{
  "best_metric": 3.4017176628112793,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.2698412698412698,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006349206349206349,
      "grad_norm": 1.7919834852218628,
      "learning_rate": 1e-05,
      "loss": 5.3818,
      "step": 1
    },
    {
      "epoch": 0.006349206349206349,
      "eval_loss": 5.688002109527588,
      "eval_runtime": 7.8261,
      "eval_samples_per_second": 33.861,
      "eval_steps_per_second": 8.561,
      "step": 1
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 2.3243520259857178,
      "learning_rate": 2e-05,
      "loss": 5.1935,
      "step": 2
    },
    {
      "epoch": 0.01904761904761905,
      "grad_norm": 1.7293851375579834,
      "learning_rate": 3e-05,
      "loss": 5.3752,
      "step": 3
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 1.892749309539795,
      "learning_rate": 4e-05,
      "loss": 5.258,
      "step": 4
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 1.4529306888580322,
      "learning_rate": 5e-05,
      "loss": 5.1409,
      "step": 5
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 1.6089597940444946,
      "learning_rate": 6e-05,
      "loss": 4.9303,
      "step": 6
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 1.647459864616394,
      "learning_rate": 7e-05,
      "loss": 4.9812,
      "step": 7
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 1.8854882717132568,
      "learning_rate": 8e-05,
      "loss": 5.1854,
      "step": 8
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.7198046445846558,
      "learning_rate": 9e-05,
      "loss": 4.7285,
      "step": 9
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 1.4365547895431519,
      "learning_rate": 0.0001,
      "loss": 5.052,
      "step": 10
    },
    {
      "epoch": 0.06984126984126984,
      "grad_norm": 1.6025629043579102,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.9475,
      "step": 11
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 1.580459713935852,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.9652,
      "step": 12
    },
    {
      "epoch": 0.08253968253968254,
      "grad_norm": 1.8582038879394531,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.6879,
      "step": 13
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.709199070930481,
      "learning_rate": 9.989068136093873e-05,
      "loss": 4.666,
      "step": 14
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.7610552310943604,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.4958,
      "step": 15
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 1.8142030239105225,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.2276,
      "step": 16
    },
    {
      "epoch": 0.10793650793650794,
      "grad_norm": 1.7192691564559937,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.518,
      "step": 17
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.9730079174041748,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.7658,
      "step": 18
    },
    {
      "epoch": 0.12063492063492064,
      "grad_norm": 1.840072751045227,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.4969,
      "step": 19
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 1.9680761098861694,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.9381,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.8718513250350952,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.5613,
      "step": 21
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 1.9406774044036865,
      "learning_rate": 9.901899829374047e-05,
      "loss": 4.6827,
      "step": 22
    },
    {
      "epoch": 0.14603174603174604,
      "grad_norm": 2.5079128742218018,
      "learning_rate": 9.884934153917997e-05,
      "loss": 4.3751,
      "step": 23
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 2.035618782043457,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.323,
      "step": 24
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 2.187474012374878,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.3775,
      "step": 25
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 2.557244300842285,
      "learning_rate": 9.826044551386744e-05,
      "loss": 4.3582,
      "step": 26
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 2.5607242584228516,
      "learning_rate": 9.803768380684242e-05,
      "loss": 4.1807,
      "step": 27
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.60034441947937,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.9065,
      "step": 28
    },
    {
      "epoch": 0.18412698412698414,
      "grad_norm": 2.400935173034668,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.4766,
      "step": 29
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 2.6716721057891846,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.8368,
      "step": 30
    },
    {
      "epoch": 0.19682539682539682,
      "grad_norm": 2.482222557067871,
      "learning_rate": 9.701596950580806e-05,
      "loss": 4.0824,
      "step": 31
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 2.7512052059173584,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.2137,
      "step": 32
    },
    {
      "epoch": 0.20952380952380953,
      "grad_norm": 2.8800597190856934,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.406,
      "step": 33
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 2.7007155418395996,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.5288,
