{
  "best_metric": 0.7657567262649536,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.08241758241758242,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005494505494505495,
      "grad_norm": 10.20637035369873,
      "learning_rate": 1e-05,
      "loss": 1.7034,
      "step": 1
    },
    {
      "epoch": 0.0005494505494505495,
      "eval_loss": 2.4982120990753174,
      "eval_runtime": 246.1723,
      "eval_samples_per_second": 12.455,
      "eval_steps_per_second": 3.116,
      "step": 1
    },
    {
      "epoch": 0.001098901098901099,
      "grad_norm": 11.44153118133545,
      "learning_rate": 2e-05,
      "loss": 2.029,
      "step": 2
    },
    {
      "epoch": 0.0016483516483516484,
      "grad_norm": 11.39004135131836,
      "learning_rate": 3e-05,
      "loss": 1.9351,
      "step": 3
    },
    {
      "epoch": 0.002197802197802198,
      "grad_norm": 12.599936485290527,
      "learning_rate": 4e-05,
      "loss": 1.6733,
      "step": 4
    },
    {
      "epoch": 0.0027472527472527475,
      "grad_norm": 9.226388931274414,
      "learning_rate": 5e-05,
      "loss": 1.5285,
      "step": 5
    },
    {
      "epoch": 0.0032967032967032967,
      "grad_norm": 7.024893283843994,
      "learning_rate": 6e-05,
      "loss": 1.147,
      "step": 6
    },
    {
      "epoch": 0.0038461538461538464,
      "grad_norm": 8.669913291931152,
      "learning_rate": 7e-05,
      "loss": 1.2284,
      "step": 7
    },
    {
      "epoch": 0.004395604395604396,
      "grad_norm": 7.4318156242370605,
      "learning_rate": 8e-05,
      "loss": 0.9729,
      "step": 8
    },
    {
      "epoch": 0.004945054945054945,
      "grad_norm": 7.1173996925354,
      "learning_rate": 9e-05,
      "loss": 0.9166,
      "step": 9
    },
    {
      "epoch": 0.005494505494505495,
      "grad_norm": 7.444589138031006,
      "learning_rate": 0.0001,
      "loss": 1.1277,
      "step": 10
    },
    {
      "epoch": 0.006043956043956044,
      "grad_norm": 6.673343658447266,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9009,
      "step": 11
    },
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 5.152169704437256,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9832,
      "step": 12
    },
    {
      "epoch": 0.007142857142857143,
      "grad_norm": 5.281370639801025,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8636,
      "step": 13
    },
    {
      "epoch": 0.007692307692307693,
      "grad_norm": 4.680879592895508,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8871,
      "step": 14
    },
    {
      "epoch": 0.008241758241758242,
      "grad_norm": 4.400333881378174,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9835,
      "step": 15
    },
    {
      "epoch": 0.008791208791208791,
      "grad_norm": 5.351457595825195,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8755,
      "step": 16
    },
    {
      "epoch": 0.00934065934065934,
      "grad_norm": 4.729643821716309,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9769,
      "step": 17
    },
    {
      "epoch": 0.00989010989010989,
      "grad_norm": 4.137618064880371,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.846,
      "step": 18
    },
    {
      "epoch": 0.010439560439560439,
      "grad_norm": 4.284829139709473,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8022,
      "step": 19
    },
    {
      "epoch": 0.01098901098901099,
      "grad_norm": 5.623097896575928,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8643,
      "step": 20
    },
    {
      "epoch": 0.011538461538461539,
      "grad_norm": 4.570623397827148,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8482,
      "step": 21
    },
    {
      "epoch": 0.012087912087912088,
      "grad_norm": 5.434322357177734,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9303,
      "step": 22
    },
    {
      "epoch": 0.012637362637362638,
      "grad_norm": 5.448188781738281,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0636,
      "step": 23
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 5.108726501464844,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.056,
      "step": 24
    },
    {
      "epoch": 0.013736263736263736,
      "grad_norm": 4.536986351013184,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9214,
      "step": 25
    },
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 4.402527809143066,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.712,
      "step": 26
    },
    {
      "epoch": 0.014835164835164835,
      "grad_norm": 4.430077075958252,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9547,
      "step": 27
    },
    {
      "epoch": 0.015384615384615385,
      "grad_norm": 3.4363932609558105,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7263,
      "step": 28
    },
    {
      "epoch": 0.015934065934065933,
      "grad_norm": 4.152787685394287,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7906,
      "step": 29
    },
    {
      "epoch": 0.016483516483516484,
