{
  "best_metric": 10.275985717773438,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06749346157091032,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033746730785455157,
      "grad_norm": 0.7895258665084839,
      "learning_rate": 1e-05,
      "loss": 41.5055,
      "step": 1
    },
    {
      "epoch": 0.00033746730785455157,
      "eval_loss": 10.375170707702637,
      "eval_runtime": 10.3481,
      "eval_samples_per_second": 482.309,
      "eval_steps_per_second": 120.601,
      "step": 1
    },
    {
      "epoch": 0.0006749346157091031,
      "grad_norm": 0.8295886516571045,
      "learning_rate": 2e-05,
      "loss": 41.5025,
      "step": 2
    },
    {
      "epoch": 0.0010124019235636548,
      "grad_norm": 0.8121634125709534,
      "learning_rate": 3e-05,
      "loss": 41.5075,
      "step": 3
    },
    {
      "epoch": 0.0013498692314182063,
      "grad_norm": 0.7989346385002136,
      "learning_rate": 4e-05,
      "loss": 41.5129,
      "step": 4
    },
    {
      "epoch": 0.001687336539272758,
      "grad_norm": 0.8402585387229919,
      "learning_rate": 5e-05,
      "loss": 41.5119,
      "step": 5
    },
    {
      "epoch": 0.0020248038471273096,
      "grad_norm": 0.859088659286499,
      "learning_rate": 6e-05,
      "loss": 41.4938,
      "step": 6
    },
    {
      "epoch": 0.002362271154981861,
      "grad_norm": 0.9027012586593628,
      "learning_rate": 7e-05,
      "loss": 41.4977,
      "step": 7
    },
    {
      "epoch": 0.0026997384628364126,
      "grad_norm": 0.9078822135925293,
      "learning_rate": 8e-05,
      "loss": 41.48,
      "step": 8
    },
    {
      "epoch": 0.0030372057706909645,
      "grad_norm": 1.084112286567688,
      "learning_rate": 9e-05,
      "loss": 41.4797,
      "step": 9
    },
    {
      "epoch": 0.003374673078545516,
      "grad_norm": 1.152192234992981,
      "learning_rate": 0.0001,
      "loss": 41.4732,
      "step": 10
    },
    {
      "epoch": 0.0037121403864000674,
      "grad_norm": 1.108066439628601,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.4686,
      "step": 11
    },
    {
      "epoch": 0.004049607694254619,
      "grad_norm": 1.220452904701233,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4665,
      "step": 12
    },
    {
      "epoch": 0.00438707500210917,
      "grad_norm": 1.4109095335006714,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.4565,
      "step": 13
    },
    {
      "epoch": 0.004724542309963722,
      "grad_norm": 1.4029890298843384,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.4613,
      "step": 14
    },
    {
      "epoch": 0.005062009617818274,
      "grad_norm": 1.4422223567962646,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.4438,
      "step": 15
    },
    {
      "epoch": 0.005399476925672825,
      "grad_norm": 1.79471755027771,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.4268,
      "step": 16
    },
    {
      "epoch": 0.005736944233527377,
      "grad_norm": 1.7171387672424316,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.4313,
      "step": 17
    },
    {
      "epoch": 0.006074411541381929,
      "grad_norm": 1.849963665008545,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.4184,
      "step": 18
    },
    {
      "epoch": 0.00641187884923648,
      "grad_norm": 2.020285129547119,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.4062,
      "step": 19
    },
    {
      "epoch": 0.006749346157091032,
      "grad_norm": 2.0122132301330566,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.3996,
      "step": 20
    },
    {
      "epoch": 0.007086813464945584,
      "grad_norm": 1.931718111038208,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.3647,
      "step": 21
    },
    {
      "epoch": 0.007424280772800135,
      "grad_norm": 2.2387871742248535,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.3692,
      "step": 22
    },
    {
      "epoch": 0.007761748080654687,
      "grad_norm": 2.1095993518829346,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.3691,
      "step": 23
    },
    {