      "step": 34
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.7668044567108154,
      "learning_rate": 9.578866633275288e-05,
      "loss": 4.1576,
      "step": 35
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 2.8741283416748047,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.0879,
      "step": 36
    },
    {
      "epoch": 0.23492063492063492,
      "grad_norm": 3.126038074493408,
      "learning_rate": 9.509956150664796e-05,
      "loss": 4.1275,
      "step": 37
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 3.3396215438842773,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.2784,
      "step": 38
    },
    {
      "epoch": 0.24761904761904763,
      "grad_norm": 4.369854927062988,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.9094,
      "step": 39
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 6.114046096801758,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.4702,
      "step": 40
    },
    {
      "epoch": 0.26031746031746034,
      "grad_norm": 4.710829734802246,
      "learning_rate": 9.357421218136386e-05,
      "loss": 4.1158,
      "step": 41
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.3691647052764893,
      "learning_rate": 9.316282404787871e-05,
      "loss": 4.2324,
      "step": 42
    },
    {
      "epoch": 0.273015873015873,
      "grad_norm": 1.985754132270813,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.8591,
      "step": 43
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 2.0531723499298096,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.9863,
      "step": 44
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.013728380203247,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.96,
      "step": 45
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 1.8266619443893433,
      "learning_rate": 9.140044155740101e-05,
      "loss": 4.162,
      "step": 46
    },
    {
      "epoch": 0.2984126984126984,
      "grad_norm": 1.7123140096664429,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.9605,
      "step": 47
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 2.1586239337921143,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.0417,
      "step": 48
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 1.9310438632965088,
      "learning_rate": 8.995939984474624e-05,
      "loss": 4.2267,
      "step": 49
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 1.7846651077270508,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.1087,
      "step": 50
    },
    {
      "epoch": 0.31746031746031744,
      "eval_loss": 3.976325750350952,
      "eval_runtime": 7.9678,
      "eval_samples_per_second": 33.259,
      "eval_steps_per_second": 8.409,
      "step": 50
    },
    {
      "epoch": 0.3238095238095238,
      "grad_norm": 1.7934757471084595,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.8398,
      "step": 51
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 1.7427952289581299,
      "learning_rate": 8.842005554284296e-05,
      "loss": 4.0476,
      "step": 52
    },
    {
      "epoch": 0.33650793650793653,
      "grad_norm": 2.0100913047790527,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.6321,
      "step": 53
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 2.344943046569824,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.8021,
      "step": 54
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 2.22444486618042,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.8569,
      "step": 55
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.1766538619995117,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.7399,
      "step": 56
    },
    {
      "epoch": 0.3619047619047619,
      "grad_norm": 2.0689213275909424,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.9971,
      "step": 57
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 2.498577117919922,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.9594,
      "step": 58
    },
    {
      "epoch": 0.3746031746031746,
      "grad_norm": 2.4442622661590576,
      "learning_rate": 8.44676704559283e-05,
      "loss": 4.0931,
      "step": 59
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.532228708267212,
      "learning_rate": 8.386407858128706e-05,
      "loss": 4.1003,
      "step": 60
    },
    {
      "epoch": 0.3873015873015873,
      "grad_norm": 2.3149659633636475,
      "learning_rate": 8.32512286056924e-05,
      "loss": 4.0305,
      "step": 61
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 2.2412238121032715,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.7559,
      "step": 62
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.372811794281006,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.734,
      "step": 63
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 2.4451539516448975,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.8719,
      "step": 64
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 2.7070627212524414,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.5613,
      "step": 65
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 2.7895255088806152,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.6789,
      "step": 66
    },
    {
      "epoch": 0.4253968253968254,
      "grad_norm": 2.761310338973999,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.9482,
      "step": 67