      "grad_norm": 4.174340724945068,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9927,
      "step": 30
    },
    {
      "epoch": 0.01703296703296703,
      "grad_norm": 4.010305881500244,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9093,
      "step": 31
    },
    {
      "epoch": 0.017582417582417582,
      "grad_norm": 3.8751678466796875,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7975,
      "step": 32
    },
    {
      "epoch": 0.018131868131868133,
      "grad_norm": 3.810492992401123,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8229,
      "step": 33
    },
    {
      "epoch": 0.01868131868131868,
      "grad_norm": 3.694744110107422,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8752,
      "step": 34
    },
    {
      "epoch": 0.019230769230769232,
      "grad_norm": 3.96274733543396,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6688,
      "step": 35
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 4.120517730712891,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.747,
      "step": 36
    },
    {
      "epoch": 0.02032967032967033,
      "grad_norm": 4.018519878387451,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6797,
      "step": 37
    },
    {
      "epoch": 0.020879120879120878,
      "grad_norm": 4.266332626342773,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8611,
      "step": 38
    },
    {
      "epoch": 0.02142857142857143,
      "grad_norm": 4.074350833892822,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7577,
      "step": 39
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 3.547234535217285,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.808,
      "step": 40
    },
    {
      "epoch": 0.022527472527472527,
      "grad_norm": 4.03273344039917,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7009,
      "step": 41
    },
    {
      "epoch": 0.023076923076923078,
      "grad_norm": 5.0143537521362305,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9845,
      "step": 42
    },
    {
      "epoch": 0.023626373626373626,
      "grad_norm": 3.6202425956726074,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8286,
      "step": 43
    },
    {
      "epoch": 0.024175824175824177,
      "grad_norm": 3.7478301525115967,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7181,
      "step": 44
    },
    {
      "epoch": 0.024725274725274724,
      "grad_norm": 3.7263989448547363,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6388,
      "step": 45
    },
    {
      "epoch": 0.025274725274725275,
      "grad_norm": 4.423315525054932,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7229,
      "step": 46
    },
    {
      "epoch": 0.025824175824175823,
      "grad_norm": 3.4380674362182617,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6488,
      "step": 47
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 3.32068133354187,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6034,
      "step": 48
    },
    {
      "epoch": 0.026923076923076925,
      "grad_norm": 3.828432559967041,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.646,
      "step": 49
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 4.410627365112305,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7029,
      "step": 50
    },
    {
      "epoch": 0.027472527472527472,
      "eval_loss": 0.8551605939865112,
      "eval_runtime": 248.255,
      "eval_samples_per_second": 12.35,
      "eval_steps_per_second": 3.09,
      "step": 50
    },
    {
      "epoch": 0.028021978021978023,
      "grad_norm": 4.3182268142700195,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9381,
      "step": 51
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 3.6858444213867188,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0042,
      "step": 52
    },
    {
      "epoch": 0.02912087912087912,
      "grad_norm": 3.4486730098724365,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9807,
      "step": 53
    },
    {
      "epoch": 0.02967032967032967,
      "grad_norm": 4.263784885406494,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7938,
      "step": 54
    },
    {
      "epoch": 0.03021978021978022,
      "grad_norm": 3.1360929012298584,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7528,
      "step": 55
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 3.7347052097320557,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8403,
      "step": 56
    },
    {
      "epoch": 0.03131868131868132,
      "grad_norm": 3.3182191848754883,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8076,
      "step": 57
    },
    {
      "epoch": 0.031868131868131866,
      "grad_norm": 2.980205774307251,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7868,
      "step": 58
    },
    {
      "epoch": 0.03241758241758242,
      "grad_norm": 3.3988683223724365,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8072,
      "step": 59
