{
  "best_metric": 0.2700521647930145,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.8465608465608465,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004232804232804233,
      "grad_norm": 5.989807605743408,
      "learning_rate": 1e-05,
      "loss": 1.3666,
      "step": 1
    },
    {
      "epoch": 0.004232804232804233,
      "eval_loss": 5.062282085418701,
      "eval_runtime": 7.109,
      "eval_samples_per_second": 55.986,
      "eval_steps_per_second": 14.067,
      "step": 1
    },
    {
      "epoch": 0.008465608465608466,
      "grad_norm": 6.316153526306152,
      "learning_rate": 2e-05,
      "loss": 1.345,
      "step": 2
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 10.638800621032715,
      "learning_rate": 3e-05,
      "loss": 2.6268,
      "step": 3
    },
    {
      "epoch": 0.016931216931216932,
      "grad_norm": 12.878622055053711,
      "learning_rate": 4e-05,
      "loss": 3.2138,
      "step": 4
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 7.205965995788574,
      "learning_rate": 5e-05,
      "loss": 1.4688,
      "step": 5
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 17.53158950805664,
      "learning_rate": 6e-05,
      "loss": 2.2297,
      "step": 6
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 10.184916496276855,
      "learning_rate": 7e-05,
      "loss": 1.6321,
      "step": 7
    },
    {
      "epoch": 0.033862433862433865,
      "grad_norm": 14.531895637512207,
      "learning_rate": 8e-05,
      "loss": 1.3396,
      "step": 8
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 13.539246559143066,
      "learning_rate": 9e-05,
      "loss": 1.1216,
      "step": 9
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 8.313826560974121,
      "learning_rate": 0.0001,
      "loss": 0.9915,
      "step": 10
    },
    {
      "epoch": 0.04656084656084656,
      "grad_norm": 5.908563613891602,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.902,
      "step": 11
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 4.567006587982178,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7427,
      "step": 12
    },
    {
      "epoch": 0.05502645502645503,
      "grad_norm": 6.336626052856445,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6648,
      "step": 13
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 3.9336471557617188,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7127,
      "step": 14
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 5.1749725341796875,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5122,
      "step": 15
    },
    {
      "epoch": 0.06772486772486773,
      "grad_norm": 5.035114765167236,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5864,
      "step": 16
    },
    {
      "epoch": 0.07195767195767196,
      "grad_norm": 4.580766677856445,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5264,
      "step": 17
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 4.2058563232421875,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.545,
      "step": 18
    },
    {
      "epoch": 0.08042328042328042,
      "grad_norm": 6.226001262664795,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.645,
      "step": 19
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 2.989558696746826,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3268,
      "step": 20
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 8.131072998046875,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6012,
      "step": 21
    },
    {
      "epoch": 0.09312169312169312,
      "grad_norm": 7.674716472625732,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4165,
      "step": 22
    },
    {
      "epoch": 0.09735449735449736,
      "grad_norm": 4.038910388946533,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4262,
      "step": 23
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 6.8995795249938965,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6409,
      "step": 24
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 3.941877841949463,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.384,
      "step": 25
    },
    {
      "epoch": 0.11005291005291006,
      "grad_norm": 3.928475856781006,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.4626,
      "step": 26
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 5.764224529266357,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4601,
      "step": 27
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 4.498023509979248,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.5976,
      "step": 28
    },
    {
      "epoch": 0.12275132275132275,
      "grad_norm": 3.8926656246185303,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3461,
      "step": 29
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 3.7749056816101074,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3468,
      "step": 30
    },
    {
      "epoch": 0.1312169312169312,
      "grad_norm": 5.922031879425049,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5041,
      "step": 31
    },
    {
      "epoch": 0.13544973544973546,
      "grad_norm": 3.284172296524048,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2845,
      "step": 32
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 4.106979846954346,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4244,
      "step": 33
    },
    {
      "epoch": 0.1439153439153439,
      "grad_norm": 5.331764221191406,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4698,
      "step": 34
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 3.97413969039917,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3834,
      "step": 35
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 5.981215000152588,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.4205,
      "step": 36
    },
    {
      "epoch": 0.15661375661375662,
      "grad_norm": 4.704588890075684,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4636,
      "step": 37
    },
    {
      "epoch": 0.16084656084656085,
      "grad_norm": 4.563809871673584,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3524,
      "step": 38
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 3.0323660373687744,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2673,
      "step": 39
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 4.433314800262451,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.483,