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 2.758392572402954,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.7602,
      "step": 68
    },
    {
      "epoch": 0.4380952380952381,
      "grad_norm": 2.938023090362549,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.6936,
      "step": 69
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 3.033060073852539,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.8681,
      "step": 70
    },
    {
      "epoch": 0.4507936507936508,
      "grad_norm": 3.1546061038970947,
      "learning_rate": 7.66515864363997e-05,
      "loss": 4.2255,
      "step": 71
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 3.3231239318847656,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.8653,
      "step": 72
    },
    {
      "epoch": 0.4634920634920635,
      "grad_norm": 3.731671094894409,
      "learning_rate": 7.52382768867422e-05,
      "loss": 4.0477,
      "step": 73
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 3.3442776203155518,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.9793,
      "step": 74
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.3896231651306152,
      "learning_rate": 7.379736965185368e-05,
      "loss": 4.0051,
      "step": 75
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 3.6277081966400146,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.8725,
      "step": 76
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 4.139486312866211,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.2459,
      "step": 77
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 4.231446743011475,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.7537,
      "step": 78
    },
    {
      "epoch": 0.5015873015873016,
      "grad_norm": 3.5066752433776855,
      "learning_rate": 7.083909302476453e-05,
      "loss": 4.1826,
      "step": 79
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.8957114219665527,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.9119,
      "step": 80
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 2.527146100997925,
      "learning_rate": 6.932495846462261e-05,
      "loss": 3.9333,
      "step": 81
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 2.5329716205596924,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.9025,
      "step": 82
    },
    {
      "epoch": 0.526984126984127,
      "grad_norm": 1.893083095550537,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.7094,
      "step": 83
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.9646106958389282,
      "learning_rate": 6.701465872208216e-05,
      "loss": 3.6633,
      "step": 84
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 1.7728943824768066,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.6633,
      "step": 85
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 1.7009302377700806,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.6011,
      "step": 86
    },
    {
      "epoch": 0.5523809523809524,
      "grad_norm": 2.0099103450775146,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.6168,
      "step": 87
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 2.1076881885528564,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.5595,
      "step": 88
    },
    {
      "epoch": 0.5650793650793651,
      "grad_norm": 2.1192877292633057,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.8202,
      "step": 89
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.256744384765625,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.8226,
      "step": 90
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 2.30214786529541,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.838,
      "step": 91
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 2.2971243858337402,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.8784,
      "step": 92
    },
    {
      "epoch": 0.5904761904761905,
      "grad_norm": 2.1242175102233887,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.153,
      "step": 93
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 2.224844217300415,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.563,
      "step": 94
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 2.2347781658172607,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.6691,
      "step": 95
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 2.467785120010376,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.8529,
      "step": 96
    },
    {
      "epoch": 0.6158730158730159,
      "grad_norm": 2.4363174438476562,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.7741,
      "step": 97
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.422653913497925,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.9519,
      "step": 98
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 2.3823914527893066,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.7048,
      "step": 99
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 2.531588077545166,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.8295,
      "step": 100
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 3.596803665161133,
      "eval_runtime": 7.8368,
      "eval_samples_per_second": 33.815,
      "eval_steps_per_second": 8.549,
      "step": 100
    },
    {
      "epoch": 0.6412698412698413,
      "grad_norm": 2.485680341720581,
      "learning_rate": 5.330452921628497e-05,
      "loss": 3.6703,
