{
  "best_metric": 0.8697016835212708,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9259259259259259,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 17.74081039428711,
      "learning_rate": 1e-05,
      "loss": 5.119,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "eval_loss": 1.331807017326355,
      "eval_runtime": 2.1622,
      "eval_samples_per_second": 168.348,
      "eval_steps_per_second": 42.087,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 23.15548324584961,
      "learning_rate": 2e-05,
      "loss": 4.727,
      "step": 2
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 15.756132125854492,
      "learning_rate": 3e-05,
      "loss": 5.2004,
      "step": 3
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 13.970314025878906,
      "learning_rate": 4e-05,
      "loss": 5.1443,
      "step": 4
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 11.418460845947266,
      "learning_rate": 5e-05,
      "loss": 4.6862,
      "step": 5
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 13.500983238220215,
      "learning_rate": 6e-05,
      "loss": 4.5296,
      "step": 6
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 10.298851013183594,
      "learning_rate": 7e-05,
      "loss": 4.162,
      "step": 7
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 12.502114295959473,
      "learning_rate": 8e-05,
      "loss": 4.7313,
      "step": 8
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 11.705147743225098,
      "learning_rate": 9e-05,
      "loss": 5.0774,
      "step": 9
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 10.60966968536377,
      "learning_rate": 0.0001,
      "loss": 4.7649,
      "step": 10
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 11.417049407958984,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.2055,
      "step": 11
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 9.979819297790527,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.1655,
      "step": 12
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 8.027524948120117,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.4812,
      "step": 13
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 6.642037391662598,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.5481,
      "step": 14
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 9.205323219299316,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.7546,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 6.705621242523193,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.9111,
      "step": 16
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 8.21707534790039,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.7691,
      "step": 17
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 6.87344217300415,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.5016,
      "step": 18
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 10.386390686035156,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.4626,
      "step": 19
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 9.1941499710083,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.315,
      "step": 20
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 6.828528881072998,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.1537,
      "step": 21
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 7.619173526763916,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.4276,
      "step": 22
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 6.7589945793151855,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.5831,
      "step": 23
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 7.9849853515625,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.3181,
      "step": 24
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 7.721384048461914,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.9834,
      "step": 25
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 5.854971408843994,
      "learning_rate": 9.826044551386744e-05,
      "loss": 4.3789,
      "step": 26
    },
    {
      "epoch": 0.125,
      "grad_norm": 5.308259010314941,
      "learning_rate": 9.803768380684242e-05,
      "loss": 3.2201,
      "step": 27
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 6.00566291809082,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.22,
      "step": 28
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 5.686971664428711,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.2483,
      "step": 29
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 5.476276397705078,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.8673,
      "step": 30
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 5.782281875610352,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.3838,
      "step": 31
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 5.124298095703125,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.1857,
      "step": 32
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 5.693724155426025,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.1698,
      "step": 33
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 6.285175800323486,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.0791,
      "step": 34
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 5.812838077545166,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.7828,
      "step": 35
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 7.24544620513916,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.5609,
      "step": 36
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 5.708943843841553,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.6163,
      "step": 37
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 6.451725482940674,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.6425,
      "step": 38
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 6.084145545959473,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.5273,
      "step": 39
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 5.903794765472412,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.8484,
      "step": 40
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 5.36998176574707,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.3448,
      "step": 41
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 6.571059703826904,
      "learning_rate": 9.316282404787871e-05,
      "loss": 4.5493,
      "step": 42
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 5.513370990753174,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.7242,
      "step": 43
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 6.563080310821533,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.5587,
      "step": 44
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 5.405109405517578,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.8323,
      "step": 45
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 5.890458106994629,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.5465,
      "step": 46
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 6.1262969970703125,
      "learning_rate": 9.093124073433463e-05,
      "loss": 4.0511,
      "step": 47
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 5.758754730224609,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.4197,
      "step": 48
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 4.904814720153809,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.6871,
      "step": 49
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 6.714904308319092,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.6617,
      "step": 50
    },
    {
      "epoch": 0.23148148148148148,
      "eval_loss": 0.9702958464622498,
      "eval_runtime": 2.1687,
      "eval_samples_per_second": 167.844,
      "eval_steps_per_second": 41.961,
