{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.991111111111111,
  "eval_steps": 500,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 3.0161187648773193,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.9094,
      "step": 1
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 3.0456559658050537,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9199,
      "step": 2
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 2.8616299629211426,
      "learning_rate": 5e-06,
      "loss": 0.8971,
      "step": 3
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 2.2876524925231934,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.8814,
      "step": 4
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 3.967463493347168,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.8735,
      "step": 5
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 1.9434279203414917,
      "learning_rate": 1e-05,
      "loss": 0.8465,
      "step": 6
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 2.0345959663391113,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.8162,
      "step": 7
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 1.519321084022522,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.7766,
      "step": 8
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.5613726377487183,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7484,
      "step": 9
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.1348494291305542,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.7333,
      "step": 10
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 1.3956992626190186,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.7199,
      "step": 11
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 1.2517744302749634,
      "learning_rate": 2e-05,
      "loss": 0.7146,
      "step": 12
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 1.2728958129882812,
      "learning_rate": 1.9995065603657317e-05,
      "loss": 0.7104,
      "step": 13
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 1.0933605432510376,
      "learning_rate": 1.9980267284282718e-05,
      "loss": 0.6716,
      "step": 14
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.8169775605201721,
      "learning_rate": 1.99556196460308e-05,
      "loss": 0.6816,
      "step": 15
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 1.0378296375274658,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 0.6847,
      "step": 16
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 0.7941539883613586,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.6453,
      "step": 17
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6657661199569702,
      "learning_rate": 1.982287250728689e-05,
      "loss": 0.6504,
      "step": 18
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 0.7748784422874451,
      "learning_rate": 1.9759167619387474e-05,
      "loss": 0.6482,
      "step": 19
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.7648543119430542,
      "learning_rate": 1.9685831611286312e-05,
      "loss": 0.6399,
      "step": 20
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.6626160740852356,
      "learning_rate": 1.9602936856769432e-05,
      "loss": 0.6304,
      "step": 21
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 0.6575434803962708,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.6415,
      "step": 22
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 0.6369120478630066,
      "learning_rate": 1.9408807689542257e-05,
      "loss": 0.6439,
      "step": 23
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.6337743401527405,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.6368,
      "step": 24
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.6001498699188232,
      "learning_rate": 1.9177546256839814e-05,
      "loss": 0.623,
      "step": 25
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.48166558146476746,
      "learning_rate": 1.9048270524660197e-05,
      "loss": 0.6155,
      "step": 26
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5851263403892517,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.617,
      "step": 27
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.603469729423523,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 0.6253,
      "step": 28
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 0.45908477902412415,
      "learning_rate": 1.860742027003944e-05,
      "loss": 0.6267,
      "step": 29
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5786503553390503,
      "learning_rate": 1.8443279255020153e-05,
