{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 2000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 3.9070186614990234,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.0857,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.667642593383789,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6733,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.0051660537719727,
      "learning_rate": 3e-06,
      "loss": 0.6534,
      "step": 30
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.0736082792282104,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5221,
      "step": 40
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.684818744659424,
      "learning_rate": 5e-06,
      "loss": 0.6807,
      "step": 50
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.5355663299560547,
      "learning_rate": 6e-06,
      "loss": 0.4381,
      "step": 60
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.204728126525879,
      "learning_rate": 7e-06,
      "loss": 0.4578,
      "step": 70
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.8668341636657715,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.362,
      "step": 80
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.7530344724655151,
      "learning_rate": 9e-06,
      "loss": 0.6272,
      "step": 90
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.6746323108673096,
      "learning_rate": 1e-05,
      "loss": 0.5589,
      "step": 100
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.4799275398254395,
      "learning_rate": 9.989898989898991e-06,
      "loss": 0.6067,
      "step": 110
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.678624153137207,
      "learning_rate": 9.97979797979798e-06,
      "loss": 0.5582,
      "step": 120
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.9827778339385986,
      "learning_rate": 9.96969696969697e-06,
      "loss": 0.4943,
      "step": 130
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.8628324270248413,
      "learning_rate": 9.95959595959596e-06,
      "loss": 0.6706,
      "step": 140
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.0590109825134277,
      "learning_rate": 9.94949494949495e-06,
      "loss": 0.4861,
      "step": 150
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.6400913596153259,
      "learning_rate": 9.939393939393939e-06,
      "loss": 0.6373,
      "step": 160
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.803528070449829,
      "learning_rate": 9.92929292929293e-06,
      "loss": 0.6073,
      "step": 170
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.7043955326080322,
      "learning_rate": 9.91919191919192e-06,
      "loss": 0.6351,
      "step": 180
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.0071933269500732,
      "learning_rate": 9.90909090909091e-06,
      "loss": 0.6624,
      "step": 190
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.8767812252044678,
      "learning_rate": 9.8989898989899e-06,
      "loss": 0.5892,
      "step": 200
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.037977695465088,
      "learning_rate": 9.88888888888889e-06,
      "loss": 0.5099,
      "step": 210
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.31269109249115,
      "learning_rate": 9.87878787878788e-06,
      "loss": 0.5048,
      "step": 220
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.604134559631348,
      "learning_rate": 9.86868686868687e-06,
      "loss": 0.7424,
      "step": 230
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.378148078918457,
      "learning_rate": 9.85858585858586e-06,
      "loss": 0.6627,
      "step": 240
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8570343852043152,
      "learning_rate": 9.84848484848485e-06,
      "loss": 0.5931,
      "step": 250
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.617653489112854,
      "learning_rate": 9.838383838383839e-06,
      "loss": 0.4749,
      "step": 260
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.7800276279449463,
      "learning_rate": 9.828282828282829e-06,
      "loss": 0.8069,
      "step": 270
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.901750564575195,
      "learning_rate": 9.81818181818182e-06,
      "loss": 0.4457,
      "step": 280
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.434395790100098,
      "learning_rate": 9.80808080808081e-06,
      "loss": 0.7167,
      "step": 290
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.92600154876709,
      "learning_rate": 9.797979797979798e-06,
      "loss": 0.3975,
      "step": 300
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.07546558231115341,
      "learning_rate": 9.787878787878788e-06,
      "loss": 0.3655,
      "step": 310
    },
    {
      "epoch": 0.02,
      "grad_norm": 6.365915775299072,
      "learning_rate": 9.777777777777779e-06,
      "loss": 0.5224,
      "step": 320
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.0982255935668945,
      "learning_rate": 9.767676767676767e-06,
      "loss": 0.6165,
      "step": 330
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.7056803703308105,
      "learning_rate": 9.757575757575758e-06,
      "loss": 0.5539,
      "step": 340
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.2261226177215576,
