{
  "best_metric": 0.3034655451774597,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.2183406113537118,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001091703056768559,
      "grad_norm": 0.2975941598415375,
      "learning_rate": 1e-05,
      "loss": 1.3655,
      "step": 1
    },
    {
      "epoch": 0.001091703056768559,
      "eval_loss": 1.3439563512802124,
      "eval_runtime": 43.097,
      "eval_samples_per_second": 35.803,
      "eval_steps_per_second": 8.957,
      "step": 1
    },
    {
      "epoch": 0.002183406113537118,
      "grad_norm": 0.30427107214927673,
      "learning_rate": 2e-05,
      "loss": 1.3422,
      "step": 2
    },
    {
      "epoch": 0.0032751091703056767,
      "grad_norm": 0.2965121865272522,
      "learning_rate": 3e-05,
      "loss": 1.3367,
      "step": 3
    },
    {
      "epoch": 0.004366812227074236,
      "grad_norm": 0.3025861084461212,
      "learning_rate": 4e-05,
      "loss": 1.3431,
      "step": 4
    },
    {
      "epoch": 0.0054585152838427945,
      "grad_norm": 0.30142030119895935,
      "learning_rate": 5e-05,
      "loss": 1.3536,
      "step": 5
    },
    {
      "epoch": 0.006550218340611353,
      "grad_norm": 0.3083294928073883,
      "learning_rate": 6e-05,
      "loss": 1.3216,
      "step": 6
    },
    {
      "epoch": 0.007641921397379912,
      "grad_norm": 0.31400877237319946,
      "learning_rate": 7e-05,
      "loss": 1.2836,
      "step": 7
    },
    {
      "epoch": 0.008733624454148471,
      "grad_norm": 0.31404849886894226,
      "learning_rate": 8e-05,
      "loss": 1.2307,
      "step": 8
    },
    {
      "epoch": 0.009825327510917031,
      "grad_norm": 0.3167654573917389,
      "learning_rate": 9e-05,
      "loss": 1.1375,
      "step": 9
    },
    {
      "epoch": 0.010917030567685589,
      "grad_norm": 0.30806154012680054,
      "learning_rate": 0.0001,
      "loss": 1.0705,
      "step": 10
    },
    {
      "epoch": 0.012008733624454149,
      "grad_norm": 0.3104648292064667,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9869,
      "step": 11
    },
    {
      "epoch": 0.013100436681222707,
      "grad_norm": 0.31911638379096985,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8853,
      "step": 12
    },
    {
      "epoch": 0.014192139737991267,
      "grad_norm": 0.35006970167160034,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8093,
      "step": 13
    },
    {
      "epoch": 0.015283842794759825,
      "grad_norm": 0.3577936291694641,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7355,
      "step": 14
    },
    {
      "epoch": 0.016375545851528384,
      "grad_norm": 0.346420556306839,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6437,
      "step": 15
    },
    {
      "epoch": 0.017467248908296942,
      "grad_norm": 0.3854060173034668,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5686,
      "step": 16
    },
    {
      "epoch": 0.018558951965065504,
      "grad_norm": 0.42565345764160156,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5548,
      "step": 17
    },
    {
      "epoch": 0.019650655021834062,
      "grad_norm": 0.2998095750808716,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5065,
      "step": 18
    },
    {
      "epoch": 0.02074235807860262,
      "grad_norm": 0.21860449016094208,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.441,
      "step": 19
    },
    {
      "epoch": 0.021834061135371178,
      "grad_norm": 0.18832187354564667,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4393,
      "step": 20
    },
    {
      "epoch": 0.02292576419213974,
      "grad_norm": 0.2223610281944275,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4149,
      "step": 21
    },
    {
      "epoch": 0.024017467248908297,
      "grad_norm": 0.16464067995548248,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.403,
      "step": 22
    },
    {
      "epoch": 0.025109170305676855,
      "grad_norm": 0.13228832185268402,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.383,
      "step": 23
    },
    {
      "epoch": 0.026200873362445413,
      "grad_norm": 0.11734681576490402,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.401,
      "step": 24
    },
    {
      "epoch": 0.027292576419213975,
      "grad_norm": 0.1098158210515976,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4009,
      "step": 25
    },
    {
      "epoch": 0.028384279475982533,
      "grad_norm": 0.10687969624996185,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3804,
      "step": 26
    },
    {
      "epoch": 0.02947598253275109,
      "grad_norm": 0.12141698598861694,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.3502,
      "step": 27
    },
    {
      "epoch": 0.03056768558951965,
      "grad_norm": 0.11846671253442764,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.358,