      "loss": 0.6087,
      "step": 30
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 0.5608594417572021,
      "learning_rate": 1.827080574274562e-05,
      "loss": 0.6103,
      "step": 31
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.43821826577186584,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.5908,
      "step": 32
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.5472081899642944,
      "learning_rate": 1.7901550123756906e-05,
      "loss": 0.6251,
      "step": 33
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 0.4198133945465088,
      "learning_rate": 1.7705132427757895e-05,
      "loss": 0.5963,
      "step": 34
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.524138867855072,
      "learning_rate": 1.7501110696304598e-05,
      "loss": 0.5929,
      "step": 35
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.399955153465271,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 0.6027,
      "step": 36
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 0.43022847175598145,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.6085,
      "step": 37
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 0.4289129972457886,
      "learning_rate": 1.684547105928689e-05,
      "loss": 0.6019,
      "step": 38
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.4198264181613922,
      "learning_rate": 1.661311865323652e-05,
      "loss": 0.6007,
      "step": 39
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3680365979671478,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.5827,
      "step": 40
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 0.4037115275859833,
      "learning_rate": 1.6129070536529767e-05,
      "loss": 0.6047,
      "step": 41
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.473398894071579,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.6041,
      "step": 42
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 0.33001384139060974,
      "learning_rate": 1.5620833778521306e-05,
      "loss": 0.5888,
      "step": 43
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.34208983182907104,
      "learning_rate": 1.5358267949789968e-05,
      "loss": 0.5927,
      "step": 44
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3997894823551178,
      "learning_rate": 1.5090414157503715e-05,
      "loss": 0.6037,
      "step": 45
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 0.3622935712337494,
      "learning_rate": 1.4817536741017153e-05,
      "loss": 0.59,
      "step": 46
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 0.35205668210983276,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.6038,
      "step": 47
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.38642618060112,
      "learning_rate": 1.4257792915650728e-05,
      "loss": 0.5796,
      "step": 48
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 0.34358909726142883,
      "learning_rate": 1.3971478906347806e-05,
      "loss": 0.5842,
      "step": 49
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3424360752105713,
      "learning_rate": 1.3681245526846782e-05,
      "loss": 0.5824,
      "step": 50
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 0.3290707468986511,
      "learning_rate": 1.3387379202452917e-05,
      "loss": 0.5766,
      "step": 51
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.3417136073112488,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.5917,
      "step": 52
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 0.3143644332885742,
      "learning_rate": 1.2789911060392295e-05,
      "loss": 0.5862,
      "step": 53
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.3264472782611847,
      "learning_rate": 1.2486898871648552e-05,
      "loss": 0.5941,
      "step": 54
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.3463677167892456,
      "learning_rate": 1.2181432413965428e-05,
      "loss": 0.5792,
      "step": 55
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.3562481105327606,
      "learning_rate": 1.187381314585725e-05,
      "loss": 0.5949,
      "step": 56
    },
    {
      "epoch": 1.0133333333333334,
      "grad_norm": 0.6014902591705322,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.9832,
      "step": 57
    },
    {
      "epoch": 1.031111111111111,
      "grad_norm": 0.4315400719642639,
      "learning_rate": 1.1253332335643043e-05,
      "loss": 0.579,
      "step": 58
    },
    {
      "epoch": 1.048888888888889,
      "grad_norm": 0.4110487401485443,
      "learning_rate": 1.0941083133185146e-05,
      "loss": 0.5473,
      "step": 59