      "epoch": 0.008099215388509239,
      "grad_norm": 2.232914686203003,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.3328,
      "step": 24
    },
    {
      "epoch": 0.00843668269636379,
      "grad_norm": 2.1020853519439697,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.3402,
      "step": 25
    },
    {
      "epoch": 0.00877415000421834,
      "grad_norm": 2.1991894245147705,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.3015,
      "step": 26
    },
    {
      "epoch": 0.009111617312072893,
      "grad_norm": 1.9060027599334717,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.306,
      "step": 27
    },
    {
      "epoch": 0.009449084619927444,
      "grad_norm": 1.9460769891738892,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.2878,
      "step": 28
    },
    {
      "epoch": 0.009786551927781996,
      "grad_norm": 1.9509384632110596,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.2629,
      "step": 29
    },
    {
      "epoch": 0.010124019235636548,
      "grad_norm": 1.80828058719635,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.2705,
      "step": 30
    },
    {
      "epoch": 0.0104614865434911,
      "grad_norm": 1.6633089780807495,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.2545,
      "step": 31
    },
    {
      "epoch": 0.01079895385134565,
      "grad_norm": 1.626420259475708,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.2521,
      "step": 32
    },
    {
      "epoch": 0.011136421159200202,
      "grad_norm": 1.5220023393630981,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.2325,
      "step": 33
    },
    {
      "epoch": 0.011473888467054754,
      "grad_norm": 1.5001860857009888,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.2372,
      "step": 34
    },
    {
      "epoch": 0.011811355774909306,
      "grad_norm": 1.377228021621704,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.2318,
      "step": 35
    },
    {
      "epoch": 0.012148823082763858,
      "grad_norm": 1.2579922676086426,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.2098,
      "step": 36
    },
    {
      "epoch": 0.012486290390618408,
      "grad_norm": 1.1617026329040527,
      "learning_rate": 9.509956150664796e-05,
      "loss": 41.195,
      "step": 37
    },
    {
      "epoch": 0.01282375769847296,
      "grad_norm": 1.1387304067611694,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.2061,
      "step": 38
    },
    {
      "epoch": 0.013161225006327512,
      "grad_norm": 1.2737197875976562,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.2373,
      "step": 39
    },
    {
      "epoch": 0.013498692314182064,
      "grad_norm": 1.3617513179779053,
      "learning_rate": 9.397368756032445e-05,
      "loss": 41.1697,
      "step": 40
    },
    {
      "epoch": 0.013836159622036616,
      "grad_norm": 1.0611796379089355,
      "learning_rate": 9.357421218136386e-05,
      "loss": 41.156,
      "step": 41
    },
    {
      "epoch": 0.014173626929891167,
      "grad_norm": 1.0229917764663696,
      "learning_rate": 9.316282404787871e-05,
      "loss": 41.183,
      "step": 42
    },
    {
      "epoch": 0.014511094237745718,
      "grad_norm": 1.1025137901306152,
      "learning_rate": 9.273963562927695e-05,
      "loss": 41.1809,
      "step": 43
    },
    {
      "epoch": 0.01484856154560027,
      "grad_norm": 0.9812190532684326,
      "learning_rate": 9.230476262104677e-05,
      "loss": 41.1779,
      "step": 44
    },
    {
      "epoch": 0.015186028853454821,
      "grad_norm": 1.2703605890274048,
      "learning_rate": 9.185832391312644e-05,
      "loss": 41.1491,
      "step": 45
    },
    {
      "epoch": 0.015523496161309373,
      "grad_norm": 0.9247879385948181,
      "learning_rate": 9.140044155740101e-05,
      "loss": 41.1521,
      "step": 46
    },
    {
      "epoch": 0.015860963469163925,
      "grad_norm": 1.0905712842941284,
      "learning_rate": 9.093124073433463e-05,
      "loss": 41.0994,
      "step": 47
    },
    {
      "epoch": 0.016198430777018477,