      "step": 28
    },
    {
      "epoch": 0.03165938864628821,
      "grad_norm": 0.12676052749156952,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3517,
      "step": 29
    },
    {
      "epoch": 0.03275109170305677,
      "grad_norm": 0.10721225291490555,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3521,
      "step": 30
    },
    {
      "epoch": 0.03384279475982533,
      "grad_norm": 0.08815053850412369,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3719,
      "step": 31
    },
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 0.09011223167181015,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3628,
      "step": 32
    },
    {
      "epoch": 0.036026200873362446,
      "grad_norm": 0.09283119440078735,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3545,
      "step": 33
    },
    {
      "epoch": 0.03711790393013101,
      "grad_norm": 0.09084271639585495,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3578,
      "step": 34
    },
    {
      "epoch": 0.03820960698689956,
      "grad_norm": 0.10225269943475723,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3584,
      "step": 35
    },
    {
      "epoch": 0.039301310043668124,
      "grad_norm": 0.07610679417848587,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.335,
      "step": 36
    },
    {
      "epoch": 0.04039301310043668,
      "grad_norm": 0.0882502943277359,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3314,
      "step": 37
    },
    {
      "epoch": 0.04148471615720524,
      "grad_norm": 0.09118633717298508,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.347,
      "step": 38
    },
    {
      "epoch": 0.0425764192139738,
      "grad_norm": 0.08780893683433533,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3643,
      "step": 39
    },
    {
      "epoch": 0.043668122270742356,
      "grad_norm": 0.09361185133457184,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3647,
      "step": 40
    },
    {
      "epoch": 0.04475982532751092,
      "grad_norm": 0.07851547747850418,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3221,
      "step": 41
    },
    {
      "epoch": 0.04585152838427948,
      "grad_norm": 0.10827722400426865,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3276,
      "step": 42
    },
    {
      "epoch": 0.04694323144104803,
      "grad_norm": 0.08991748094558716,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3388,
      "step": 43
    },
    {
      "epoch": 0.048034934497816595,
      "grad_norm": 0.1069718450307846,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.312,
      "step": 44
    },
    {
      "epoch": 0.04912663755458515,
      "grad_norm": 0.09495409578084946,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.302,
      "step": 45
    },
    {
      "epoch": 0.05021834061135371,
      "grad_norm": 0.0822974145412445,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.289,
      "step": 46
    },
    {
      "epoch": 0.05131004366812227,
      "grad_norm": 0.07541394233703613,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2953,
      "step": 47
    },
    {
      "epoch": 0.05240174672489083,
      "grad_norm": 0.0835643783211708,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3238,
      "step": 48
    },
    {
      "epoch": 0.05349344978165939,
      "grad_norm": 0.10220137238502502,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3309,
      "step": 49
    },
    {
      "epoch": 0.05458515283842795,
      "grad_norm": 0.08587832003831863,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3393,
      "step": 50
    },
    {
      "epoch": 0.05458515283842795,
      "eval_loss": 0.3398367762565613,
      "eval_runtime": 43.4237,
      "eval_samples_per_second": 35.534,
      "eval_steps_per_second": 8.889,
      "step": 50
    },
    {
      "epoch": 0.055676855895196505,
      "grad_norm": 0.23572339117527008,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4263,
      "step": 51
    },
    {
      "epoch": 0.056768558951965066,
      "grad_norm": 0.1507434844970703,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4094,
      "step": 52
    },
    {
      "epoch": 0.05786026200873363,
      "grad_norm": 0.10726453363895416,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3811,
      "step": 53
    },
    {
      "epoch": 0.05895196506550218,
      "grad_norm": 0.095211461186409,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3557,
      "step": 54
    },
    {
      "epoch": 0.060043668122270744,
      "grad_norm": 0.16252461075782776,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3814,
      "step": 55
    },
    {
      "epoch": 0.0611353711790393,
      "grad_norm": 0.14758841693401337,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.3658,
      "step": 56
    },
    {
      "epoch": 0.06222707423580786,