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 3.52750301361084,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8784,
      "step": 60
    },
    {
      "epoch": 0.033516483516483515,
      "grad_norm": 3.604893684387207,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7565,
      "step": 61
    },
    {
      "epoch": 0.03406593406593406,
      "grad_norm": 3.4089083671569824,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8974,
      "step": 62
    },
    {
      "epoch": 0.03461538461538462,
      "grad_norm": 4.178040504455566,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.868,
      "step": 63
    },
    {
      "epoch": 0.035164835164835165,
      "grad_norm": 3.4511518478393555,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.0132,
      "step": 64
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 3.3299479484558105,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8356,
      "step": 65
    },
    {
      "epoch": 0.03626373626373627,
      "grad_norm": 3.3526644706726074,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8513,
      "step": 66
    },
    {
      "epoch": 0.036813186813186814,
      "grad_norm": 3.367147922515869,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0042,
      "step": 67
    },
    {
      "epoch": 0.03736263736263736,
      "grad_norm": 3.2283849716186523,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8084,
      "step": 68
    },
    {
      "epoch": 0.03791208791208791,
      "grad_norm": 3.1080996990203857,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9091,
      "step": 69
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 3.440809488296509,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.912,
      "step": 70
    },
    {
      "epoch": 0.03901098901098901,
      "grad_norm": 4.543209552764893,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9512,
      "step": 71
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 3.6167526245117188,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7516,
      "step": 72
    },
    {
      "epoch": 0.04010989010989011,
      "grad_norm": 4.1947479248046875,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9431,
      "step": 73
    },
    {
      "epoch": 0.04065934065934066,
      "grad_norm": 3.461369752883911,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8908,
      "step": 74
    },
    {
      "epoch": 0.04120879120879121,
      "grad_norm": 3.3791346549987793,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7087,
      "step": 75
    },
    {
      "epoch": 0.041758241758241756,
      "grad_norm": 3.541050434112549,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7779,
      "step": 76
    },
    {
      "epoch": 0.04230769230769231,
      "grad_norm": 3.108454465866089,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8149,
      "step": 77
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 3.772913932800293,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7668,
      "step": 78
    },
    {
      "epoch": 0.043406593406593405,
      "grad_norm": 3.0966885089874268,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8225,
      "step": 79
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 3.7791407108306885,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8693,
      "step": 80
    },
    {
      "epoch": 0.04450549450549451,
      "grad_norm": 4.253763198852539,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0137,
      "step": 81
    },
    {
      "epoch": 0.045054945054945054,
      "grad_norm": 3.970787525177002,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.0145,
      "step": 82
    },
    {
      "epoch": 0.0456043956043956,
      "grad_norm": 3.273193597793579,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8402,
      "step": 83
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 3.246183156967163,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8381,
      "step": 84
    },
    {
      "epoch": 0.046703296703296704,
      "grad_norm": 3.3997747898101807,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9744,
      "step": 85
    },
    {
      "epoch": 0.04725274725274725,
      "grad_norm": 3.4663801193237305,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9223,
      "step": 86
    },
    {
      "epoch": 0.0478021978021978,
      "grad_norm": 3.421869993209839,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9882,
      "step": 87
    },
    {
      "epoch": 0.04835164835164835,
      "grad_norm": 2.5848114490509033,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6518,
      "step": 88
    },
    {
      "epoch": 0.0489010989010989,
      "grad_norm": 4.04249382019043,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8867,
      "step": 89
    },
    {
      "epoch": 0.04945054945054945,
      "grad_norm": 3.6130316257476807,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8811,
      "step": 90
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.202869176864624,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6812,