      "learning_rate": 9.747474747474748e-06,
      "loss": 0.4769,
      "step": 350
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9531151056289673,
      "learning_rate": 9.737373737373738e-06,
      "loss": 0.3609,
      "step": 360
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.2107353210449219,
      "learning_rate": 9.727272727272728e-06,
      "loss": 0.5399,
      "step": 370
    },
    {
      "epoch": 0.02,
      "grad_norm": 7.582059860229492,
      "learning_rate": 9.717171717171719e-06,
      "loss": 0.6101,
      "step": 380
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.4467086791992188,
      "learning_rate": 9.707070707070709e-06,
      "loss": 0.5436,
      "step": 390
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.19772769510746002,
      "learning_rate": 9.696969696969698e-06,
      "loss": 0.6105,
      "step": 400
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.347663164138794,
      "learning_rate": 9.686868686868688e-06,
      "loss": 0.4353,
      "step": 410
    },
    {
      "epoch": 0.02,
      "grad_norm": 5.073924541473389,
      "learning_rate": 9.676767676767678e-06,
      "loss": 0.6866,
      "step": 420
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.099503517150879,
      "learning_rate": 9.666666666666667e-06,
      "loss": 0.5744,
      "step": 430
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.2135908603668213,
      "learning_rate": 9.656565656565657e-06,
      "loss": 0.5677,
      "step": 440
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.5008598566055298,
      "learning_rate": 9.646464646464647e-06,
      "loss": 0.3873,
      "step": 450
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.6704565286636353,
      "learning_rate": 9.636363636363638e-06,
      "loss": 0.6814,
      "step": 460
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.4024767875671387,
      "learning_rate": 9.626262626262626e-06,
      "loss": 0.5843,
      "step": 470
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.00467598857358098,
      "learning_rate": 9.616161616161616e-06,
      "loss": 0.4113,
      "step": 480
    },
    {
      "epoch": 0.02,
      "grad_norm": 4.787539958953857,
      "learning_rate": 9.606060606060607e-06,
      "loss": 0.7154,
      "step": 490
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.0733729600906372,
      "learning_rate": 9.595959595959597e-06,
      "loss": 0.6492,
      "step": 500
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.1921634674072266,
      "learning_rate": 9.585858585858586e-06,
      "loss": 0.5533,
      "step": 510
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.963071584701538,
      "learning_rate": 9.575757575757576e-06,
      "loss": 0.6422,
      "step": 520
    },
    {
      "epoch": 0.03,
      "grad_norm": 6.266462326049805,
      "learning_rate": 9.565656565656566e-06,
      "loss": 0.4266,
      "step": 530
    },
    {
      "epoch": 0.03,
      "grad_norm": 4.4488701820373535,
      "learning_rate": 9.555555555555556e-06,
      "loss": 0.4274,
      "step": 540
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.9400691986083984,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.5337,
      "step": 550
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.224618434906006,
      "learning_rate": 9.535353535353537e-06,
      "loss": 0.5675,
      "step": 560
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.3731207847595215,
      "learning_rate": 9.525252525252526e-06,
      "loss": 0.362,
      "step": 570
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.9596872329711914,
      "learning_rate": 9.515151515151516e-06,
      "loss": 0.5264,
      "step": 580
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.6627348065376282,
      "learning_rate": 9.505050505050506e-06,
      "loss": 0.435,
      "step": 590
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.430358409881592,
      "learning_rate": 9.494949494949497e-06,
      "loss": 0.5424,
      "step": 600
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.306655406951904,
      "learning_rate": 9.484848484848485e-06,
      "loss": 0.4153,
      "step": 610
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.6357769966125488,
      "learning_rate": 9.474747474747475e-06,
      "loss": 0.5251,
      "step": 620
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.038285732269287,
      "learning_rate": 9.464646464646466e-06,
      "loss": 0.5593,
      "step": 630
    },
    {
      "epoch": 0.03,
      "grad_norm": 5.054030895233154,
      "learning_rate": 9.454545454545456e-06,
      "loss": 0.582,
      "step": 640
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.8453586101531982,
      "learning_rate": 9.444444444444445e-06,
      "loss": 0.5627,
      "step": 650
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.760792851448059,
      "learning_rate": 9.434343434343435e-06,
      "loss": 0.4531,
      "step": 660
    },
    {
      "epoch": 0.03,
      "grad_norm": 6.7284159660339355,
      "learning_rate": 9.424242424242425e-06,
      "loss": 0.4397,
      "step": 670
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.4066224694252014,
      "learning_rate": 9.414141414141414e-06,
      "loss": 0.4056,