      "step": 50
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 20.221776962280273,
      "learning_rate": 8.894386393810563e-05,
      "loss": 4.2732,
      "step": 51
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 16.344329833984375,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.9804,
      "step": 52
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 6.809448719024658,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.487,
      "step": 53
    },
    {
      "epoch": 0.25,
      "grad_norm": 6.327234745025635,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.7712,
      "step": 54
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 6.9847893714904785,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.4735,
      "step": 55
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 8.009485244750977,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.9744,
      "step": 56
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 6.824001789093018,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.5011,
      "step": 57
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 5.762353420257568,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.4073,
      "step": 58
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 5.401088714599609,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.8418,
      "step": 59
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 5.030090808868408,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.9488,
      "step": 60
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 5.913733005523682,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.826,
      "step": 61
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 6.456943988800049,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.4096,
      "step": 62
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 5.376137733459473,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.3528,
      "step": 63
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 5.072855472564697,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.7979,
      "step": 64
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 5.128457546234131,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.7199,
      "step": 65
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 6.406092643737793,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.694,
      "step": 66
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 6.283804893493652,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.9685,
      "step": 67
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 5.726156711578369,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.2076,
      "step": 68
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 5.308560371398926,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.9325,
      "step": 69
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 5.263147354125977,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.6324,
      "step": 70
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 5.057857990264893,
      "learning_rate": 7.66515864363997e-05,
      "loss": 3.3463,
      "step": 71
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.06999397277832,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.7402,
      "step": 72
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 6.316456317901611,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.5321,
      "step": 73
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 5.1350226402282715,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.4508,
      "step": 74
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 5.298104286193848,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.6093,
      "step": 75
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 5.161414623260498,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.3262,
      "step": 76
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 5.5423760414123535,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.4641,
      "step": 77
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 5.767210960388184,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.4669,
      "step": 78
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 5.003150463104248,
      "learning_rate": 7.083909302476453e-05,
      "loss": 3.8682,
      "step": 79
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 6.046299457550049,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.535,
      "step": 80
    },
    {
      "epoch": 0.375,
      "grad_norm": 5.120626926422119,
      "learning_rate": 6.932495846462261e-05,
      "loss": 3.7726,
      "step": 81
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 5.308913230895996,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.3077,
      "step": 82
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 5.3037190437316895,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.7274,
      "step": 83
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 6.450857162475586,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.0835,
      "step": 84
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 5.488162040710449,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.4219,
      "step": 85
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 6.159575462341309,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.5361,
      "step": 86
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 5.267491817474365,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.3553,
      "step": 87
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 5.131758689880371,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.5911,
      "step": 88
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 5.814986705780029,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.3552,
      "step": 89
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 5.31785774230957,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.6088,
      "step": 90
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 6.320995807647705,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.9202,
      "step": 91
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 4.3204121589660645,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.8025,
      "step": 92
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 5.522643089294434,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.3761,
      "step": 93
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 5.45990514755249,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.4183,
      "step": 94
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 5.297749042510986,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.5136,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 6.1016974449157715,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.8129,
      "step": 96
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 4.9432373046875,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.7191,
      "step": 97
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 5.719691753387451,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.4068,
      "step": 98
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 7.548406600952148,
      "learning_rate": 5.495227651252315e-05,
      "loss": 4.0513,
      "step": 99
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 7.3912787437438965,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.4147,
      "step": 100
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 0.9646923542022705,
      "eval_runtime": 2.1703,
      "eval_samples_per_second": 167.72,
      "eval_steps_per_second": 41.93,
      "step": 100
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 18.450489044189453,
      "learning_rate": 5.330452921628497e-05,
      "loss": 4.2183,
      "step": 101