      "step": 91
    },
    {
      "epoch": 0.05054945054945055,
      "grad_norm": 5.957513332366943,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8074,
      "step": 92
    },
    {
      "epoch": 0.0510989010989011,
      "grad_norm": 9.279909133911133,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7514,
      "step": 93
    },
    {
      "epoch": 0.051648351648351645,
      "grad_norm": 3.816479206085205,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7612,
      "step": 94
    },
    {
      "epoch": 0.0521978021978022,
      "grad_norm": 3.6703317165374756,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6952,
      "step": 95
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.994513988494873,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5601,
      "step": 96
    },
    {
      "epoch": 0.053296703296703295,
      "grad_norm": 3.6805593967437744,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7776,
      "step": 97
    },
    {
      "epoch": 0.05384615384615385,
      "grad_norm": 3.7631995677948,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6875,
      "step": 98
    },
    {
      "epoch": 0.0543956043956044,
      "grad_norm": 4.067095756530762,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6078,
      "step": 99
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 3.9707226753234863,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5355,
      "step": 100
    },
    {
      "epoch": 0.054945054945054944,
      "eval_loss": 0.810309112071991,
      "eval_runtime": 248.3207,
      "eval_samples_per_second": 12.347,
      "eval_steps_per_second": 3.089,
      "step": 100
    },
    {
      "epoch": 0.05549450549450549,
      "grad_norm": 2.7428088188171387,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8487,
      "step": 101
    },
    {
      "epoch": 0.056043956043956046,
      "grad_norm": 4.557298183441162,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7637,
      "step": 102
    },
    {
      "epoch": 0.056593406593406594,
      "grad_norm": 3.209634780883789,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8463,
      "step": 103
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 5.7075276374816895,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7269,
      "step": 104
    },
    {
      "epoch": 0.057692307692307696,
      "grad_norm": 3.590937376022339,
      "learning_rate": 5e-05,
      "loss": 0.9204,
      "step": 105
    },
    {
      "epoch": 0.05824175824175824,
      "grad_norm": 3.8173980712890625,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9498,
      "step": 106
    },
    {
      "epoch": 0.05879120879120879,
      "grad_norm": 3.6682701110839844,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.846,
      "step": 107
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 3.0619313716888428,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7405,
      "step": 108
    },
    {
      "epoch": 0.05989010989010989,
      "grad_norm": 3.3937807083129883,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8557,
      "step": 109
    },
    {
      "epoch": 0.06043956043956044,
      "grad_norm": 3.5738933086395264,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8423,
      "step": 110
    },
    {
      "epoch": 0.06098901098901099,
      "grad_norm": 3.2693288326263428,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7375,
      "step": 111
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 3.017500638961792,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7283,
      "step": 112
    },
    {
      "epoch": 0.06208791208791209,
      "grad_norm": 3.3882884979248047,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.949,
      "step": 113
    },
    {
      "epoch": 0.06263736263736264,
      "grad_norm": 3.357642650604248,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9024,
      "step": 114
    },
    {
      "epoch": 0.06318681318681318,
      "grad_norm": 3.2038471698760986,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7567,
      "step": 115
    },
    {
      "epoch": 0.06373626373626373,
      "grad_norm": 3.5930140018463135,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.847,
      "step": 116
    },
    {
      "epoch": 0.06428571428571428,
      "grad_norm": 3.030806303024292,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.817,
      "step": 117
    },
    {
      "epoch": 0.06483516483516484,
      "grad_norm": 3.528214693069458,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8314,
      "step": 118
    },
    {
      "epoch": 0.06538461538461539,
      "grad_norm": 3.717010736465454,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8658,
      "step": 119
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 3.4061574935913086,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7038,
      "step": 120
    },
    {
      "epoch": 0.06648351648351648,
      "grad_norm": 2.5591681003570557,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7427,