      "step": 680
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.083108425140381,
      "learning_rate": 9.404040404040404e-06,
      "loss": 0.6092,
      "step": 690
    },
    {
      "epoch": 0.04,
      "grad_norm": 4.98835563659668,
      "learning_rate": 9.393939393939396e-06,
      "loss": 0.4545,
      "step": 700
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.849491119384766,
      "learning_rate": 9.383838383838385e-06,
      "loss": 0.4038,
      "step": 710
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.9796783924102783,
      "learning_rate": 9.373737373737375e-06,
      "loss": 0.6097,
      "step": 720
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.3015940189361572,
      "learning_rate": 9.363636363636365e-06,
      "loss": 0.4561,
      "step": 730
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.0265772342681885,
      "learning_rate": 9.353535353535354e-06,
      "loss": 0.5972,
      "step": 740
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.158243656158447,
      "learning_rate": 9.343434343434344e-06,
      "loss": 0.4375,
      "step": 750
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6322413682937622,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.4394,
      "step": 760
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.8402198553085327,
      "learning_rate": 9.323232323232325e-06,
      "loss": 0.4942,
      "step": 770
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.9348700046539307,
      "learning_rate": 9.313131313131313e-06,
      "loss": 0.6713,
      "step": 780
    },
    {
      "epoch": 0.04,
      "grad_norm": 7.633822917938232,
      "learning_rate": 9.303030303030303e-06,
      "loss": 0.5727,
      "step": 790
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.5603723526000977,
      "learning_rate": 9.292929292929294e-06,
      "loss": 0.6393,
      "step": 800
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.2063639163970947,
      "learning_rate": 9.282828282828284e-06,
      "loss": 0.6278,
      "step": 810
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.9794161319732666,
      "learning_rate": 9.272727272727273e-06,
      "loss": 0.5332,
      "step": 820
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.441140055656433,
      "learning_rate": 9.262626262626263e-06,
      "loss": 0.5951,
      "step": 830
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.256943941116333,
      "learning_rate": 9.252525252525253e-06,
      "loss": 0.3266,
      "step": 840
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.15118904411792755,
      "learning_rate": 9.242424242424244e-06,
      "loss": 0.5511,
      "step": 850
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.8574471473693848,
      "learning_rate": 9.232323232323232e-06,
      "loss": 0.8058,
      "step": 860
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.2425239086151123,
      "learning_rate": 9.222222222222224e-06,
      "loss": 0.5866,
      "step": 870
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.476180911064148,
      "learning_rate": 9.212121212121213e-06,
      "loss": 0.5133,
      "step": 880
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.133812665939331,
      "learning_rate": 9.202020202020203e-06,
      "loss": 0.3262,
      "step": 890
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.0041747093200684,
      "learning_rate": 9.191919191919193e-06,
      "loss": 0.6861,
      "step": 900
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.9870094060897827,
      "learning_rate": 9.181818181818184e-06,
      "loss": 0.4655,
      "step": 910
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.3034363985061646,
      "learning_rate": 9.171717171717172e-06,
      "loss": 0.6274,
      "step": 920
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.1342576742172241,
      "learning_rate": 9.161616161616162e-06,
      "loss": 0.404,
      "step": 930
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.735161781311035,
      "learning_rate": 9.151515151515153e-06,
      "loss": 0.4047,
      "step": 940
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.926325798034668,
      "learning_rate": 9.141414141414143e-06,
      "loss": 0.3813,
      "step": 950
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.1905412673950195,
      "learning_rate": 9.131313131313132e-06,
      "loss": 0.7336,
      "step": 960
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.6212941408157349,
      "learning_rate": 9.121212121212122e-06,
      "loss": 0.6218,
      "step": 970
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.1676979064941406,
      "learning_rate": 9.111111111111112e-06,
      "loss": 0.4894,
      "step": 980
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.414123773574829,
      "learning_rate": 9.1010101010101e-06,
      "loss": 0.505,
      "step": 990
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.8107662200927734,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3938,
      "step": 1000
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.8321704864501953,
      "learning_rate": 9.080808080808081e-06,
      "loss": 0.504,
      "step": 1010
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.217884540557861,