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3785395920276642,
      "learning_rate": 1.0627905195293135e-05,
      "loss": 0.5123,
      "step": 60
    },
    {
      "epoch": 1.0844444444444445,
      "grad_norm": 0.41390877962112427,
      "learning_rate": 1.0314107590781284e-05,
      "loss": 0.5945,
      "step": 61
    },
    {
      "epoch": 1.1022222222222222,
      "grad_norm": 0.35746318101882935,
      "learning_rate": 1e-05,
      "loss": 0.525,
      "step": 62
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.4079684019088745,
      "learning_rate": 9.685892409218718e-06,
      "loss": 0.5318,
      "step": 63
    },
    {
      "epoch": 1.1377777777777778,
      "grad_norm": 0.36759430170059204,
      "learning_rate": 9.372094804706867e-06,
      "loss": 0.5176,
      "step": 64
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.41054409742355347,
      "learning_rate": 9.058916866814857e-06,
      "loss": 0.5637,
      "step": 65
    },
    {
      "epoch": 1.1733333333333333,
      "grad_norm": 0.3619822859764099,
      "learning_rate": 8.746667664356957e-06,
      "loss": 0.5567,
      "step": 66
    },
    {
      "epoch": 1.1911111111111112,
      "grad_norm": 0.3154706656932831,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.5005,
      "step": 67
    },
    {
      "epoch": 1.208888888888889,
      "grad_norm": 0.38217437267303467,
      "learning_rate": 8.126186854142752e-06,
      "loss": 0.5691,
      "step": 68
    },
    {
      "epoch": 1.2266666666666666,
      "grad_norm": 0.30643534660339355,
      "learning_rate": 7.818567586034578e-06,
      "loss": 0.5169,
      "step": 69
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.335054486989975,
      "learning_rate": 7.513101128351454e-06,
      "loss": 0.5474,
      "step": 70
    },
    {
      "epoch": 1.2622222222222224,
      "grad_norm": 0.32074597477912903,
      "learning_rate": 7.210088939607709e-06,
      "loss": 0.499,
      "step": 71
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.3078364431858063,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.5772,
      "step": 72
    },
    {
      "epoch": 1.2977777777777777,
      "grad_norm": 0.26938191056251526,
      "learning_rate": 6.612620797547087e-06,
      "loss": 0.4868,
      "step": 73
    },
    {
      "epoch": 1.3155555555555556,
      "grad_norm": 0.34066033363342285,
      "learning_rate": 6.318754473153221e-06,
      "loss": 0.5599,
      "step": 74
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.28962934017181396,
      "learning_rate": 6.028521093652195e-06,
      "loss": 0.5101,
      "step": 75
    },
    {
      "epoch": 1.3511111111111112,
      "grad_norm": 0.2816958427429199,
      "learning_rate": 5.742207084349274e-06,
      "loss": 0.5604,
      "step": 76
    },
    {
      "epoch": 1.3688888888888888,
      "grad_norm": 0.31672269105911255,
      "learning_rate": 5.460095002604533e-06,
      "loss": 0.5351,
      "step": 77
    },
    {
      "epoch": 1.3866666666666667,
      "grad_norm": 0.307559609413147,
      "learning_rate": 5.1824632589828465e-06,
      "loss": 0.5609,
      "step": 78
    },
    {
      "epoch": 1.4044444444444444,
      "grad_norm": 0.3002449572086334,
      "learning_rate": 4.909585842496287e-06,
      "loss": 0.4945,
      "step": 79
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.4366104304790497,
      "learning_rate": 4.641732050210032e-06,
      "loss": 0.529,
      "step": 80
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.2942907214164734,
      "learning_rate": 4.379166221478697e-06,
      "loss": 0.5456,
      "step": 81
    },
    {
      "epoch": 1.4577777777777778,
      "grad_norm": 0.29603904485702515,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.5672,
      "step": 82
    },
    {
      "epoch": 1.4755555555555555,
      "grad_norm": 0.26003167033195496,
      "learning_rate": 3.8709294634702374e-06,
      "loss": 0.4796,
      "step": 83
    },
    {
      "epoch": 1.4933333333333334,
      "grad_norm": 0.2945937514305115,
      "learning_rate": 3.625760102513103e-06,
      "loss": 0.5144,
      "step": 84
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.32350650429725647,
      "learning_rate": 3.3868813467634833e-06,
      "loss": 0.5563,
      "step": 85
    },
    {
      "epoch": 1.528888888888889,
      "grad_norm": 0.28247952461242676,
      "learning_rate": 3.1545289407131128e-06,
      "loss": 0.5267,
      "step": 86
    },
    {
      "epoch": 1.5466666666666666,
      "grad_norm": 0.2574496269226074,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.5464,
      "step": 87