      "grad_norm": 1.372781753540039,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.1446,
      "step": 48
    },
    {
      "epoch": 0.01653589808487303,
      "grad_norm": 1.3849130868911743,
      "learning_rate": 8.995939984474624e-05,
      "loss": 41.1094,
      "step": 49
    },
    {
      "epoch": 0.01687336539272758,
      "grad_norm": 1.7061666250228882,
      "learning_rate": 8.945702546981969e-05,
      "loss": 41.1111,
      "step": 50
    },
    {
      "epoch": 0.01687336539272758,
      "eval_loss": 10.294983863830566,
      "eval_runtime": 10.3411,
      "eval_samples_per_second": 482.639,
      "eval_steps_per_second": 120.684,
      "step": 50
    },
    {
      "epoch": 0.017210832700582133,
      "grad_norm": 0.9282559752464294,
      "learning_rate": 8.894386393810563e-05,
      "loss": 41.2286,
      "step": 51
    },
    {
      "epoch": 0.01754830000843668,
      "grad_norm": 0.8676416873931885,
      "learning_rate": 8.842005554284296e-05,
      "loss": 41.212,
      "step": 52
    },
    {
      "epoch": 0.017885767316291233,
      "grad_norm": 0.7983180284500122,
      "learning_rate": 8.788574348801675e-05,
      "loss": 41.2051,
      "step": 53
    },
    {
      "epoch": 0.018223234624145785,
      "grad_norm": 0.7766379117965698,
      "learning_rate": 8.73410738492077e-05,
      "loss": 41.2212,
      "step": 54
    },
    {
      "epoch": 0.018560701932000337,
      "grad_norm": 0.7279344797134399,
      "learning_rate": 8.678619553365659e-05,
      "loss": 41.2116,
      "step": 55
    },
    {
      "epoch": 0.01889816923985489,
      "grad_norm": 0.8041073679924011,
      "learning_rate": 8.622126023955446e-05,
      "loss": 41.2166,
      "step": 56
    },
    {
      "epoch": 0.01923563654770944,
      "grad_norm": 0.724818766117096,
      "learning_rate": 8.564642241456986e-05,
      "loss": 41.1921,
      "step": 57
    },
    {
      "epoch": 0.019573103855563993,
      "grad_norm": 0.6515514254570007,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.1825,
      "step": 58
    },
    {
      "epoch": 0.019910571163418544,
      "grad_norm": 0.6870782971382141,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.2044,
      "step": 59
    },
    {
      "epoch": 0.020248038471273096,
      "grad_norm": 0.8518241047859192,
      "learning_rate": 8.386407858128706e-05,
      "loss": 41.198,
      "step": 60
    },
    {
      "epoch": 0.02058550577912765,
      "grad_norm": 0.6704785823822021,
      "learning_rate": 8.32512286056924e-05,
      "loss": 41.2015,
      "step": 61
    },
    {
      "epoch": 0.0209229730869822,
      "grad_norm": 0.6663302183151245,
      "learning_rate": 8.262928807620843e-05,
      "loss": 41.1905,
      "step": 62
    },
    {
      "epoch": 0.02126044039483675,
      "grad_norm": 0.6286836266517639,
      "learning_rate": 8.199842702516583e-05,
      "loss": 41.1688,
      "step": 63
    },
    {
      "epoch": 0.0215979077026913,
      "grad_norm": 0.577825665473938,
      "learning_rate": 8.135881792367686e-05,
      "loss": 41.188,
      "step": 64
    },
    {
      "epoch": 0.021935375010545852,
      "grad_norm": 0.6440315246582031,
      "learning_rate": 8.07106356344834e-05,
      "loss": 41.1983,
      "step": 65
    },
    {
      "epoch": 0.022272842318400404,
      "grad_norm": 0.4762708842754364,
      "learning_rate": 8.005405736415126e-05,
      "loss": 41.1535,
      "step": 66
    },
    {
      "epoch": 0.022610309626254956,
      "grad_norm": 0.4513339698314667,
      "learning_rate": 7.938926261462366e-05,
      "loss": 41.1452,
      "step": 67
    },
    {
      "epoch": 0.022947776934109508,
      "grad_norm": 0.4892549514770508,
      "learning_rate": 7.871643313414718e-05,
      "loss": 41.2013,
      "step": 68
    },
    {
      "epoch": 0.02328524424196406,
      "grad_norm": 0.3965024948120117,
      "learning_rate": 7.803575286758364e-05,
      "loss": 41.1865,
      "step": 69
    },
    {
      "epoch": 0.023622711549818612,
      "grad_norm": 0.4913993179798126,
      "learning_rate": 7.734740790612136e-05,
      "loss": 41.1834,
      "step": 70