      "learning_rate": 9.070707070707072e-06,
      "loss": 0.5721,
      "step": 1020
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.3424525260925293,
      "learning_rate": 9.06060606060606e-06,
      "loss": 0.7381,
      "step": 1030
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.54730749130249,
      "learning_rate": 9.050505050505052e-06,
      "loss": 0.4286,
      "step": 1040
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.27701061964035034,
      "learning_rate": 9.040404040404042e-06,
      "loss": 0.4992,
      "step": 1050
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.010037928819656372,
      "learning_rate": 9.030303030303031e-06,
      "loss": 0.3576,
      "step": 1060
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.300331711769104,
      "learning_rate": 9.020202020202021e-06,
      "loss": 0.4664,
      "step": 1070
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.9744607210159302,
      "learning_rate": 9.010101010101012e-06,
      "loss": 0.6967,
      "step": 1080
    },
    {
      "epoch": 0.05,
      "grad_norm": 11.244192123413086,
      "learning_rate": 9e-06,
      "loss": 0.5748,
      "step": 1090
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7657531499862671,
      "learning_rate": 8.98989898989899e-06,
      "loss": 0.5886,
      "step": 1100
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.8190665245056152,
      "learning_rate": 8.97979797979798e-06,
      "loss": 0.4612,
      "step": 1110
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.700965404510498,
      "learning_rate": 8.969696969696971e-06,
      "loss": 0.4551,
      "step": 1120
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.6943060755729675,
      "learning_rate": 8.95959595959596e-06,
      "loss": 0.4099,
      "step": 1130
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.1452864408493042,
      "learning_rate": 8.94949494949495e-06,
      "loss": 0.5128,
      "step": 1140
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.24422715604305267,
      "learning_rate": 8.93939393939394e-06,
      "loss": 0.6912,
      "step": 1150
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.50047492980957,
      "learning_rate": 8.92929292929293e-06,
      "loss": 0.4031,
      "step": 1160
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.4065107107162476,
      "learning_rate": 8.919191919191919e-06,
      "loss": 0.4238,
      "step": 1170
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.607456922531128,
      "learning_rate": 8.90909090909091e-06,
      "loss": 0.5757,
      "step": 1180
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.915406584739685,
      "learning_rate": 8.8989898989899e-06,
      "loss": 0.5571,
      "step": 1190
    },
    {
      "epoch": 0.06,
      "grad_norm": 5.252658843994141,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.6749,
      "step": 1200
    },
    {
      "epoch": 0.06,
      "grad_norm": 2.4744722843170166,
      "learning_rate": 8.87878787878788e-06,
      "loss": 0.6021,
      "step": 1210
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.5909355878829956,
      "learning_rate": 8.86868686868687e-06,
      "loss": 0.3381,
      "step": 1220
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.02662992477417,
      "learning_rate": 8.85858585858586e-06,
      "loss": 0.5778,
      "step": 1230
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.4688441753387451,
      "learning_rate": 8.84848484848485e-06,
      "loss": 0.512,
      "step": 1240
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.9729368090629578,
      "learning_rate": 8.83838383838384e-06,
      "loss": 0.5566,
      "step": 1250
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.964110255241394,
      "learning_rate": 8.82828282828283e-06,
      "loss": 0.3959,
      "step": 1260
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.288043022155762,
      "learning_rate": 8.818181818181819e-06,
      "loss": 0.5016,
      "step": 1270
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.6841915845870972,
      "learning_rate": 8.808080808080809e-06,
      "loss": 0.598,
      "step": 1280
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.1980228424072266,
      "learning_rate": 8.7979797979798e-06,
      "loss": 0.5803,
      "step": 1290
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.8826773166656494,
      "learning_rate": 8.787878787878788e-06,
      "loss": 0.3286,
      "step": 1300
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.622875690460205,
      "learning_rate": 8.777777777777778e-06,
      "loss": 0.4741,
      "step": 1310
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.7105564475059509,
      "learning_rate": 8.767676767676768e-06,
      "loss": 0.515,
      "step": 1320
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.3432900607585907,
      "learning_rate": 8.757575757575759e-06,
      "loss": 0.7004,
      "step": 1330
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.025210857391357,
      "learning_rate": 8.747474747474747e-06,
      "loss": 0.3985,
      "step": 1340
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.137606382369995,
      "learning_rate": 8.737373737373738e-06,
      "loss": 0.4918,
      "step": 1350
