{
  "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": 6.02266263961792,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.9993,
      "step": 1
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 6.143394947052002,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0111,
      "step": 2
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 5.803601264953613,
      "learning_rate": 5e-06,
      "loss": 0.9858,
      "step": 3
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 4.266067028045654,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.9484,
      "step": 4
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.9427103996276855,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.9376,
      "step": 5
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 4.489638805389404,
      "learning_rate": 1e-05,
      "loss": 0.9214,
      "step": 6
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 4.621401786804199,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.9122,
      "step": 7
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 3.9608113765716553,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.8665,
      "step": 8
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.7279064655303955,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.8395,
      "step": 9
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.407290458679199,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8198,
      "step": 10
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 2.280531644821167,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.7984,
      "step": 11
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 2.6176528930664062,
      "learning_rate": 2e-05,
      "loss": 0.794,
      "step": 12
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 1.707384467124939,
      "learning_rate": 1.9995065603657317e-05,
      "loss": 0.783,
      "step": 13
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 1.9082920551300049,
      "learning_rate": 1.9980267284282718e-05,
      "loss": 0.7379,
      "step": 14
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.7811676263809204,
      "learning_rate": 1.99556196460308e-05,
      "loss": 0.7524,
      "step": 15
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 1.3555017709732056,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 0.754,
      "step": 16
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 1.3673418760299683,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.7073,
      "step": 17
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.4924910068511963,
      "learning_rate": 1.982287250728689e-05,
      "loss": 0.7159,
      "step": 18
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 1.6850374937057495,
      "learning_rate": 1.9759167619387474e-05,
      "loss": 0.7114,
      "step": 19
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.511631727218628,
      "learning_rate": 1.9685831611286312e-05,
      "loss": 0.7012,
      "step": 20
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 1.2830287218093872,
      "learning_rate": 1.9602936856769432e-05,
      "loss": 0.6948,
      "step": 21
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 1.2557350397109985,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.7046,
      "step": 22
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 0.9395996928215027,
      "learning_rate": 1.9408807689542257e-05,
      "loss": 0.7076,
      "step": 23
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.0723974704742432,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 0.6983,
      "step": 24
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.0539971590042114,
      "learning_rate": 1.9177546256839814e-05,
      "loss": 0.6839,
      "step": 25
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.9047765135765076,
      "learning_rate": 1.9048270524660197e-05,
      "loss": 0.6768,
      "step": 26
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9144095182418823,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.6773,
      "step": 27
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.8761118054389954,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 0.6852,
      "step": 28
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 0.9473320841789246,
      "learning_rate": 1.860742027003944e-05,
      "loss": 0.6882,
      "step": 29
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.0702017545700073,
      "learning_rate": 1.8443279255020153e-05,
      "loss": 0.6677,
      "step": 30