    },
    {
      "epoch": 0.023960178857673164,
      "grad_norm": 0.5384320616722107,
      "learning_rate": 7.66515864363997e-05,
      "loss": 41.1577,
      "step": 71
    },
    {
      "epoch": 0.024297646165527716,
      "grad_norm": 0.5206311345100403,
      "learning_rate": 7.594847868906076e-05,
      "loss": 41.1674,
      "step": 72
    },
    {
      "epoch": 0.024635113473382268,
      "grad_norm": 0.4966866075992584,
      "learning_rate": 7.52382768867422e-05,
      "loss": 41.1593,
      "step": 73
    },
    {
      "epoch": 0.024972580781236816,
      "grad_norm": 0.3750408887863159,
      "learning_rate": 7.452117519152542e-05,
      "loss": 41.1699,
      "step": 74
    },
    {
      "epoch": 0.025310048089091368,
      "grad_norm": 0.4515850245952606,
      "learning_rate": 7.379736965185368e-05,
      "loss": 41.1687,
      "step": 75
    },
    {
      "epoch": 0.02564751539694592,
      "grad_norm": 0.46759793162345886,
      "learning_rate": 7.30670581489344e-05,
      "loss": 41.1856,
      "step": 76
    },
    {
      "epoch": 0.02598498270480047,
      "grad_norm": 0.4177912175655365,
      "learning_rate": 7.233044034264034e-05,
      "loss": 41.1781,
      "step": 77
    },
    {
      "epoch": 0.026322450012655024,
      "grad_norm": 0.4441013038158417,
      "learning_rate": 7.158771761692464e-05,
      "loss": 41.1735,
      "step": 78
    },
    {
      "epoch": 0.026659917320509575,
      "grad_norm": 0.5250781774520874,
      "learning_rate": 7.083909302476453e-05,
      "loss": 41.1585,
      "step": 79
    },
    {
      "epoch": 0.026997384628364127,
      "grad_norm": 0.5329623818397522,
      "learning_rate": 7.008477123264848e-05,
      "loss": 41.1723,
      "step": 80
    },
    {
      "epoch": 0.02733485193621868,
      "grad_norm": 0.5593544840812683,
      "learning_rate": 6.932495846462261e-05,
      "loss": 41.183,
      "step": 81
    },
    {
      "epoch": 0.02767231924407323,
      "grad_norm": 0.5466566681861877,
      "learning_rate": 6.855986244591104e-05,
      "loss": 41.1486,
      "step": 82
    },
    {
      "epoch": 0.028009786551927783,
      "grad_norm": 0.5816398859024048,
      "learning_rate": 6.778969234612584e-05,
      "loss": 41.1519,
      "step": 83
    },
    {
      "epoch": 0.028347253859782335,
      "grad_norm": 0.6356281042098999,
      "learning_rate": 6.701465872208216e-05,
      "loss": 41.1429,
      "step": 84
    },
    {
      "epoch": 0.028684721167636887,
      "grad_norm": 0.5690599083900452,
      "learning_rate": 6.623497346023418e-05,
      "loss": 41.129,
      "step": 85
    },
    {
      "epoch": 0.029022188475491435,
      "grad_norm": 0.6062594056129456,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.1624,
      "step": 86
    },
    {
      "epoch": 0.029359655783345987,
      "grad_norm": 0.6127517819404602,
      "learning_rate": 6.466250186922325e-05,
      "loss": 41.136,
      "step": 87
    },
    {
      "epoch": 0.02969712309120054,
      "grad_norm": 0.6459049582481384,
      "learning_rate": 6.387014543809223e-05,
      "loss": 41.1903,
      "step": 88
    },
    {
      "epoch": 0.03003459039905509,
      "grad_norm": 0.7877275347709656,
      "learning_rate": 6.307399704769099e-05,
      "loss": 41.1553,
      "step": 89
    },
    {
      "epoch": 0.030372057706909643,
      "grad_norm": 0.5700125694274902,
      "learning_rate": 6.227427435703997e-05,
      "loss": 41.1488,
      "step": 90
    },
    {
      "epoch": 0.030709525014764195,
      "grad_norm": 0.7931616306304932,
      "learning_rate": 6.147119600233758e-05,
      "loss": 41.1491,
      "step": 91
    },
    {
      "epoch": 0.031046992322618747,
      "grad_norm": 0.7663997411727905,
      "learning_rate": 6.066498153718735e-05,
      "loss": 41.1098,
      "step": 92
    },
    {
      "epoch": 0.031384459630473295,
      "grad_norm": 0.5951213240623474,
      "learning_rate": 5.985585137257401e-05,
      "loss": 41.1219,
      "step": 93
    },
    {
      "epoch": 0.03172192693832785,
      "grad_norm": 0.700258195400238,