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.4660451114177704,
      "learning_rate": 8.727272727272728e-06,
      "loss": 0.6669,
      "step": 1360
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.9560216069221497,
      "learning_rate": 8.717171717171718e-06,
      "loss": 0.3283,
      "step": 1370
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.245961904525757,
      "learning_rate": 8.707070707070707e-06,
      "loss": 0.7393,
      "step": 1380
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.01912454143166542,
      "learning_rate": 8.696969696969699e-06,
      "loss": 0.418,
      "step": 1390
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.0197285413742065,
      "learning_rate": 8.686868686868687e-06,
      "loss": 0.492,
      "step": 1400
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.5338358879089355,
      "learning_rate": 8.676767676767678e-06,
      "loss": 0.6951,
      "step": 1410
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.198877334594727,
      "learning_rate": 8.666666666666668e-06,
      "loss": 0.3249,
      "step": 1420
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.8914008140563965,
      "learning_rate": 8.656565656565658e-06,
      "loss": 0.3945,
      "step": 1430
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.6320083141326904,
      "learning_rate": 8.646464646464647e-06,
      "loss": 0.6922,
      "step": 1440
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.5630173683166504,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.4658,
      "step": 1450
    },
    {
      "epoch": 0.07,
      "grad_norm": 3.9083809852600098,
      "learning_rate": 8.626262626262627e-06,
      "loss": 0.4208,
      "step": 1460
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0006579883047379553,
      "learning_rate": 8.616161616161618e-06,
      "loss": 0.4293,
      "step": 1470
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.7547767162323,
      "learning_rate": 8.606060606060606e-06,
      "loss": 0.5838,
      "step": 1480
    },
    {
      "epoch": 0.07,
      "grad_norm": 6.998627662658691,
      "learning_rate": 8.595959595959596e-06,
      "loss": 0.6267,
      "step": 1490
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.166638374328613,
      "learning_rate": 8.585858585858587e-06,
      "loss": 0.7075,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.313971519470215,
      "learning_rate": 8.575757575757575e-06,
      "loss": 0.6543,
      "step": 1510
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.2389867305755615,
      "learning_rate": 8.565656565656566e-06,
      "loss": 0.5254,
      "step": 1520
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.2064523696899414,
      "learning_rate": 8.555555555555556e-06,
      "loss": 0.4022,
      "step": 1530
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.1788508892059326,
      "learning_rate": 8.545454545454546e-06,
      "loss": 0.4377,
      "step": 1540
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.40915897488594055,
      "learning_rate": 8.535353535353535e-06,
      "loss": 0.5123,
      "step": 1550
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.2502992153167725,
      "learning_rate": 8.525252525252527e-06,
      "loss": 0.5134,
      "step": 1560
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.067376136779785,
      "learning_rate": 8.515151515151517e-06,
      "loss": 0.7065,
      "step": 1570
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.364538669586182,
      "learning_rate": 8.505050505050506e-06,
      "loss": 0.5286,
      "step": 1580
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.8198277950286865,
      "learning_rate": 8.494949494949496e-06,
      "loss": 0.7122,
      "step": 1590
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.0054919719696045,
      "learning_rate": 8.484848484848486e-06,
      "loss": 0.6057,
      "step": 1600
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.340848684310913,
      "learning_rate": 8.474747474747475e-06,
      "loss": 0.586,
      "step": 1610
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.649854898452759,
      "learning_rate": 8.464646464646465e-06,
      "loss": 0.6599,
      "step": 1620
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0032835814636200666,
      "learning_rate": 8.454545454545455e-06,
      "loss": 0.5668,
      "step": 1630
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.295167326927185,
      "learning_rate": 8.444444444444446e-06,
      "loss": 0.4962,
      "step": 1640
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.4222893714904785,
      "learning_rate": 8.434343434343434e-06,
      "loss": 0.303,
      "step": 1650
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.70741868019104,
      "learning_rate": 8.424242424242425e-06,
      "loss": 0.3325,
      "step": 1660
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6272850632667542,
      "learning_rate": 8.414141414141415e-06,
      "loss": 0.3552,
      "step": 1670
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.39682525396347046,
      "learning_rate": 8.404040404040405e-06,
      "loss": 0.5188,
      "step": 1680
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.233819484710693,