      "grad_norm": 0.11625952273607254,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3508,
      "step": 57
    },
    {
      "epoch": 0.06331877729257641,
      "grad_norm": 0.09824848920106888,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3414,
      "step": 58
    },
    {
      "epoch": 0.06441048034934498,
      "grad_norm": 0.08111011236906052,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3559,
      "step": 59
    },
    {
      "epoch": 0.06550218340611354,
      "grad_norm": 0.08074962347745895,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3459,
      "step": 60
    },
    {
      "epoch": 0.0665938864628821,
      "grad_norm": 0.07944554090499878,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3425,
      "step": 61
    },
    {
      "epoch": 0.06768558951965066,
      "grad_norm": 0.0876033827662468,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3286,
      "step": 62
    },
    {
      "epoch": 0.06877729257641921,
      "grad_norm": 0.0882960855960846,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3634,
      "step": 63
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 0.09544792771339417,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3414,
      "step": 64
    },
    {
      "epoch": 0.07096069868995633,
      "grad_norm": 0.08954335004091263,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3257,
      "step": 65
    },
    {
      "epoch": 0.07205240174672489,
      "grad_norm": 0.08375678956508636,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3049,
      "step": 66
    },
    {
      "epoch": 0.07314410480349345,
      "grad_norm": 0.08086434751749039,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3331,
      "step": 67
    },
    {
      "epoch": 0.07423580786026202,
      "grad_norm": 0.08048471808433533,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3239,
      "step": 68
    },
    {
      "epoch": 0.07532751091703056,
      "grad_norm": 0.07186366617679596,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3285,
      "step": 69
    },
    {
      "epoch": 0.07641921397379912,
      "grad_norm": 0.09012856334447861,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3211,
      "step": 70
    },
    {
      "epoch": 0.07751091703056769,
      "grad_norm": 0.07422231137752533,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3339,
      "step": 71
    },
    {
      "epoch": 0.07860262008733625,
      "grad_norm": 0.07478148490190506,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3073,
      "step": 72
    },
    {
      "epoch": 0.07969432314410481,
      "grad_norm": 0.07684729993343353,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3083,
      "step": 73
    },
    {
      "epoch": 0.08078602620087336,
      "grad_norm": 0.08593175560235977,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3296,
      "step": 74
    },
    {
      "epoch": 0.08187772925764192,
      "grad_norm": 0.06883702427148819,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3303,
      "step": 75
    },
    {
      "epoch": 0.08296943231441048,
      "grad_norm": 0.07267885655164719,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3322,
      "step": 76
    },
    {
      "epoch": 0.08406113537117904,
      "grad_norm": 0.0797484740614891,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3219,
      "step": 77
    },
    {
      "epoch": 0.0851528384279476,
      "grad_norm": 0.08103577792644501,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3135,
      "step": 78
    },
    {
      "epoch": 0.08624454148471616,
      "grad_norm": 0.07814051955938339,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.2974,
      "step": 79
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.08056455105543137,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3051,
      "step": 80
    },
    {
      "epoch": 0.08842794759825327,
      "grad_norm": 0.0700024738907814,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3188,
      "step": 81
    },
    {
      "epoch": 0.08951965065502183,
      "grad_norm": 0.07185326516628265,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3148,
      "step": 82
    },
    {
      "epoch": 0.0906113537117904,
      "grad_norm": 0.07313404232263565,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2772,
      "step": 83
    },
    {
      "epoch": 0.09170305676855896,
      "grad_norm": 0.07803550362586975,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3257,
      "step": 84
    },
    {
      "epoch": 0.0927947598253275,
      "grad_norm": 0.08105993270874023,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3075,
      "step": 85
    },
    {
      "epoch": 0.09388646288209607,
      "grad_norm": 0.07943282276391983,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2945,
      "step": 86
    },