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 17.376441955566406,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.6943,
      "step": 102
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 14.51460075378418,
      "learning_rate": 5.165316846586541e-05,
      "loss": 4.121,
      "step": 103
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 10.328911781311035,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 4.3782,
      "step": 104
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 8.784762382507324,
      "learning_rate": 5e-05,
      "loss": 4.5478,
      "step": 105
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 8.304478645324707,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.2826,
      "step": 106
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 5.987887382507324,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.3061,
      "step": 107
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.221620082855225,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.9905,
      "step": 108
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 7.557285785675049,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.7794,
      "step": 109
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 6.457733631134033,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.9203,
      "step": 110
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 7.666470527648926,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.9129,
      "step": 111
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 5.721335411071777,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.2919,
      "step": 112
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 7.203523635864258,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.783,
      "step": 113
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 5.980920791625977,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.652,
      "step": 114
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 6.08820915222168,
      "learning_rate": 4.17702704859633e-05,
      "loss": 4.0208,
      "step": 115
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 5.037003993988037,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.715,
      "step": 116
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 5.541400909423828,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.4085,
      "step": 117
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 5.038794040679932,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.931,
      "step": 118
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 5.460513591766357,
      "learning_rate": 3.852880399766243e-05,
      "loss": 3.6238,
      "step": 119
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 5.334316253662109,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.5903,
      "step": 120
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 5.919313907623291,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.8601,
      "step": 121
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 5.2587199211120605,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.9171,
      "step": 122
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 5.094286918640137,
      "learning_rate": 3.533749813077677e-05,
      "loss": 3.641,
      "step": 123
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 4.917911052703857,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.4377,
      "step": 124
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 5.048930644989014,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.6676,
      "step": 125
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 5.701276779174805,
      "learning_rate": 3.298534127791785e-05,
      "loss": 4.1437,
      "step": 126
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 5.184892654418945,
      "learning_rate": 3.221030765387417e-05,
      "loss": 3.6208,
      "step": 127
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 4.330986976623535,
      "learning_rate": 3.144013755408895e-05,
      "loss": 3.217,
      "step": 128
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 4.709600925445557,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 3.2861,
      "step": 129
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 4.892893314361572,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.3637,
      "step": 130
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 5.514613151550293,
      "learning_rate": 2.916090697523549e-05,
      "loss": 3.4668,
      "step": 131
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 5.297546863555908,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.1875,
      "step": 132
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 4.126865386962891,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.2023,
      "step": 133
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 6.193218231201172,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.7733,
      "step": 134
    },
    {
      "epoch": 0.625,
      "grad_norm": 4.718311786651611,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.3158,
      "step": 135
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 5.396933555603027,
      "learning_rate": 2.547882480847461e-05,
      "loss": 3.9144,
      "step": 136
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 6.254210948944092,
      "learning_rate": 2.476172311325783e-05,
      "loss": 3.2999,
      "step": 137
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 4.480340003967285,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.9775,
      "step": 138
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 7.0759196281433105,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 4.1188,
      "step": 139
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 4.7826361656188965,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.9519,
      "step": 140
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 5.8113532066345215,
      "learning_rate": 2.196424713241637e-05,
      "loss": 4.2316,
      "step": 141
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 4.667482852935791,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.0943,
      "step": 142
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 4.8316264152526855,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.7233,
      "step": 143
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 5.5991621017456055,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.5901,
      "step": 144
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 5.402121543884277,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.5171,
      "step": 145
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 5.180799961090088,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.5333,
      "step": 146
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 5.5413947105407715,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.9408,
      "step": 147
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 5.534701347351074,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.961,
      "step": 148
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 5.425957202911377,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.9605,
      "step": 149
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 6.874478816986084,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.9809,
      "step": 150
    },
    {
      "epoch": 0.6944444444444444,
      "eval_loss": 0.9585354924201965,
      "eval_runtime": 2.1522,
      "eval_samples_per_second": 169.129,
      "eval_steps_per_second": 42.282,
      "step": 150
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 12.832749366760254,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.7949,
      "step": 151
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 13.965093612670898,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.3499,