    },
    {
      "epoch": 1.5644444444444443,
      "grad_norm": 0.2627605199813843,
      "learning_rate": 2.7103137257858867e-06,
      "loss": 0.5406,
      "step": 88
    },
    {
      "epoch": 1.5822222222222222,
      "grad_norm": 0.2714482545852661,
      "learning_rate": 2.4988893036954045e-06,
      "loss": 0.5094,
      "step": 89
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.28099218010902405,
      "learning_rate": 2.2948675722421086e-06,
      "loss": 0.5433,
      "step": 90
    },
    {
      "epoch": 1.6177777777777778,
      "grad_norm": 0.24211485683918,
      "learning_rate": 2.098449876243096e-06,
      "loss": 0.5239,
      "step": 91
    },
    {
      "epoch": 1.6355555555555554,
      "grad_norm": 0.2546832859516144,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.5626,
      "step": 92
    },
    {
      "epoch": 1.6533333333333333,
      "grad_norm": 0.2391272783279419,
      "learning_rate": 1.7291942572543806e-06,
      "loss": 0.5097,
      "step": 93
    },
    {
      "epoch": 1.6711111111111112,
      "grad_norm": 0.2698579430580139,
      "learning_rate": 1.5567207449798517e-06,
      "loss": 0.5432,
      "step": 94
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.2520196735858917,
      "learning_rate": 1.3925797299605649e-06,
      "loss": 0.5245,
      "step": 95
    },
    {
      "epoch": 1.7066666666666666,
      "grad_norm": 0.25460532307624817,
      "learning_rate": 1.2369331995613664e-06,
      "loss": 0.5438,
      "step": 96
    },
    {
      "epoch": 1.7244444444444444,
      "grad_norm": 0.26885905861854553,
      "learning_rate": 1.0899347581163222e-06,
      "loss": 0.5418,
      "step": 97
    },
    {
      "epoch": 1.7422222222222223,
      "grad_norm": 0.22826924920082092,
      "learning_rate": 9.517294753398066e-07,
      "loss": 0.5258,
      "step": 98
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.2222457379102707,
      "learning_rate": 8.224537431601886e-07,
      "loss": 0.4905,
      "step": 99
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.24972008168697357,
      "learning_rate": 7.022351411174866e-07,
      "loss": 0.5436,
      "step": 100
    },
    {
      "epoch": 1.7955555555555556,
      "grad_norm": 0.24206911027431488,
      "learning_rate": 5.911923104577455e-07,
      "loss": 0.5322,
      "step": 101
    },
    {
      "epoch": 1.8133333333333335,
      "grad_norm": 0.2620464861392975,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.5142,
      "step": 102
    },
    {
      "epoch": 1.8311111111111111,
      "grad_norm": 0.25102680921554565,
      "learning_rate": 3.9706314323056936e-07,
      "loss": 0.5264,
      "step": 103
    },
    {
      "epoch": 1.8488888888888888,
      "grad_norm": 0.24889089167118073,
      "learning_rate": 3.1416838871368925e-07,
      "loss": 0.5069,
      "step": 104
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.24384674429893494,
      "learning_rate": 2.4083238061252565e-07,
      "loss": 0.5694,
      "step": 105
    },
    {
      "epoch": 1.8844444444444446,
      "grad_norm": 0.2293427288532257,
      "learning_rate": 1.7712749271311392e-07,
      "loss": 0.4963,
      "step": 106
    },
    {
      "epoch": 1.9022222222222223,
      "grad_norm": 0.2467752993106842,
      "learning_rate": 1.231165940486234e-07,
      "loss": 0.512,
      "step": 107
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.2353520542383194,
      "learning_rate": 7.885298685522235e-08,
      "loss": 0.5168,
      "step": 108
    },
    {
      "epoch": 1.9377777777777778,
      "grad_norm": 0.2465604692697525,
      "learning_rate": 4.438035396920004e-08,
      "loss": 0.5412,
      "step": 109
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.23654182255268097,
      "learning_rate": 1.973271571728441e-08,
      "loss": 0.5511,
      "step": 110
    },
    {
      "epoch": 1.9733333333333334,
      "grad_norm": 0.22757108509540558,
      "learning_rate": 4.9343963426840006e-09,
      "loss": 0.5274,
      "step": 111
    },
    {
      "epoch": 1.991111111111111,
      "grad_norm": 0.24920369684696198,
      "learning_rate": 0.0,
      "loss": 0.544,
      "step": 112
    },
    {
      "epoch": 1.991111111111111,
      "step": 112,
      "total_flos": 467112937127936.0,
      "train_loss": 0.6003679327134576,
      "train_runtime": 29362.7142,
      "train_samples_per_second": 0.367,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 1,
  "max_steps": 112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 467112937127936.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}