      "learning_rate": 5.90440267166055e-05,
      "loss": 41.0836,
      "step": 94
    },
    {
      "epoch": 0.0320593942461824,
      "grad_norm": 0.7702288627624512,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 41.1307,
      "step": 95
    },
    {
      "epoch": 0.032396861554036954,
      "grad_norm": 0.6966155767440796,
      "learning_rate": 5.74131823855921e-05,
      "loss": 41.0971,
      "step": 96
    },
    {
      "epoch": 0.0327343288618915,
      "grad_norm": 0.7049131989479065,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 41.1293,
      "step": 97
    },
    {
      "epoch": 0.03307179616974606,
      "grad_norm": 0.7961778044700623,
      "learning_rate": 5.577423184847932e-05,
      "loss": 41.0863,
      "step": 98
    },
    {
      "epoch": 0.033409263477600606,
      "grad_norm": 1.2966079711914062,
      "learning_rate": 5.495227651252315e-05,
      "loss": 41.0694,
      "step": 99
    },
    {
      "epoch": 0.03374673078545516,
      "grad_norm": 1.6207212209701538,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 40.9814,
      "step": 100
    },
    {
      "epoch": 0.03374673078545516,
      "eval_loss": 10.283768653869629,
      "eval_runtime": 10.3865,
      "eval_samples_per_second": 480.525,
      "eval_steps_per_second": 120.155,
      "step": 100
    },
    {
      "epoch": 0.03408419809330971,
      "grad_norm": 0.6631452441215515,
      "learning_rate": 5.330452921628497e-05,
      "loss": 41.1736,
      "step": 101
    },
    {
      "epoch": 0.034421665401164266,
      "grad_norm": 0.5232149958610535,
      "learning_rate": 5.247918773366112e-05,
      "loss": 41.1804,
      "step": 102
    },
    {
      "epoch": 0.034759132709018814,
      "grad_norm": 0.5507115721702576,
      "learning_rate": 5.165316846586541e-05,
      "loss": 41.179,
      "step": 103
    },
    {
      "epoch": 0.03509660001687336,
      "grad_norm": 0.6441167593002319,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 41.1841,
      "step": 104
    },
    {
      "epoch": 0.03543406732472792,
      "grad_norm": 0.627568781375885,
      "learning_rate": 5e-05,
      "loss": 41.1701,
      "step": 105
    },
    {
      "epoch": 0.035771534632582466,
      "grad_norm": 0.5853610634803772,
      "learning_rate": 4.917330276168208e-05,
      "loss": 41.1665,
      "step": 106
    },
    {
      "epoch": 0.03610900194043702,
      "grad_norm": 0.5873425006866455,
      "learning_rate": 4.834683153413459e-05,
      "loss": 41.1707,
      "step": 107
    },
    {
      "epoch": 0.03644646924829157,
      "grad_norm": 0.6461912989616394,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 41.1673,
      "step": 108
    },
    {
      "epoch": 0.036783936556146125,
      "grad_norm": 0.7396220564842224,
      "learning_rate": 4.669547078371504e-05,
      "loss": 41.1618,
      "step": 109
    },
    {
      "epoch": 0.037121403864000674,
      "grad_norm": 0.7948446273803711,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 41.1691,
      "step": 110
    },
    {
      "epoch": 0.03745887117185523,
      "grad_norm": 0.6458503603935242,
      "learning_rate": 4.504772348747687e-05,
      "loss": 41.1518,
      "step": 111
    },
    {
      "epoch": 0.03779633847970978,
      "grad_norm": 0.7759207487106323,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 41.1519,
      "step": 112
    },
    {
      "epoch": 0.03813380578756433,
      "grad_norm": 0.5650349855422974,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 41.1527,
      "step": 113
    },
    {
      "epoch": 0.03847127309541888,
      "grad_norm": 0.5120344758033752,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 41.1563,
      "step": 114
    },
    {
      "epoch": 0.03880874040327343,
      "grad_norm": 0.505688488483429,
      "learning_rate": 4.17702704859633e-05,
      "loss": 41.1726,
      "step": 115
    },
    {
      "epoch": 0.039146207711127985,
      "grad_norm": 0.5561630725860596,
      "learning_rate": 4.095597328339452e-05,
      "loss": 41.1642,
      "step": 116
    },
    {