      "learning_rate": 8.393939393939394e-06,
      "loss": 0.4309,
      "step": 1690
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.6901202201843262,
      "learning_rate": 8.383838383838384e-06,
      "loss": 0.4005,
      "step": 1700
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.25327730178833,
      "learning_rate": 8.373737373737374e-06,
      "loss": 0.5327,
      "step": 1710
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.563572883605957,
      "learning_rate": 8.363636363636365e-06,
      "loss": 0.5132,
      "step": 1720
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.6525028944015503,
      "learning_rate": 8.353535353535355e-06,
      "loss": 0.3818,
      "step": 1730
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.6655619144439697,
      "learning_rate": 8.343434343434345e-06,
      "loss": 0.4418,
      "step": 1740
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.8698630332946777,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.6928,
      "step": 1750
    },
    {
      "epoch": 0.09,
      "grad_norm": 5.353645324707031,
      "learning_rate": 8.323232323232324e-06,
      "loss": 0.6257,
      "step": 1760
    },
    {
      "epoch": 0.09,
      "grad_norm": 6.349965572357178,
      "learning_rate": 8.313131313131314e-06,
      "loss": 0.9007,
      "step": 1770
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.7333180904388428,
      "learning_rate": 8.303030303030305e-06,
      "loss": 0.4963,
      "step": 1780
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.6360317468643188,
      "learning_rate": 8.292929292929293e-06,
      "loss": 0.9028,
      "step": 1790
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3366623520851135,
      "learning_rate": 8.282828282828283e-06,
      "loss": 0.4281,
      "step": 1800
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.0651333332061768,
      "learning_rate": 8.272727272727274e-06,
      "loss": 0.3646,
      "step": 1810
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.6993482708930969,
      "learning_rate": 8.262626262626264e-06,
      "loss": 0.5423,
      "step": 1820
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.010565996170044,
      "learning_rate": 8.252525252525253e-06,
      "loss": 0.7413,
      "step": 1830
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.367119312286377,
      "learning_rate": 8.242424242424243e-06,
      "loss": 0.6385,
      "step": 1840
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.1688125133514404,
      "learning_rate": 8.232323232323233e-06,
      "loss": 0.5547,
      "step": 1850
    },
    {
      "epoch": 0.09,
      "grad_norm": 2.5372488498687744,
      "learning_rate": 8.222222222222222e-06,
      "loss": 0.5464,
      "step": 1860
    },
    {
      "epoch": 0.09,
      "grad_norm": 7.86212682723999,
      "learning_rate": 8.212121212121212e-06,
      "loss": 0.414,
      "step": 1870
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.5354101657867432,
      "learning_rate": 8.202020202020202e-06,
      "loss": 0.6147,
      "step": 1880
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.8895275592803955,
      "learning_rate": 8.191919191919193e-06,
      "loss": 0.4875,
      "step": 1890
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.0076402425765991,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.553,
      "step": 1900
    },
    {
      "epoch": 0.1,
      "grad_norm": 5.115602493286133,
      "learning_rate": 8.171717171717173e-06,
      "loss": 0.3642,
      "step": 1910
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.1112468242645264,
      "learning_rate": 8.161616161616162e-06,
      "loss": 0.4393,
      "step": 1920
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.099217891693115,
      "learning_rate": 8.151515151515152e-06,
      "loss": 0.3543,
      "step": 1930
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.719365358352661,
      "learning_rate": 8.141414141414142e-06,
      "loss": 0.6467,
      "step": 1940
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.9949913024902344,
      "learning_rate": 8.131313131313133e-06,
      "loss": 0.5151,
      "step": 1950
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.5979423522949219,
      "learning_rate": 8.121212121212121e-06,
      "loss": 0.3655,
      "step": 1960
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.0186359882354736,
      "learning_rate": 8.111111111111112e-06,
      "loss": 0.5278,
      "step": 1970
    },
    {
      "epoch": 0.1,
      "grad_norm": 5.232735633850098,
      "learning_rate": 8.101010101010102e-06,
      "loss": 0.5965,
      "step": 1980
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.5541656017303467,
      "learning_rate": 8.090909090909092e-06,
      "loss": 0.5226,
      "step": 1990
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.416280269622803,
      "learning_rate": 8.08080808080808e-06,
      "loss": 0.3881,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.49726012349128723,
      "eval_runtime": 296.5886,
      "eval_samples_per_second": 3.372,
      "eval_steps_per_second": 3.372,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "total_flos": 8.1602751234048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}