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 0.7134117484092712,
      "learning_rate": 1.827080574274562e-05,
      "loss": 0.6696,
      "step": 31
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.8997704386711121,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.6484,
      "step": 32
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.7318180203437805,
      "learning_rate": 1.7901550123756906e-05,
      "loss": 0.6859,
      "step": 33
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 0.8574209213256836,
      "learning_rate": 1.7705132427757895e-05,
      "loss": 0.6557,
      "step": 34
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.7167562246322632,
      "learning_rate": 1.7501110696304598e-05,
      "loss": 0.6511,
      "step": 35
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.701689600944519,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 0.6603,
      "step": 36
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 0.6708585023880005,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.6674,
      "step": 37
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 0.7055069208145142,
      "learning_rate": 1.684547105928689e-05,
      "loss": 0.6624,
      "step": 38
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.6366652250289917,
      "learning_rate": 1.661311865323652e-05,
      "loss": 0.659,
      "step": 39
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.7192656397819519,
      "learning_rate": 1.63742398974869e-05,
      "loss": 0.6403,
      "step": 40
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 0.7419708967208862,
      "learning_rate": 1.6129070536529767e-05,
      "loss": 0.6649,
      "step": 41
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.6875132918357849,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.6636,
      "step": 42
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 0.7200429439544678,
      "learning_rate": 1.5620833778521306e-05,
      "loss": 0.6464,
      "step": 43
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.6726692318916321,
      "learning_rate": 1.5358267949789968e-05,
      "loss": 0.6513,
      "step": 44
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6832252740859985,
      "learning_rate": 1.5090414157503715e-05,
      "loss": 0.6625,
      "step": 45
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 0.7112930417060852,
      "learning_rate": 1.4817536741017153e-05,
      "loss": 0.6471,
      "step": 46
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 0.671824038028717,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.6625,
      "step": 47
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.6902845501899719,
      "learning_rate": 1.4257792915650728e-05,
      "loss": 0.6374,
      "step": 48
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 0.5699530243873596,
      "learning_rate": 1.3971478906347806e-05,
      "loss": 0.6431,
      "step": 49
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.6002618670463562,
      "learning_rate": 1.3681245526846782e-05,
      "loss": 0.6381,
      "step": 50
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 0.576767086982727,
      "learning_rate": 1.3387379202452917e-05,
      "loss": 0.6338,
      "step": 51
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.6442639231681824,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.6502,
      "step": 52
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 0.651739776134491,
      "learning_rate": 1.2789911060392295e-05,
      "loss": 0.6449,
      "step": 53
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.8692764043807983,
      "learning_rate": 1.2486898871648552e-05,
      "loss": 0.6511,
      "step": 54
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.6121811270713806,
      "learning_rate": 1.2181432413965428e-05,
      "loss": 0.6367,
      "step": 55
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.8803330659866333,
      "learning_rate": 1.187381314585725e-05,
      "loss": 0.6532,
      "step": 56
    },
    {
      "epoch": 1.0133333333333334,
      "grad_norm": 1.236048698425293,
      "learning_rate": 1.156434465040231e-05,
      "loss": 1.0796,
      "step": 57
    },
    {
      "epoch": 1.031111111111111,
      "grad_norm": 0.899872362613678,
      "learning_rate": 1.1253332335643043e-05,
      "loss": 0.634,
      "step": 58
    },
    {
      "epoch": 1.048888888888889,
      "grad_norm": 0.5719662308692932,
      "learning_rate": 1.0941083133185146e-05,
      "loss": 0.6002,
      "step": 59
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.788408100605011,