      "epoch": 0.039483675018982534,
      "grad_norm": 0.6357062458992004,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 41.1606,
      "step": 117
    },
    {
      "epoch": 0.03982114232683709,
      "grad_norm": 0.4704327881336212,
      "learning_rate": 3.933501846281267e-05,
      "loss": 41.1532,
      "step": 118
    },
    {
      "epoch": 0.04015860963469164,
      "grad_norm": 0.46163249015808105,
      "learning_rate": 3.852880399766243e-05,
      "loss": 41.1663,
      "step": 119
    },
    {
      "epoch": 0.04049607694254619,
      "grad_norm": 0.6409414410591125,
      "learning_rate": 3.772572564296005e-05,
      "loss": 41.1349,
      "step": 120
    },
    {
      "epoch": 0.04083354425040074,
      "grad_norm": 0.44758090376853943,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 41.1493,
      "step": 121
    },
    {
      "epoch": 0.0411710115582553,
      "grad_norm": 0.5253282785415649,
      "learning_rate": 3.612985456190778e-05,
      "loss": 41.0972,
      "step": 122
    },
    {
      "epoch": 0.041508478866109845,
      "grad_norm": 0.47354239225387573,
      "learning_rate": 3.533749813077677e-05,
      "loss": 41.1512,
      "step": 123
    },
    {
      "epoch": 0.0418459461739644,
      "grad_norm": 0.4809248149394989,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.1492,
      "step": 124
    },
    {
      "epoch": 0.04218341348181895,
      "grad_norm": 0.4678039848804474,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 41.1347,
      "step": 125
    },
    {
      "epoch": 0.0425208807896735,
      "grad_norm": 0.5021424293518066,
      "learning_rate": 3.298534127791785e-05,
      "loss": 41.1462,
      "step": 126
    },
    {
      "epoch": 0.04285834809752805,
      "grad_norm": 0.45669126510620117,
      "learning_rate": 3.221030765387417e-05,
      "loss": 41.1469,
      "step": 127
    },
    {
      "epoch": 0.0431958154053826,
      "grad_norm": 0.4208684265613556,
      "learning_rate": 3.144013755408895e-05,
      "loss": 41.1082,
      "step": 128
    },
    {
      "epoch": 0.043533282713237156,
      "grad_norm": 0.6064273715019226,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 41.1508,
      "step": 129
    },
    {
      "epoch": 0.043870750021091705,
      "grad_norm": 0.5487428903579712,
      "learning_rate": 2.991522876735154e-05,
      "loss": 41.1412,
      "step": 130
    },
    {
      "epoch": 0.04420821732894626,
      "grad_norm": 0.6283019781112671,
      "learning_rate": 2.916090697523549e-05,
      "loss": 41.1142,
      "step": 131
    },
    {
      "epoch": 0.04454568463680081,
      "grad_norm": 0.5648553371429443,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 41.0876,
      "step": 132
    },
    {
      "epoch": 0.044883151944655364,
      "grad_norm": 0.5364258289337158,
      "learning_rate": 2.766955965735968e-05,
      "loss": 41.1021,
      "step": 133
    },
    {
      "epoch": 0.04522061925250991,
      "grad_norm": 0.4650258719921112,
      "learning_rate": 2.693294185106562e-05,
      "loss": 41.0846,
      "step": 134
    },
    {
      "epoch": 0.04555808656036447,
      "grad_norm": 0.6070722937583923,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 41.1021,
      "step": 135
    },
    {
      "epoch": 0.045895553868219016,
      "grad_norm": 0.4972531497478485,
      "learning_rate": 2.547882480847461e-05,
      "loss": 41.101,
      "step": 136
    },
    {
      "epoch": 0.046233021176073565,
      "grad_norm": 0.5745977163314819,
      "learning_rate": 2.476172311325783e-05,
      "loss": 41.1361,
      "step": 137
    },
    {
      "epoch": 0.04657048848392812,
      "grad_norm": 0.557130753993988,
      "learning_rate": 2.405152131093926e-05,
      "loss": 41.0751,
      "step": 138
    },
    {
      "epoch": 0.04690795579178267,
      "grad_norm": 0.6838893294334412,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 41.0566,
      "step": 139
    },
    {
      "epoch": 0.047245423099637224,
      "grad_norm": 0.6785029172897339,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 41.0965,