      "step": 40
    },
    {
      "epoch": 0.17354497354497356,
      "grad_norm": 4.264368057250977,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3424,
      "step": 41
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 3.4314918518066406,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3673,
      "step": 42
    },
    {
      "epoch": 0.182010582010582,
      "grad_norm": 3.459148645401001,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.38,
      "step": 43
    },
    {
      "epoch": 0.18624338624338624,
      "grad_norm": 4.779259204864502,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4235,
      "step": 44
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.835719585418701,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3475,
      "step": 45
    },
    {
      "epoch": 0.19470899470899472,
      "grad_norm": 7.6107707023620605,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5044,
      "step": 46
    },
    {
      "epoch": 0.19894179894179895,
      "grad_norm": 5.723545074462891,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5977,
      "step": 47
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 4.643585681915283,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4517,
      "step": 48
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 4.273600101470947,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3745,
      "step": 49
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 4.797636985778809,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3813,
      "step": 50
    },
    {
      "epoch": 0.21164021164021163,
      "eval_loss": 0.5755835771560669,
      "eval_runtime": 6.9872,
      "eval_samples_per_second": 56.961,
      "eval_steps_per_second": 14.312,
      "step": 50
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 20.69525146484375,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9335,
      "step": 51
    },
    {
      "epoch": 0.2201058201058201,
      "grad_norm": 11.730290412902832,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6205,
      "step": 52
    },
    {
      "epoch": 0.22433862433862434,
      "grad_norm": 5.993229389190674,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5954,
      "step": 53
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 3.6728155612945557,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4229,
      "step": 54
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 4.024419784545898,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3441,
      "step": 55
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 4.492297649383545,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4556,
      "step": 56
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 3.746833562850952,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2984,
      "step": 57
    },
    {
      "epoch": 0.2455026455026455,
      "grad_norm": 3.87406587600708,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3625,
      "step": 58
    },
    {
      "epoch": 0.24973544973544973,
      "grad_norm": 2.2833709716796875,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.307,
      "step": 59
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 2.9336328506469727,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4017,
      "step": 60
    },
    {
      "epoch": 0.2582010582010582,
      "grad_norm": 2.199486017227173,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.2931,
      "step": 61
    },
    {
      "epoch": 0.2624338624338624,
      "grad_norm": 2.768583059310913,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3269,
      "step": 62
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.6997485160827637,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2989,
      "step": 63
    },
    {
      "epoch": 0.2708994708994709,
      "grad_norm": 1.978134274482727,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2595,
      "step": 64
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 2.372404098510742,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3205,
      "step": 65
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 2.7943341732025146,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2694,
      "step": 66
    },
    {
      "epoch": 0.28359788359788357,
      "grad_norm": 2.8816003799438477,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2665,
      "step": 67
    },
    {
      "epoch": 0.2878306878306878,
      "grad_norm": 3.0825653076171875,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3359,
      "step": 68
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 4.2906646728515625,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2757,
      "step": 69
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 3.2166454792022705,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3426,
      "step": 70
    },
    {
      "epoch": 0.30052910052910053,
      "grad_norm": 2.342562675476074,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2638,
      "step": 71
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 2.900041341781616,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1823,
      "step": 72
    },
    {
      "epoch": 0.308994708994709,
      "grad_norm": 4.97504186630249,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4141,
      "step": 73
    },
    {
      "epoch": 0.31322751322751324,
      "grad_norm": 4.636997222900391,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2363,
      "step": 74
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.6801393032073975,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2555,
      "step": 75
    },
    {
      "epoch": 0.3216931216931217,
      "grad_norm": 2.5482003688812256,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2069,
      "step": 76
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 4.265755653381348,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.3863,
      "step": 77
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 2.9740467071533203,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2409,
      "step": 78
    },
    {
      "epoch": 0.3343915343915344,
      "grad_norm": 5.217772483825684,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.318,
      "step": 79
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 2.200723886489868,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.2173,
      "step": 80