    {
      "epoch": 0.09497816593886463,
      "grad_norm": 0.08007430285215378,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2828,
      "step": 87
    },
    {
      "epoch": 0.09606986899563319,
      "grad_norm": 0.07345171272754669,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3008,
      "step": 88
    },
    {
      "epoch": 0.09716157205240175,
      "grad_norm": 0.08184145390987396,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2739,
      "step": 89
    },
    {
      "epoch": 0.0982532751091703,
      "grad_norm": 0.07878600805997849,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3077,
      "step": 90
    },
    {
      "epoch": 0.09934497816593886,
      "grad_norm": 0.06953173130750656,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2956,
      "step": 91
    },
    {
      "epoch": 0.10043668122270742,
      "grad_norm": 0.0769491121172905,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2696,
      "step": 92
    },
    {
      "epoch": 0.10152838427947598,
      "grad_norm": 0.07854235172271729,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3171,
      "step": 93
    },
    {
      "epoch": 0.10262008733624454,
      "grad_norm": 0.07137403637170792,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2906,
      "step": 94
    },
    {
      "epoch": 0.1037117903930131,
      "grad_norm": 0.0802653506398201,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2638,
      "step": 95
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 0.07894200831651688,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.305,
      "step": 96
    },
    {
      "epoch": 0.10589519650655022,
      "grad_norm": 0.07629965245723724,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3044,
      "step": 97
    },
    {
      "epoch": 0.10698689956331878,
      "grad_norm": 0.09323137253522873,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2894,
      "step": 98
    },
    {
      "epoch": 0.10807860262008734,
      "grad_norm": 0.07961030304431915,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3064,
      "step": 99
    },
    {
      "epoch": 0.1091703056768559,
      "grad_norm": 0.08129587024450302,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.285,
      "step": 100
    },
    {
      "epoch": 0.1091703056768559,
      "eval_loss": 0.3178919851779938,
      "eval_runtime": 43.4568,
      "eval_samples_per_second": 35.506,
      "eval_steps_per_second": 8.882,
      "step": 100
    },
    {
      "epoch": 0.11026200873362445,
      "grad_norm": 0.1888505220413208,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3843,
      "step": 101
    },
    {
      "epoch": 0.11135371179039301,
      "grad_norm": 0.1845075935125351,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.394,
      "step": 102
    },
    {
      "epoch": 0.11244541484716157,
      "grad_norm": 0.15565142035484314,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3475,
      "step": 103
    },
    {
      "epoch": 0.11353711790393013,
      "grad_norm": 0.12783858180046082,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3455,
      "step": 104
    },
    {
      "epoch": 0.1146288209606987,
      "grad_norm": 0.08673954755067825,
      "learning_rate": 5e-05,
      "loss": 0.352,
      "step": 105
    },
    {
      "epoch": 0.11572052401746726,
      "grad_norm": 0.10427646338939667,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3592,
      "step": 106
    },
    {
      "epoch": 0.1168122270742358,
      "grad_norm": 0.1011277288198471,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3364,
      "step": 107
    },
    {
      "epoch": 0.11790393013100436,
      "grad_norm": 0.13620641827583313,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3477,
      "step": 108
    },
    {
      "epoch": 0.11899563318777293,
      "grad_norm": 0.11845588684082031,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.317,
      "step": 109
    },
    {
      "epoch": 0.12008733624454149,
      "grad_norm": 0.11437731981277466,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3509,
      "step": 110
    },
    {
      "epoch": 0.12117903930131005,
      "grad_norm": 0.10618239641189575,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3349,
      "step": 111
    },
    {
      "epoch": 0.1222707423580786,
      "grad_norm": 0.09904322028160095,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3265,
      "step": 112
    },
    {
      "epoch": 0.12336244541484716,
      "grad_norm": 0.08547835797071457,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3056,
      "step": 113
    },
    {
      "epoch": 0.12445414847161572,
      "grad_norm": 0.08401244133710861,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.3312,
      "step": 114
    },
    {
      "epoch": 0.12554585152838427,
