "learning_rate": 5.341212066823355e-05,
      "loss": 0.0861,
      "step": 144
    },
    {
      "epoch": 0.7532467532467533,
      "grad_norm": 0.5090363621711731,
      "learning_rate": 5.1707055509298396e-05,
      "loss": 0.0811,
      "step": 145
    },
    {
      "epoch": 0.7584415584415585,
      "grad_norm": 0.4959089457988739,
      "learning_rate": 5e-05,
      "loss": 0.066,
      "step": 146
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.3657388389110565,
      "learning_rate": 4.829294449070161e-05,
      "loss": 0.0581,
      "step": 147
    },
    {
      "epoch": 0.7688311688311689,
      "grad_norm": 0.34298643469810486,
      "learning_rate": 4.658787933176646e-05,
      "loss": 0.0513,
      "step": 148
    },
    {
      "epoch": 0.7740259740259741,
      "grad_norm": 0.3530295491218567,
      "learning_rate": 4.4886792552898286e-05,
      "loss": 0.0528,
      "step": 149
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.3703291118144989,
      "learning_rate": 4.319166754518768e-05,
      "loss": 0.053,
      "step": 150
    },
    {
      "epoch": 0.7844155844155845,
      "grad_norm": 0.48950472474098206,
      "learning_rate": 4.150448074856667e-05,
      "loss": 0.0513,
      "step": 151
    },
    {
      "epoch": 0.7896103896103897,
      "grad_norm": 0.4313073754310608,
      "learning_rate": 3.982719934736832e-05,
      "loss": 0.0589,
      "step": 152
    },
    {
      "epoch": 0.7948051948051948,
      "grad_norm": 0.3637271821498871,
      "learning_rate": 3.8161778976677666e-05,
      "loss": 0.0579,
      "step": 153
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.34480196237564087,
      "learning_rate": 3.651016144214878e-05,
      "loss": 0.0633,
      "step": 154
    },
    {
      "epoch": 0.8051948051948052,
      "grad_norm": 0.34707579016685486,
      "learning_rate": 3.487427245594622e-05,
      "loss": 0.0625,
      "step": 155
    },
    {
      "epoch": 0.8103896103896104,
      "grad_norm": 0.3132532835006714,
      "learning_rate": 3.325601939145069e-05,
      "loss": 0.037,
      "step": 156
    },
    {
      "epoch": 0.8155844155844156,
      "grad_norm": 0.3370595872402191,
      "learning_rate": 3.165728905934718e-05,
      "loss": 0.0582,
      "step": 157
    },
    {
      "epoch": 0.8207792207792208,
      "grad_norm": 0.45950737595558167,
      "learning_rate": 3.007994550768793e-05,
      "loss": 0.0673,
      "step": 158
    },
    {
      "epoch": 0.825974025974026,
      "grad_norm": 0.394106388092041,
      "learning_rate": 2.8525827848495913e-05,
      "loss": 0.0641,
      "step": 159
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.481926292181015,
      "learning_rate": 2.6996748113442394e-05,
      "loss": 0.0585,
      "step": 160
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.4318128824234009,
      "learning_rate": 2.5494489141099153e-05,
      "loss": 0.0488,
      "step": 161
    },
    {
      "epoch": 0.8415584415584415,
      "grad_norm": 0.47509336471557617,
      "learning_rate": 2.4020802498228335e-05,
      "loss": 0.0674,
      "step": 162
    },
    {
      "epoch": 0.8467532467532467,
      "grad_norm": 0.46252065896987915,
      "learning_rate": 2.2577406437534054e-05,
      "loss": 0.0534,
      "step": 163
    },
    {
      "epoch": 0.8519480519480519,
      "grad_norm": 0.30728793144226074,
      "learning_rate": 2.1165983894256647e-05,
      "loss": 0.0411,
      "step": 164
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5630347728729248,
      "learning_rate": 1.9788180523945277e-05,
      "loss": 0.09,
      "step": 165
    },
    {
      "epoch": 0.8623376623376623,
      "grad_norm": 0.4824998080730438,
      "learning_rate": 1.8445602783697374e-05,
      "loss": 0.0567,
      "step": 166
    },
    {
      "epoch": 0.8675324675324675,
      "grad_norm": 0.48469027876853943,
      "learning_rate": 1.713981605910137e-05,
      "loss": 0.0645,
      "step": 167
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.6316553354263306,
      "learning_rate": 1.5872342839067306e-05,
      "loss": 0.0822,
      "step": 168
    },
    {
      "epoch": 0.8779220779220779,