      "learning_rate": 1.0627905195293135e-05,
      "loss": 0.5628,
      "step": 60
    },
    {
      "epoch": 1.0844444444444445,
      "grad_norm": 0.7448046207427979,
      "learning_rate": 1.0314107590781284e-05,
      "loss": 0.6532,
      "step": 61
    },
    {
      "epoch": 1.1022222222222222,
      "grad_norm": 0.8060784935951233,
      "learning_rate": 1e-05,
      "loss": 0.5744,
      "step": 62
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.7961754202842712,
      "learning_rate": 9.685892409218718e-06,
      "loss": 0.5798,
      "step": 63
    },
    {
      "epoch": 1.1377777777777778,
      "grad_norm": 0.6215574145317078,
      "learning_rate": 9.372094804706867e-06,
      "loss": 0.567,
      "step": 64
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.7157091498374939,
      "learning_rate": 9.058916866814857e-06,
      "loss": 0.6152,
      "step": 65
    },
    {
      "epoch": 1.1733333333333333,
      "grad_norm": 0.6254159212112427,
      "learning_rate": 8.746667664356957e-06,
      "loss": 0.6099,
      "step": 66
    },
    {
      "epoch": 1.1911111111111112,
      "grad_norm": 0.5155752897262573,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.5508,
      "step": 67
    },
    {
      "epoch": 1.208888888888889,
      "grad_norm": 0.5491471886634827,
      "learning_rate": 8.126186854142752e-06,
      "loss": 0.625,
      "step": 68
    },
    {
      "epoch": 1.2266666666666666,
      "grad_norm": 0.5200133919715881,
      "learning_rate": 7.818567586034578e-06,
      "loss": 0.5666,
      "step": 69
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.5425897240638733,
      "learning_rate": 7.513101128351454e-06,
      "loss": 0.6,
      "step": 70
    },
    {
      "epoch": 1.2622222222222224,
      "grad_norm": 0.420964777469635,
      "learning_rate": 7.210088939607709e-06,
      "loss": 0.5466,
      "step": 71
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.5204867124557495,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.6297,
      "step": 72
    },
    {
      "epoch": 1.2977777777777777,
      "grad_norm": 0.491071879863739,
      "learning_rate": 6.612620797547087e-06,
      "loss": 0.5333,
      "step": 73
    },
    {
      "epoch": 1.3155555555555556,
      "grad_norm": 0.4720323979854584,
      "learning_rate": 6.318754473153221e-06,
      "loss": 0.6132,
      "step": 74
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.430493026971817,
      "learning_rate": 6.028521093652195e-06,
      "loss": 0.5587,
      "step": 75
    },
    {
      "epoch": 1.3511111111111112,
      "grad_norm": 0.583470344543457,
      "learning_rate": 5.742207084349274e-06,
      "loss": 0.6111,
      "step": 76
    },
    {
      "epoch": 1.3688888888888888,
      "grad_norm": 0.5109282732009888,
      "learning_rate": 5.460095002604533e-06,
      "loss": 0.5848,
      "step": 77
    },
    {
      "epoch": 1.3866666666666667,
      "grad_norm": 0.5880340933799744,
      "learning_rate": 5.1824632589828465e-06,
      "loss": 0.6158,
      "step": 78
    },
    {
      "epoch": 1.4044444444444444,
      "grad_norm": 0.5229690670967102,
      "learning_rate": 4.909585842496287e-06,
      "loss": 0.5424,
      "step": 79
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.5499680638313293,
      "learning_rate": 4.641732050210032e-06,
      "loss": 0.5793,
      "step": 80
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.42541825771331787,
      "learning_rate": 4.379166221478697e-06,
      "loss": 0.5984,
      "step": 81
    },
    {
      "epoch": 1.4577777777777778,
      "grad_norm": 0.46670961380004883,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.621,
      "step": 82
    },
    {
      "epoch": 1.4755555555555555,
      "grad_norm": 0.4210701286792755,
      "learning_rate": 3.8709294634702374e-06,
      "loss": 0.5242,
      "step": 83
    },
    {
      "epoch": 1.4933333333333334,
      "grad_norm": 0.4062272310256958,
      "learning_rate": 3.625760102513103e-06,
      "loss": 0.563,
      "step": 84
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.42036882042884827,
      "learning_rate": 3.3868813467634833e-06,
      "loss": 0.6099,
      "step": 85
    },
    {
      "epoch": 1.528888888888889,
      "grad_norm": 0.413107693195343,
      "learning_rate": 3.1545289407131128e-06,
      "loss": 0.5765,
      "step": 86
    },
    {
      "epoch": 1.5466666666666666,
      "grad_norm": 0.4331943392753601,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.5988,
      "step": 87
    },