      "step": 101
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 2.5790393352508545,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.4628,
      "step": 102
    },
    {
      "epoch": 0.653968253968254,
      "grad_norm": 2.5979650020599365,
      "learning_rate": 5.165316846586541e-05,
      "loss": 3.6254,
      "step": 103
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 2.791707754135132,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 3.9911,
      "step": 104
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.891598701477051,
      "learning_rate": 5e-05,
      "loss": 3.67,
      "step": 105
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 3.37996244430542,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.6864,
      "step": 106
    },
    {
      "epoch": 0.6793650793650794,
      "grad_norm": 3.093928813934326,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.4836,
      "step": 107
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 3.0105931758880615,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.7234,
      "step": 108
    },
    {
      "epoch": 0.692063492063492,
      "grad_norm": 3.0275254249572754,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.3812,
      "step": 109
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 3.345993757247925,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.5929,
      "step": 110
    },
    {
      "epoch": 0.7047619047619048,
      "grad_norm": 3.6041181087493896,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.8898,
      "step": 111
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 3.606980323791504,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.6729,
      "step": 112
    },
    {
      "epoch": 0.7174603174603175,
      "grad_norm": 3.904892921447754,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.4376,
      "step": 113
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 3.9271838665008545,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.798,
      "step": 114
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 4.634347438812256,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.5947,
      "step": 115
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 4.055920600891113,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.3834,
      "step": 116
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 5.504981994628906,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.587,
      "step": 117
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 2.268176794052124,
      "learning_rate": 3.933501846281267e-05,
      "loss": 3.741,
      "step": 118
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.2775723934173584,
      "learning_rate": 3.852880399766243e-05,
      "loss": 3.7643,
      "step": 119
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.3815295696258545,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.6489,
      "step": 120
    },
    {
      "epoch": 0.7682539682539683,
      "grad_norm": 1.9776639938354492,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.7522,
      "step": 121
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 1.9130133390426636,
      "learning_rate": 3.612985456190778e-05,
      "loss": 3.8116,
      "step": 122
    },
    {
      "epoch": 0.780952380952381,
      "grad_norm": 1.9774221181869507,
      "learning_rate": 3.533749813077677e-05,
      "loss": 3.4564,
      "step": 123
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 2.0334343910217285,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.5085,
      "step": 124
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 2.2311933040618896,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.4223,
      "step": 125
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.2889347076416016,
      "learning_rate": 3.298534127791785e-05,
      "loss": 3.4384,
      "step": 126
    },
    {
      "epoch": 0.8063492063492064,
      "grad_norm": 2.1580703258514404,
      "learning_rate": 3.221030765387417e-05,
      "loss": 3.7176,
      "step": 127
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 2.447000741958618,
      "learning_rate": 3.144013755408895e-05,
      "loss": 3.6256,
      "step": 128
    },
    {
      "epoch": 0.819047619047619,
      "grad_norm": 2.2722136974334717,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 3.5514,
      "step": 129
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 2.456970691680908,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.5435,
      "step": 130
    },
    {
      "epoch": 0.8317460317460318,
      "grad_norm": 2.243635654449463,
      "learning_rate": 2.916090697523549e-05,
      "loss": 3.5228,
      "step": 131
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 2.376413106918335,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.3049,
      "step": 132
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 2.4247326850891113,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.7036,
      "step": 133
    },
    {
      "epoch": 0.8507936507936508,
      "grad_norm": 2.2563536167144775,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.1924,
      "step": 134
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.4976725578308105,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.3018,
      "step": 135
    },
    {
      "epoch": 0.8634920634920635,
      "grad_norm": 2.6335246562957764,