      "grad_norm": 0.08806813508272171,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3065,
      "step": 115
    },
    {
      "epoch": 0.12663755458515283,
      "grad_norm": 0.07266682386398315,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3004,
      "step": 116
    },
    {
      "epoch": 0.1277292576419214,
      "grad_norm": 0.07965347915887833,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3287,
      "step": 117
    },
    {
      "epoch": 0.12882096069868995,
      "grad_norm": 0.07704725116491318,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.2863,
      "step": 118
    },
    {
      "epoch": 0.1299126637554585,
      "grad_norm": 0.08367490023374557,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2977,
      "step": 119
    },
    {
      "epoch": 0.13100436681222707,
      "grad_norm": 0.09149157255887985,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3096,
      "step": 120
    },
    {
      "epoch": 0.13209606986899564,
      "grad_norm": 0.0751381367444992,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2934,
      "step": 121
    },
    {
      "epoch": 0.1331877729257642,
      "grad_norm": 0.08060850948095322,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3049,
      "step": 122
    },
    {
      "epoch": 0.13427947598253276,
      "grad_norm": 0.07600171864032745,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2867,
      "step": 123
    },
    {
      "epoch": 0.13537117903930132,
      "grad_norm": 0.08224236220121384,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3192,
      "step": 124
    },
    {
      "epoch": 0.13646288209606988,
      "grad_norm": 0.08224937319755554,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3049,
      "step": 125
    },
    {
      "epoch": 0.13755458515283842,
      "grad_norm": 0.08308456838130951,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3176,
      "step": 126
    },
    {
      "epoch": 0.13864628820960698,
      "grad_norm": 0.07902124524116516,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2985,
      "step": 127
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 0.08209823817014694,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3133,
      "step": 128
    },
    {
      "epoch": 0.1408296943231441,
      "grad_norm": 0.07935135811567307,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3048,
      "step": 129
    },
    {
      "epoch": 0.14192139737991266,
      "grad_norm": 0.10151193290948868,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3046,
      "step": 130
    },
    {
      "epoch": 0.14301310043668122,
      "grad_norm": 0.08930856734514236,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3014,
      "step": 131
    },
    {
      "epoch": 0.14410480349344978,
      "grad_norm": 0.08064421266317368,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2967,
      "step": 132
    },
    {
      "epoch": 0.14519650655021835,
      "grad_norm": 0.08940005302429199,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.29,
      "step": 133
    },
    {
      "epoch": 0.1462882096069869,
      "grad_norm": 0.07480018585920334,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3213,
      "step": 134
    },
    {
      "epoch": 0.14737991266375547,
      "grad_norm": 0.07465320080518723,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2929,
      "step": 135
    },
    {
      "epoch": 0.14847161572052403,
      "grad_norm": 0.07933533191680908,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2663,
      "step": 136
    },
    {
      "epoch": 0.14956331877729256,
      "grad_norm": 0.07854016125202179,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2822,
      "step": 137
    },
    {
      "epoch": 0.15065502183406113,
      "grad_norm": 0.07450557500123978,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2906,
      "step": 138
    },
    {
      "epoch": 0.1517467248908297,
      "grad_norm": 0.08186682313680649,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3108,
      "step": 139
    },
    {
      "epoch": 0.15283842794759825,
      "grad_norm": 0.0828670859336853,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2715,
      "step": 140
    },
    {
      "epoch": 0.1539301310043668,
      "grad_norm": 0.08974476903676987,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3078,
      "step": 141
    },
    {
      "epoch": 0.15502183406113537,
      "grad_norm": 0.08462100476026535,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3128,
      "step": 142
    },
    {
      "epoch": 0.15611353711790393,
      "grad_norm": 0.08132698386907578,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.276,
      "step": 143
    },
    {
      "epoch": 0.1572052401746725,
      "grad_norm": 0.08387470990419388,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2912,
      "step": 144