      "grad_norm": 0.41797518730163574,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0583,
      "step": 169
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 0.5921850800514221,
      "learning_rate": 1.3458201786093794e-05,
      "loss": 0.0546,
      "step": 170
    },
    {
      "epoch": 0.8883116883116883,
      "grad_norm": 0.5195260047912598,
      "learning_rate": 1.2314348733631959e-05,
      "loss": 0.0707,
      "step": 171
    },
    {
      "epoch": 0.8935064935064935,
      "grad_norm": 0.5332620739936829,
      "learning_rate": 1.1214435464779006e-05,
      "loss": 0.065,
      "step": 172
    },
    {
      "epoch": 0.8987012987012987,
      "grad_norm": 0.6313295960426331,
      "learning_rate": 1.0159744429204777e-05,
      "loss": 0.0729,
      "step": 173
    },
    {
      "epoch": 0.9038961038961039,
      "grad_norm": 0.47485223412513733,
      "learning_rate": 9.151505349477902e-06,
      "loss": 0.068,
      "step": 174
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.6088980436325073,
      "learning_rate": 8.19089378726447e-06,
      "loss": 0.0695,
      "step": 175
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.6692063212394714,
      "learning_rate": 7.2790297726755716e-06,
      "loss": 0.0789,
      "step": 176
    },
    {
      "epoch": 0.9194805194805195,
      "grad_norm": 0.49499738216400146,
      "learning_rate": 6.416976498362432e-06,
      "loss": 0.0502,
      "step": 177
    },
    {
      "epoch": 0.9246753246753247,
      "grad_norm": 0.6727550625801086,
      "learning_rate": 5.605739079881239e-06,
      "loss": 0.0903,
      "step": 178
    },
    {
      "epoch": 0.9298701298701298,
      "grad_norm": 0.7829493284225464,
      "learning_rate": 4.846263383773364e-06,
      "loss": 0.0991,
      "step": 179
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 0.6316432952880859,
      "learning_rate": 4.139434924727359e-06,
      "loss": 0.0686,
      "step": 180
    },
    {
      "epoch": 0.9402597402597402,
      "grad_norm": 0.7055174708366394,
      "learning_rate": 3.486077833108342e-06,
      "loss": 0.054,
      "step": 181
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.8642033338546753,
      "learning_rate": 2.88695389405898e-06,
      "loss": 0.0964,
      "step": 182
    },
    {
      "epoch": 0.9506493506493506,
      "grad_norm": 0.7204033732414246,
      "learning_rate": 2.342761659291959e-06,
      "loss": 0.0693,
      "step": 183
    },
    {
      "epoch": 0.9558441558441558,
      "grad_norm": 0.6897662878036499,
      "learning_rate": 1.8541356326100433e-06,
      "loss": 0.0483,
      "step": 184
    },
    {
      "epoch": 0.961038961038961,
      "grad_norm": 0.8913400769233704,
      "learning_rate": 1.4216455301029275e-06,
      "loss": 0.1057,
      "step": 185
    },
    {
      "epoch": 0.9662337662337662,
      "grad_norm": 0.9551857709884644,
      "learning_rate": 1.0457956158838544e-06,
      "loss": 0.0997,
      "step": 186
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 0.9144113063812256,
      "learning_rate": 7.270241141401569e-07,
      "loss": 0.0553,
      "step": 187
    },
    {
      "epoch": 0.9766233766233766,
      "grad_norm": 1.390611171722412,
      "learning_rate": 4.6570269818346224e-07,
      "loss": 0.077,
      "step": 188
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.8106120228767395,
      "learning_rate": 2.62136057095258e-07,
      "loss": 0.0483,
      "step": 189
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 1.1034706830978394,
      "learning_rate": 1.1656154047303691e-07,
      "loss": 0.0563,
      "step": 190
    },
    {
      "epoch": 0.9922077922077922,
      "grad_norm": 1.87571382522583,
      "learning_rate": 2.9148881691298813e-08,
      "loss": 0.1062,
      "step": 191
    },
    {
      "epoch": 0.9974025974025974,
      "grad_norm": 1.577938199043274,
      "learning_rate": 0.0,
      "loss": 0.0844,
      "step": 192
    }
  ],
  "logging_steps": 1,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 239,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0869176476657254e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}