    {
      "epoch": 1.5644444444444443,
      "grad_norm": 0.4215940535068512,
      "learning_rate": 2.7103137257858867e-06,
      "loss": 0.5901,
      "step": 88
    },
    {
      "epoch": 1.5822222222222222,
      "grad_norm": 0.3558850586414337,
      "learning_rate": 2.4988893036954045e-06,
      "loss": 0.5578,
      "step": 89
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.35593435168266296,
      "learning_rate": 2.2948675722421086e-06,
      "loss": 0.5952,
      "step": 90
    },
    {
      "epoch": 1.6177777777777778,
      "grad_norm": 0.35841694474220276,
      "learning_rate": 2.098449876243096e-06,
      "loss": 0.5729,
      "step": 91
    },
    {
      "epoch": 1.6355555555555554,
      "grad_norm": 0.36976689100265503,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.6167,
      "step": 92
    },
    {
      "epoch": 1.6533333333333333,
      "grad_norm": 0.34893473982810974,
      "learning_rate": 1.7291942572543806e-06,
      "loss": 0.558,
      "step": 93
    },
    {
      "epoch": 1.6711111111111112,
      "grad_norm": 0.3704639673233032,
      "learning_rate": 1.5567207449798517e-06,
      "loss": 0.5948,
      "step": 94
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.3578838109970093,
      "learning_rate": 1.3925797299605649e-06,
      "loss": 0.5715,
      "step": 95
    },
    {
      "epoch": 1.7066666666666666,
      "grad_norm": 0.35762616991996765,
      "learning_rate": 1.2369331995613664e-06,
      "loss": 0.5936,
      "step": 96
    },
    {
      "epoch": 1.7244444444444444,
      "grad_norm": 0.3288617730140686,
      "learning_rate": 1.0899347581163222e-06,
      "loss": 0.5924,
      "step": 97
    },
    {
      "epoch": 1.7422222222222223,
      "grad_norm": 0.35121095180511475,
      "learning_rate": 9.517294753398066e-07,
      "loss": 0.575,
      "step": 98
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.32291051745414734,
      "learning_rate": 8.224537431601886e-07,
      "loss": 0.5367,
      "step": 99
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.37526610493659973,
      "learning_rate": 7.022351411174866e-07,
      "loss": 0.5957,
      "step": 100
    },
    {
      "epoch": 1.7955555555555556,
      "grad_norm": 0.34747347235679626,
      "learning_rate": 5.911923104577455e-07,
      "loss": 0.5824,
      "step": 101
    },
    {
      "epoch": 1.8133333333333335,
      "grad_norm": 0.3201601803302765,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.561,
      "step": 102
    },
    {
      "epoch": 1.8311111111111111,
      "grad_norm": 0.36945855617523193,
      "learning_rate": 3.9706314323056936e-07,
      "loss": 0.5761,
      "step": 103
    },
    {
      "epoch": 1.8488888888888888,
      "grad_norm": 0.3337363600730896,
      "learning_rate": 3.1416838871368925e-07,
      "loss": 0.5536,
      "step": 104
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.35673728585243225,
      "learning_rate": 2.4083238061252565e-07,
      "loss": 0.6234,
      "step": 105
    },
    {
      "epoch": 1.8844444444444446,
      "grad_norm": 0.3251909613609314,
      "learning_rate": 1.7712749271311392e-07,
      "loss": 0.5415,
      "step": 106
    },
    {
      "epoch": 1.9022222222222223,
      "grad_norm": 0.35213449597358704,
      "learning_rate": 1.231165940486234e-07,
      "loss": 0.5611,
      "step": 107
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.34044721722602844,
      "learning_rate": 7.885298685522235e-08,
      "loss": 0.5628,
      "step": 108
    },
    {
      "epoch": 1.9377777777777778,
      "grad_norm": 0.34606897830963135,
      "learning_rate": 4.438035396920004e-08,
      "loss": 0.5907,
      "step": 109
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.3360365629196167,
      "learning_rate": 1.973271571728441e-08,
      "loss": 0.6009,
      "step": 110
    },
    {
      "epoch": 1.9733333333333334,
      "grad_norm": 0.3323586583137512,
      "learning_rate": 4.9343963426840006e-09,
      "loss": 0.5773,
      "step": 111
    },
    {
      "epoch": 1.991111111111111,
      "grad_norm": 0.3478974997997284,
      "learning_rate": 0.0,
      "loss": 0.5963,
      "step": 112
    },
    {
      "epoch": 1.991111111111111,
      "step": 112,
      "total_flos": 185195202609152.0,
      "train_loss": 0.65867241738098,
      "train_runtime": 12992.6194,
      "train_samples_per_second": 0.83,
      "train_steps_per_second": 0.009
    }
  ],
  "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": 185195202609152.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}