    },
    {
      "epoch": 0.15829694323144106,
      "grad_norm": 0.07746601849794388,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2807,
      "step": 145
    },
    {
      "epoch": 0.15938864628820962,
      "grad_norm": 0.08222941309213638,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3053,
      "step": 146
    },
    {
      "epoch": 0.16048034934497818,
      "grad_norm": 0.09132669866085052,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.305,
      "step": 147
    },
    {
      "epoch": 0.1615720524017467,
      "grad_norm": 0.09736882895231247,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2986,
      "step": 148
    },
    {
      "epoch": 0.16266375545851527,
      "grad_norm": 0.07748762518167496,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.304,
      "step": 149
    },
    {
      "epoch": 0.16375545851528384,
      "grad_norm": 0.08709319680929184,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2802,
      "step": 150
    },
    {
      "epoch": 0.16375545851528384,
      "eval_loss": 0.30889540910720825,
      "eval_runtime": 43.4257,
      "eval_samples_per_second": 35.532,
      "eval_steps_per_second": 8.889,
      "step": 150
    },
    {
      "epoch": 0.1648471615720524,
      "grad_norm": 0.21688246726989746,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4037,
      "step": 151
    },
    {
      "epoch": 0.16593886462882096,
      "grad_norm": 0.18882548809051514,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3731,
      "step": 152
    },
    {
      "epoch": 0.16703056768558952,
      "grad_norm": 0.15937484800815582,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.3573,
      "step": 153
    },
    {
      "epoch": 0.16812227074235808,
      "grad_norm": 0.15585066378116608,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3821,
      "step": 154
    },
    {
      "epoch": 0.16921397379912664,
      "grad_norm": 0.12806940078735352,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3222,
      "step": 155
    },
    {
      "epoch": 0.1703056768558952,
      "grad_norm": 0.10342378914356232,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3375,
      "step": 156
    },
    {
      "epoch": 0.17139737991266377,
      "grad_norm": 0.09817603975534439,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3276,
      "step": 157
    },
    {
      "epoch": 0.17248908296943233,
      "grad_norm": 0.08999243378639221,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3151,
      "step": 158
    },
    {
      "epoch": 0.17358078602620086,
      "grad_norm": 0.09126586467027664,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3106,
      "step": 159
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.09301239997148514,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3088,
      "step": 160
    },
    {
      "epoch": 0.17576419213973798,
      "grad_norm": 0.07879643887281418,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3233,
      "step": 161
    },
    {
      "epoch": 0.17685589519650655,
      "grad_norm": 0.08082161098718643,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.324,
      "step": 162
    },
    {
      "epoch": 0.1779475982532751,
      "grad_norm": 0.08480893075466156,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.3173,
      "step": 163
    },
    {
      "epoch": 0.17903930131004367,
      "grad_norm": 0.08276057988405228,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.297,
      "step": 164
    },
    {
      "epoch": 0.18013100436681223,
      "grad_norm": 0.09619864076375961,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2755,
      "step": 165
    },
    {
      "epoch": 0.1812227074235808,
      "grad_norm": 0.09253904223442078,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.2988,
      "step": 166
    },
    {
      "epoch": 0.18231441048034935,
      "grad_norm": 0.08451859652996063,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3187,
      "step": 167
    },
    {
      "epoch": 0.18340611353711792,
      "grad_norm": 0.09276089072227478,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.289,
      "step": 168
    },
    {
      "epoch": 0.18449781659388648,
      "grad_norm": 0.09770864248275757,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3006,
      "step": 169
    },
    {
      "epoch": 0.185589519650655,
      "grad_norm": 0.08487655967473984,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2933,
      "step": 170
    },
    {
      "epoch": 0.18668122270742357,
      "grad_norm": 0.08979937434196472,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3154,
      "step": 171
    },
    {
      "epoch": 0.18777292576419213,
      "grad_norm": 0.096524178981781,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2813,
      "step": 172
    },
    {
      "epoch": 0.1888646288209607,