      "step": 121
    },
    {
      "epoch": 0.06703296703296703,
      "grad_norm": 3.146589756011963,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.724,
      "step": 122
    },
    {
      "epoch": 0.06758241758241758,
      "grad_norm": 3.002185344696045,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6943,
      "step": 123
    },
    {
      "epoch": 0.06813186813186813,
      "grad_norm": 3.108757257461548,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8639,
      "step": 124
    },
    {
      "epoch": 0.06868131868131869,
      "grad_norm": 3.310210704803467,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9398,
      "step": 125
    },
    {
      "epoch": 0.06923076923076923,
      "grad_norm": 3.308823347091675,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.788,
      "step": 126
    },
    {
      "epoch": 0.06978021978021978,
      "grad_norm": 3.1850717067718506,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7686,
      "step": 127
    },
    {
      "epoch": 0.07032967032967033,
      "grad_norm": 3.594505786895752,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7049,
      "step": 128
    },
    {
      "epoch": 0.07087912087912088,
      "grad_norm": 3.527811288833618,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9086,
      "step": 129
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 3.708664894104004,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8532,
      "step": 130
    },
    {
      "epoch": 0.07197802197802197,
      "grad_norm": 3.2360305786132812,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6813,
      "step": 131
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 4.264449596405029,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.958,
      "step": 132
    },
    {
      "epoch": 0.07307692307692308,
      "grad_norm": 2.919825315475464,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7465,
      "step": 133
    },
    {
      "epoch": 0.07362637362637363,
      "grad_norm": 3.232802629470825,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7196,
      "step": 134
    },
    {
      "epoch": 0.07417582417582418,
      "grad_norm": 3.242577314376831,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.71,
      "step": 135
    },
    {
      "epoch": 0.07472527472527472,
      "grad_norm": 3.7792561054229736,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8448,
      "step": 136
    },
    {
      "epoch": 0.07527472527472527,
      "grad_norm": 3.8947784900665283,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.9169,
      "step": 137
    },
    {
      "epoch": 0.07582417582417582,
      "grad_norm": 3.439913749694824,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7157,
      "step": 138
    },
    {
      "epoch": 0.07637362637362638,
      "grad_norm": 2.68253231048584,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6558,
      "step": 139
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 4.011876583099365,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9641,
      "step": 140
    },
    {
      "epoch": 0.07747252747252747,
      "grad_norm": 4.138200759887695,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7938,
      "step": 141
    },
    {
      "epoch": 0.07802197802197802,
      "grad_norm": 4.425159454345703,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9208,
      "step": 142
    },
    {
      "epoch": 0.07857142857142857,
      "grad_norm": 3.966238498687744,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8659,
      "step": 143
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 4.205827236175537,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8532,
      "step": 144
    },
    {
      "epoch": 0.07967032967032966,
      "grad_norm": 3.454686403274536,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7116,
      "step": 145
    },
    {
      "epoch": 0.08021978021978023,
      "grad_norm": 3.6158885955810547,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8404,
      "step": 146
    },
    {
      "epoch": 0.08076923076923077,
      "grad_norm": 4.816569805145264,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.0318,
      "step": 147
    },
    {
      "epoch": 0.08131868131868132,
      "grad_norm": 4.617947101593018,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7545,
      "step": 148
    },
    {
      "epoch": 0.08186813186813187,
      "grad_norm": 2.717759132385254,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5016,
      "step": 149
    },
    {
      "epoch": 0.08241758241758242,
      "grad_norm": 3.2810633182525635,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6501,
      "step": 150
    },
    {
      "epoch": 0.08241758241758242,
      "eval_loss": 0.7657567262649536,
      "eval_runtime": 248.2901,
      "eval_samples_per_second": 12.348,
      "eval_steps_per_second": 3.089,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.20339070042112e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}