      "learning_rate": 2.547882480847461e-05,
      "loss": 3.4697,
      "step": 136
    },
    {
      "epoch": 0.8698412698412699,
      "grad_norm": 2.7315828800201416,
      "learning_rate": 2.476172311325783e-05,
      "loss": 3.2125,
      "step": 137
    },
    {
      "epoch": 0.8761904761904762,
      "grad_norm": 2.9368021488189697,
      "learning_rate": 2.405152131093926e-05,
      "loss": 3.5936,
      "step": 138
    },
    {
      "epoch": 0.8825396825396825,
      "grad_norm": 2.6744894981384277,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 3.5129,
      "step": 139
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.7112088203430176,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.3262,
      "step": 140
    },
    {
      "epoch": 0.8952380952380953,
      "grad_norm": 2.641974925994873,
      "learning_rate": 2.196424713241637e-05,
      "loss": 3.2787,
      "step": 141
    },
    {
      "epoch": 0.9015873015873016,
      "grad_norm": 2.668889045715332,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.917,
      "step": 142
    },
    {
      "epoch": 0.9079365079365079,
      "grad_norm": 2.9755706787109375,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.456,
      "step": 143
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 2.917559862136841,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.3205,
      "step": 144
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 3.132016897201538,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.8338,
      "step": 145
    },
    {
      "epoch": 0.926984126984127,
      "grad_norm": 3.0399343967437744,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.5204,
      "step": 146
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 3.2588672637939453,
      "learning_rate": 1.800157297483417e-05,
      "loss": 3.6792,
      "step": 147
    },
    {
      "epoch": 0.9396825396825397,
      "grad_norm": 3.2456412315368652,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 3.826,
      "step": 148
    },
    {
      "epoch": 0.946031746031746,
      "grad_norm": 3.3431389331817627,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 3.5614,
      "step": 149
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 3.5043041706085205,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.7408,
      "step": 150
    },
    {
      "epoch": 0.9523809523809523,
      "eval_loss": 3.429945468902588,
      "eval_runtime": 7.8373,
      "eval_samples_per_second": 33.813,
      "eval_steps_per_second": 8.549,
      "step": 150
    },
    {
      "epoch": 0.9587301587301588,
      "grad_norm": 3.992246150970459,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.7248,
      "step": 151
    },
    {
      "epoch": 0.9650793650793651,
      "grad_norm": 4.156944274902344,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.6745,
      "step": 152
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 3.944906234741211,
      "learning_rate": 1.435357758543015e-05,
      "loss": 3.5398,
      "step": 153
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 4.224757671356201,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 3.3527,
      "step": 154
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 4.584436893463135,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.4942,
      "step": 155
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 4.649446964263916,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.8346,
      "step": 156
    },
    {
      "epoch": 0.9968253968253968,
      "grad_norm": 2.168961763381958,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 3.4173,
      "step": 157
    },
    {
      "epoch": 1.0031746031746032,
      "grad_norm": 6.067371845245361,
      "learning_rate": 1.157994445715706e-05,
      "loss": 5.6579,
      "step": 158
    },
    {
      "epoch": 1.0095238095238095,
      "grad_norm": 1.7930011749267578,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 3.3162,
      "step": 159
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 1.9318212270736694,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.2391,
      "step": 160
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 1.849679708480835,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 3.4187,
      "step": 161
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 1.8898353576660156,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.3368,
      "step": 162
    },
    {
      "epoch": 1.034920634920635,
      "grad_norm": 1.8551974296569824,
      "learning_rate": 9.068759265665384e-06,
      "loss": 3.2576,
      "step": 163
    },
    {
      "epoch": 1.0412698412698413,
      "grad_norm": 1.9199113845825195,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.1357,
      "step": 164
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 2.1685104370117188,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.4626,
      "step": 165
    },
    {
      "epoch": 1.053968253968254,
      "grad_norm": 2.0551602840423584,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.0889,
      "step": 166
    },
    {
      "epoch": 1.0603174603174603,
      "grad_norm": 2.069248914718628,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.0122,
      "step": 167
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 2.0197272300720215,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.9759,
      "step": 168
    },
    {
      "epoch": 1.073015873015873,