      "grad_norm": 0.10998646914958954,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2969,
      "step": 173
    },
    {
      "epoch": 0.18995633187772926,
      "grad_norm": 0.09334790706634521,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2947,
      "step": 174
    },
    {
      "epoch": 0.19104803493449782,
      "grad_norm": 0.09990426152944565,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2991,
      "step": 175
    },
    {
      "epoch": 0.19213973799126638,
      "grad_norm": 0.08489777147769928,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3212,
      "step": 176
    },
    {
      "epoch": 0.19323144104803494,
      "grad_norm": 0.0899246335029602,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3077,
      "step": 177
    },
    {
      "epoch": 0.1943231441048035,
      "grad_norm": 0.0905328243970871,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2955,
      "step": 178
    },
    {
      "epoch": 0.19541484716157206,
      "grad_norm": 0.08357493579387665,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2989,
      "step": 179
    },
    {
      "epoch": 0.1965065502183406,
      "grad_norm": 0.0902591198682785,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3075,
      "step": 180
    },
    {
      "epoch": 0.19759825327510916,
      "grad_norm": 0.08497989177703857,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2954,
      "step": 181
    },
    {
      "epoch": 0.19868995633187772,
      "grad_norm": 0.08928415179252625,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2792,
      "step": 182
    },
    {
      "epoch": 0.19978165938864628,
      "grad_norm": 0.09985055774450302,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2843,
      "step": 183
    },
    {
      "epoch": 0.20087336244541484,
      "grad_norm": 0.09803275763988495,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2875,
      "step": 184
    },
    {
      "epoch": 0.2019650655021834,
      "grad_norm": 0.08874229341745377,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2972,
      "step": 185
    },
    {
      "epoch": 0.20305676855895197,
      "grad_norm": 0.09153217077255249,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2888,
      "step": 186
    },
    {
      "epoch": 0.20414847161572053,
      "grad_norm": 0.09361408650875092,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.2992,
      "step": 187
    },
    {
      "epoch": 0.2052401746724891,
      "grad_norm": 0.0951196625828743,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2879,
      "step": 188
    },
    {
      "epoch": 0.20633187772925765,
      "grad_norm": 0.09497038275003433,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2795,
      "step": 189
    },
    {
      "epoch": 0.2074235807860262,
      "grad_norm": 0.10524021089076996,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3004,
      "step": 190
    },
    {
      "epoch": 0.20851528384279475,
      "grad_norm": 0.10494808107614517,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3059,
      "step": 191
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 0.10303197801113129,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.283,
      "step": 192
    },
    {
      "epoch": 0.21069868995633187,
      "grad_norm": 0.10884859412908554,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3106,
      "step": 193
    },
    {
      "epoch": 0.21179039301310043,
      "grad_norm": 0.1263623982667923,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2823,
      "step": 194
    },
    {
      "epoch": 0.212882096069869,
      "grad_norm": 0.11123377829790115,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2804,
      "step": 195
    },
    {
      "epoch": 0.21397379912663755,
      "grad_norm": 0.12132084369659424,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3011,
      "step": 196
    },
    {
      "epoch": 0.21506550218340612,
      "grad_norm": 0.11492640525102615,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.298,
      "step": 197
    },
    {
      "epoch": 0.21615720524017468,
      "grad_norm": 0.13940326869487762,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2876,
      "step": 198
    },
    {
      "epoch": 0.21724890829694324,
      "grad_norm": 0.13420909643173218,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.2906,
      "step": 199
    },
    {
      "epoch": 0.2183406113537118,
      "grad_norm": 0.1722777783870697,
      "learning_rate": 0.0,
      "loss": 0.29,
      "step": 200
    },
    {
      "epoch": 0.2183406113537118,
      "eval_loss": 0.3034655451774597,
      "eval_runtime": 43.4259,
      "eval_samples_per_second": 35.532,
      "eval_steps_per_second": 8.889,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.61808020979712e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}