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 2.724498748779297,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.256,
      "step": 81
    },
    {
      "epoch": 0.3470899470899471,
      "grad_norm": 1.8411164283752441,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.1702,
      "step": 82
    },
    {
      "epoch": 0.3513227513227513,
      "grad_norm": 2.9929609298706055,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2627,
      "step": 83
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.430234909057617,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2584,
      "step": 84
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 2.970780849456787,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2901,
      "step": 85
    },
    {
      "epoch": 0.364021164021164,
      "grad_norm": 3.937288761138916,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4919,
      "step": 86
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 2.6099743843078613,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.311,
      "step": 87
    },
    {
      "epoch": 0.3724867724867725,
      "grad_norm": 2.918137311935425,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3155,
      "step": 88
    },
    {
      "epoch": 0.37671957671957673,
      "grad_norm": 3.519662857055664,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2522,
      "step": 89
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.4978795051574707,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2469,
      "step": 90
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 3.212397336959839,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2626,
      "step": 91
    },
    {
      "epoch": 0.38941798941798944,
      "grad_norm": 3.0960588455200195,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2057,
      "step": 92
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 4.3554463386535645,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.288,
      "step": 93
    },
    {
      "epoch": 0.3978835978835979,
      "grad_norm": 2.8997602462768555,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2262,
      "step": 94
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 3.578720808029175,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3103,
      "step": 95
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 5.090838432312012,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5029,
      "step": 96
    },
    {
      "epoch": 0.4105820105820106,
      "grad_norm": 3.4183642864227295,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2747,
      "step": 97
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 5.304195404052734,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4358,
      "step": 98
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 3.6772615909576416,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3692,
      "step": 99
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 4.6896443367004395,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2795,
      "step": 100
    },
    {
      "epoch": 0.42328042328042326,
      "eval_loss": 0.36472705006599426,
      "eval_runtime": 7.0094,
      "eval_samples_per_second": 56.781,
      "eval_steps_per_second": 14.267,
      "step": 100
    },
    {
      "epoch": 0.4275132275132275,
      "grad_norm": 5.146337509155273,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.308,
      "step": 101
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 5.34895133972168,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4739,
      "step": 102
    },
    {
      "epoch": 0.43597883597883597,
      "grad_norm": 3.8021786212921143,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3234,
      "step": 103
    },
    {
      "epoch": 0.4402116402116402,
      "grad_norm": 1.8886805772781372,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2313,
      "step": 104
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.8070755004882812,
      "learning_rate": 5e-05,
      "loss": 0.232,
      "step": 105
    },
    {
      "epoch": 0.4486772486772487,
      "grad_norm": 1.6209335327148438,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1647,
      "step": 106
    },
    {
      "epoch": 0.45291005291005293,
      "grad_norm": 2.5175647735595703,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2209,
      "step": 107
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 3.4359962940216064,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2189,
      "step": 108
    },
    {
      "epoch": 0.4613756613756614,
      "grad_norm": 3.6596169471740723,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.328,
      "step": 109
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 4.373483180999756,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4405,
      "step": 110
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 1.9046685695648193,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.2028,
      "step": 111
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.4778344631195068,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1099,
      "step": 112
    },
    {
      "epoch": 0.4783068783068783,
      "grad_norm": 1.6936434507369995,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1587,
      "step": 113
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 2.3894147872924805,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2339,
      "step": 114
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 1.4886194467544556,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.147,
      "step": 115
    },
    {
      "epoch": 0.491005291005291,
      "grad_norm": 2.1064565181732178,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1837,
      "step": 116
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 2.651761770248413,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.2609,
      "step": 117
    },
    {
      "epoch": 0.49947089947089945,
      "grad_norm": 2.197373390197754,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1743,
      "step": 118
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 2.887385368347168,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2721,
      "step": 119
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.6008212566375732,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1933,
      "step": 120
    },
    {
      "epoch": 0.5121693121693122,