      "grad_norm": 2.132718324661255,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.3946,
      "step": 169
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 2.1848578453063965,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.9215,
      "step": 170
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 2.2243034839630127,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.0126,
      "step": 171
    },
    {
      "epoch": 1.0920634920634922,
      "grad_norm": 2.3244950771331787,
      "learning_rate": 5.263533508961827e-06,
      "loss": 2.9098,
      "step": 172
    },
    {
      "epoch": 1.0984126984126985,
      "grad_norm": 2.3358757495880127,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.3265,
      "step": 173
    },
    {
      "epoch": 1.1047619047619048,
      "grad_norm": 2.351515769958496,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.7997,
      "step": 174
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 2.610258102416992,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.2258,
      "step": 175
    },
    {
      "epoch": 1.1174603174603175,
      "grad_norm": 2.4132823944091797,
      "learning_rate": 3.885512251130763e-06,
      "loss": 3.2962,
      "step": 176
    },
    {
      "epoch": 1.1238095238095238,
      "grad_norm": 2.4606800079345703,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.2457,
      "step": 177
    },
    {
      "epoch": 1.1301587301587301,
      "grad_norm": 2.5596439838409424,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.3477,
      "step": 178
    },
    {
      "epoch": 1.1365079365079365,
      "grad_norm": 2.730008125305176,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 3.5382,
      "step": 179
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.7552294731140137,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.2392,
      "step": 180
    },
    {
      "epoch": 1.1492063492063491,
      "grad_norm": 2.6675021648406982,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.0333,
      "step": 181
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 2.7317609786987305,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.7124,
      "step": 182
    },
    {
      "epoch": 1.161904761904762,
      "grad_norm": 2.805018186569214,
      "learning_rate": 1.962316193157593e-06,
      "loss": 3.0156,
      "step": 183
    },
    {
      "epoch": 1.1682539682539683,
      "grad_norm": 2.9215996265411377,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 3.1559,
      "step": 184
    },
    {
      "epoch": 1.1746031746031746,
      "grad_norm": 2.9618685245513916,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.2151,
      "step": 185
    },
    {
      "epoch": 1.180952380952381,
      "grad_norm": 3.2099640369415283,
      "learning_rate": 1.333670137599713e-06,
      "loss": 3.1224,
      "step": 186
    },
    {
      "epoch": 1.1873015873015873,
      "grad_norm": 3.08341908454895,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 3.2178,
      "step": 187
    },
    {
      "epoch": 1.1936507936507936,
      "grad_norm": 3.145102024078369,
      "learning_rate": 9.810017062595322e-07,
      "loss": 3.005,
      "step": 188
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.336474657058716,
      "learning_rate": 8.247462563808817e-07,
      "loss": 3.3198,
      "step": 189
    },
    {
      "epoch": 1.2063492063492063,
      "grad_norm": 3.524651050567627,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.2201,
      "step": 190
    },
    {
      "epoch": 1.2126984126984126,
      "grad_norm": 3.4539432525634766,
      "learning_rate": 5.526064699265753e-07,
      "loss": 3.1732,
      "step": 191
    },
    {
      "epoch": 1.2190476190476192,
      "grad_norm": 3.5301644802093506,
      "learning_rate": 4.367965336512403e-07,
      "loss": 3.2683,
      "step": 192
    },
    {
      "epoch": 1.2253968253968255,
      "grad_norm": 3.9130232334136963,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 3.3309,
      "step": 193
    },
    {
      "epoch": 1.2317460317460318,
      "grad_norm": 3.7009236812591553,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.949,
      "step": 194
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 4.472840785980225,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.7686,
      "step": 195
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 4.348317623138428,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 3.072,
      "step": 196
    },
    {
      "epoch": 1.2507936507936508,
      "grad_norm": 3.510545492172241,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.2371,
      "step": 197
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 1.8828840255737305,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.219,
      "step": 198
    },
    {
      "epoch": 1.2634920634920634,
      "grad_norm": 1.7613160610198975,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.3699,
      "step": 199
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 1.8520058393478394,
      "learning_rate": 0.0,
      "loss": 3.4738,
      "step": 200
    },
    {
      "epoch": 1.2698412698412698,
      "eval_loss": 3.4017176628112793,
      "eval_runtime": 7.8371,
      "eval_samples_per_second": 33.813,
      "eval_steps_per_second": 8.549,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.43864235229184e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}