      "step": 152
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 15.061342239379883,
      "learning_rate": 1.435357758543015e-05,
      "loss": 3.7575,
      "step": 153
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 16.196308135986328,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 3.8578,
      "step": 154
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 21.1320858001709,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.777,
      "step": 155
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 19.516660690307617,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 4.0046,
      "step": 156
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 24.361995697021484,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.1469,
      "step": 157
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 23.684062957763672,
      "learning_rate": 1.157994445715706e-05,
      "loss": 4.408,
      "step": 158
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 21.370405197143555,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 4.4792,
      "step": 159
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 16.428136825561523,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 4.2565,
      "step": 160
    },
    {
      "epoch": 0.7453703703703703,
      "grad_norm": 17.35951042175293,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 3.7254,
      "step": 161
    },
    {
      "epoch": 0.75,
      "grad_norm": 14.073481559753418,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.777,
      "step": 162
    },
    {
      "epoch": 0.7546296296296297,
      "grad_norm": 10.28995418548584,
      "learning_rate": 9.068759265665384e-06,
      "loss": 3.5491,
      "step": 163
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 9.316683769226074,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.7196,
      "step": 164
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 8.205052375793457,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.4147,
      "step": 165
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 7.976834297180176,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.9481,
      "step": 166
    },
    {
      "epoch": 0.7731481481481481,
      "grad_norm": 6.665153980255127,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.4377,
      "step": 167
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 5.826473712921143,
      "learning_rate": 6.837175952121306e-06,
      "loss": 4.0598,
      "step": 168
    },
    {
      "epoch": 0.7824074074074074,
      "grad_norm": 5.745697498321533,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.7762,
      "step": 169
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 4.820688247680664,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.2407,
      "step": 170
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 5.060487747192383,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.2788,
      "step": 171
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 6.067325115203857,
      "learning_rate": 5.263533508961827e-06,
      "loss": 4.092,
      "step": 172
    },
    {
      "epoch": 0.8009259259259259,
      "grad_norm": 5.4149346351623535,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.2632,
      "step": 173
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 5.965126991271973,
      "learning_rate": 4.549673247541875e-06,
      "loss": 3.388,
      "step": 174
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 5.540269374847412,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.8504,
      "step": 175
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 6.351028919219971,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.9714,
      "step": 176
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 6.072516441345215,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.6493,
      "step": 177
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 6.93353796005249,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.7549,
      "step": 178
    },
    {
      "epoch": 0.8287037037037037,
      "grad_norm": 6.242271900177002,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 3.5361,
      "step": 179
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 5.817343711853027,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.1307,
      "step": 180
    },
    {
      "epoch": 0.8379629629629629,
      "grad_norm": 6.139359474182129,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.0001,
      "step": 181
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 6.002723217010498,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 3.2015,
      "step": 182
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 6.321844577789307,
      "learning_rate": 1.962316193157593e-06,
      "loss": 3.3331,
      "step": 183
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 6.900054931640625,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 3.8878,
      "step": 184
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 5.622521877288818,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.2468,
      "step": 185
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 6.7337727546691895,
      "learning_rate": 1.333670137599713e-06,
      "loss": 3.4629,
      "step": 186
    },
    {
      "epoch": 0.8657407407407407,
      "grad_norm": 8.05529499053955,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 3.4291,
      "step": 187
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 7.836898326873779,
      "learning_rate": 9.810017062595322e-07,
      "loss": 3.2885,
      "step": 188
    },
    {
      "epoch": 0.875,
      "grad_norm": 9.317109107971191,
      "learning_rate": 8.247462563808817e-07,
      "loss": 4.3713,
      "step": 189
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 7.2047505378723145,
      "learning_rate": 6.819348298638839e-07,
      "loss": 4.0013,
      "step": 190
    },
    {
      "epoch": 0.8842592592592593,
      "grad_norm": 7.929425239562988,
      "learning_rate": 5.526064699265753e-07,
      "loss": 3.5308,
      "step": 191
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.0645623207092285,
      "learning_rate": 4.367965336512403e-07,
      "loss": 3.2958,
      "step": 192
    },
    {
      "epoch": 0.8935185185185185,
      "grad_norm": 6.917335033416748,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 3.2794,
      "step": 193
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 8.151914596557617,
      "learning_rate": 2.458548727494292e-07,
      "loss": 3.7163,
      "step": 194
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 7.046786308288574,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.0356,
      "step": 195
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 7.417269229888916,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 3.2312,
      "step": 196
    },
    {
      "epoch": 0.9120370370370371,
      "grad_norm": 8.883611679077148,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.3584,
      "step": 197
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 8.838685989379883,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.1816,
      "step": 198
    },
    {
      "epoch": 0.9212962962962963,
      "grad_norm": 8.655529022216797,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.2133,
      "step": 199
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 9.378191947937012,
      "learning_rate": 0.0,
      "loss": 3.469,
      "step": 200
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 0.8697016835212708,
      "eval_runtime": 2.1499,
      "eval_samples_per_second": 169.313,
      "eval_steps_per_second": 42.328,
      "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": 3762008830771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}