      "grad_norm": 3.60152006149292,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3356,
      "step": 121
    },
    {
      "epoch": 0.5164021164021164,
      "grad_norm": 2.5666725635528564,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.225,
      "step": 122
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 3.189014196395874,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3376,
      "step": 123
    },
    {
      "epoch": 0.5248677248677248,
      "grad_norm": 2.342768430709839,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2432,
      "step": 124
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 2.7981984615325928,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.241,
      "step": 125
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.9936574697494507,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2379,
      "step": 126
    },
    {
      "epoch": 0.5375661375661376,
      "grad_norm": 3.128868818283081,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2296,
      "step": 127
    },
    {
      "epoch": 0.5417989417989418,
      "grad_norm": 2.780970811843872,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2795,
      "step": 128
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 2.3473737239837646,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.1861,
      "step": 129
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 2.4287045001983643,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.2407,
      "step": 130
    },
    {
      "epoch": 0.5544973544973545,
      "grad_norm": 3.5494046211242676,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2898,
      "step": 131
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 3.836782932281494,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3,
      "step": 132
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 2.944845199584961,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2455,
      "step": 133
    },
    {
      "epoch": 0.5671957671957671,
      "grad_norm": 3.2262251377105713,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2911,
      "step": 134
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.456899642944336,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2159,
      "step": 135
    },
    {
      "epoch": 0.5756613756613757,
      "grad_norm": 3.59541916847229,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3309,
      "step": 136
    },
    {
      "epoch": 0.5798941798941799,
      "grad_norm": 2.197277545928955,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.1675,
      "step": 137
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 1.3671990633010864,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1157,
      "step": 138
    },
    {
      "epoch": 0.5883597883597883,
      "grad_norm": 3.6059229373931885,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.2949,
      "step": 139
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 2.130404472351074,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1753,
      "step": 140
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 3.1766140460968018,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3266,
      "step": 141
    },
    {
      "epoch": 0.6010582010582011,
      "grad_norm": 2.271630048751831,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.1516,
      "step": 142
    },
    {
      "epoch": 0.6052910052910053,
      "grad_norm": 3.10626482963562,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2478,
      "step": 143
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 2.8248608112335205,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2155,
      "step": 144
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 1.9203581809997559,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1176,
      "step": 145
    },
    {
      "epoch": 0.617989417989418,
      "grad_norm": 2.805983543395996,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2056,
      "step": 146
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.9474689960479736,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2977,
      "step": 147
    },
    {
      "epoch": 0.6264550264550265,
      "grad_norm": 4.4699788093566895,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4549,
      "step": 148
    },
    {
      "epoch": 0.6306878306878307,
      "grad_norm": 4.517536163330078,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3431,
      "step": 149
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 4.581890106201172,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3979,
      "step": 150
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 0.2808743715286255,
      "eval_runtime": 7.0376,
      "eval_samples_per_second": 56.554,
      "eval_steps_per_second": 14.209,
      "step": 150
    },
    {
      "epoch": 0.6391534391534391,
      "grad_norm": 1.4164944887161255,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.126,
      "step": 151
    },
    {
      "epoch": 0.6433862433862434,
      "grad_norm": 2.673814058303833,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2205,
      "step": 152
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 3.4250433444976807,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.2783,
      "step": 153
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 2.1850826740264893,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1736,
      "step": 154
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 2.3093180656433105,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1921,
      "step": 155
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 2.9909355640411377,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.2812,
      "step": 156
    },
    {
      "epoch": 0.6645502645502646,
      "grad_norm": 2.1385881900787354,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1607,
      "step": 157
    },
    {
      "epoch": 0.6687830687830688,
      "grad_norm": 2.3770594596862793,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2192,
      "step": 158
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 1.6676785945892334,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.142,
      "step": 159
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 1.4343023300170898,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1207,
      "step": 160
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.645560383796692,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1328,
      "step": 161
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.8658156394958496,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1755,
      "step": 162
    },
    {
      "epoch": 0.68994708994709,
      "grad_norm": 3.323204755783081,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.3358,
      "step": 163
    },
    {
      "epoch": 0.6941798941798942,
      "grad_norm": 2.0126280784606934,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1846,
      "step": 164
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 1.881239891052246,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1686,
      "step": 165
    },
    {
      "epoch": 0.7026455026455026,
      "grad_norm": 2.024827718734741,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1695,
      "step": 166
    },
    {
      "epoch": 0.7068783068783069,
      "grad_norm": 2.1224584579467773,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.1574,
      "step": 167
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.7643535137176514,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2625,
      "step": 168
    },
    {
      "epoch": 0.7153439153439154,
      "grad_norm": 1.9550964832305908,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2037,
      "step": 169
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 2.267641305923462,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1929,
      "step": 170
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 1.5063822269439697,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.1445,
      "step": 171
    },
    {
      "epoch": 0.728042328042328,
      "grad_norm": 2.174779176712036,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2054,
      "step": 172
    },
    {
      "epoch": 0.7322751322751323,
      "grad_norm": 2.037992477416992,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2259,
      "step": 173
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 2.3221635818481445,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.232,
      "step": 174
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.7228755950927734,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2813,
      "step": 175
    },
    {
      "epoch": 0.744973544973545,
      "grad_norm": 1.9721616506576538,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1698,
      "step": 176
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 2.4876978397369385,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3285,
      "step": 177
    },
    {
      "epoch": 0.7534391534391535,
      "grad_norm": 1.5748313665390015,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1139,
      "step": 178
    },
    {
      "epoch": 0.7576719576719577,
      "grad_norm": 2.8624324798583984,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2948,
      "step": 179
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.4231516122817993,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1268,
      "step": 180
    },
    {
      "epoch": 0.7661375661375661,
      "grad_norm": 2.291111707687378,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2673,
      "step": 181
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 2.087951421737671,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1376,
      "step": 182
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 2.8163769245147705,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2216,
      "step": 183
    },
    {
      "epoch": 0.7788359788359789,
      "grad_norm": 2.627511501312256,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2518,
      "step": 184
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 4.190913200378418,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3029,
      "step": 185
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 2.049123764038086,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2338,
      "step": 186
    },
    {
      "epoch": 0.7915343915343915,
      "grad_norm": 1.5632001161575317,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.15,
      "step": 187
    },
    {
      "epoch": 0.7957671957671958,
      "grad_norm": 2.3084685802459717,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1823,
      "step": 188
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.2926528453826904,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.1124,
      "step": 189
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 3.5566582679748535,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3107,
      "step": 190
    },
    {
      "epoch": 0.8084656084656084,
      "grad_norm": 2.930521249771118,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2431,
      "step": 191
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 2.847296714782715,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2566,
      "step": 192
    },
    {
      "epoch": 0.816931216931217,
      "grad_norm": 2.586358070373535,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.1997,
      "step": 193
    },
    {
      "epoch": 0.8211640211640212,
      "grad_norm": 2.188652276992798,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2186,
      "step": 194
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 2.7327771186828613,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.244,
      "step": 195
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 3.0980334281921387,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3155,
      "step": 196
    },
    {
      "epoch": 0.8338624338624339,
      "grad_norm": 3.2832977771759033,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.1617,
      "step": 197
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 3.0339345932006836,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2642,
      "step": 198
    },
    {
      "epoch": 0.8423280423280424,
      "grad_norm": 5.147420406341553,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4465,
      "step": 199
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 5.519458293914795,
      "learning_rate": 0.0,
      "loss": 0.323,
      "step": 200
    },
    {
      "epoch": 0.8465608465608465,
      "eval_loss": 0.2700521647930145,
      "eval_runtime": 6.971,
      "eval_samples_per_second": 57.093,
      "eval_steps_per_second": 14.345,
      "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": 1.54569648635904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}