      "step": 140
    },
    {
      "epoch": 0.04758289040749177,
      "grad_norm": 0.7374997138977051,
      "learning_rate": 2.196424713241637e-05,
      "loss": 41.0599,
      "step": 141
    },
    {
      "epoch": 0.04792035771534633,
      "grad_norm": 0.8638346791267395,
      "learning_rate": 2.128356686585282e-05,
      "loss": 41.0706,
      "step": 142
    },
    {
      "epoch": 0.048257825023200876,
      "grad_norm": 0.7817887663841248,
      "learning_rate": 2.061073738537635e-05,
      "loss": 41.0814,
      "step": 143
    },
    {
      "epoch": 0.04859529233105543,
      "grad_norm": 0.655842125415802,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 41.0559,
      "step": 144
    },
    {
      "epoch": 0.04893275963890998,
      "grad_norm": 0.773841917514801,
      "learning_rate": 1.928936436551661e-05,
      "loss": 41.0618,
      "step": 145
    },
    {
      "epoch": 0.049270226946764535,
      "grad_norm": 0.8239593505859375,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 41.0583,
      "step": 146
    },
    {
      "epoch": 0.049607694254619084,
      "grad_norm": 0.9407422542572021,
      "learning_rate": 1.800157297483417e-05,
      "loss": 41.0591,
      "step": 147
    },
    {
      "epoch": 0.04994516156247363,
      "grad_norm": 0.9903011918067932,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 41.0109,
      "step": 148
    },
    {
      "epoch": 0.05028262887032819,
      "grad_norm": 1.2458070516586304,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 41.001,
      "step": 149
    },
    {
      "epoch": 0.050620096178182736,
      "grad_norm": 1.5455807447433472,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 40.9556,
      "step": 150
    },
    {
      "epoch": 0.050620096178182736,
      "eval_loss": 10.277101516723633,
      "eval_runtime": 10.3531,
      "eval_samples_per_second": 482.077,
      "eval_steps_per_second": 120.543,
      "step": 150
    },
    {
      "epoch": 0.05095756348603729,
      "grad_norm": 0.6087143421173096,
      "learning_rate": 1.553232954407171e-05,
      "loss": 41.1649,
      "step": 151
    },
    {
      "epoch": 0.05129503079389184,
      "grad_norm": 0.5204493403434753,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 41.1489,
      "step": 152
    },
    {
      "epoch": 0.051632498101746395,
      "grad_norm": 0.5976318717002869,
      "learning_rate": 1.435357758543015e-05,
      "loss": 41.1418,
      "step": 153
    },
    {
      "epoch": 0.05196996540960094,
      "grad_norm": 0.6087062954902649,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 41.1612,
      "step": 154
    },
    {
      "epoch": 0.0523074327174555,
      "grad_norm": 0.5197517275810242,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 41.1769,
      "step": 155
    },
    {
      "epoch": 0.05264490002531005,
      "grad_norm": 0.6037111282348633,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 41.153,
      "step": 156
    },
    {
      "epoch": 0.0529823673331646,
      "grad_norm": 0.49915647506713867,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 41.1569,
      "step": 157
    },
    {
      "epoch": 0.05331983464101915,
      "grad_norm": 0.5264829993247986,
      "learning_rate": 1.157994445715706e-05,
      "loss": 41.1188,
      "step": 158
    },
    {
      "epoch": 0.053657301948873706,
      "grad_norm": 0.571643054485321,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.1578,
      "step": 159
    },
    {
      "epoch": 0.053994769256728255,
      "grad_norm": 0.5075641870498657,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 41.1523,
      "step": 160
    },
    {
      "epoch": 0.0543322365645828,
      "grad_norm": 0.4338206350803375,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 41.1532,
      "step": 161
    },
    {
      "epoch": 0.05466970387243736,
      "grad_norm": 0.5018669366836548,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.1471,
      "step": 162
    },
    {
      "epoch": 0.05500717118029191,
      "grad_norm": 0.46041765809059143,
      "learning_rate": 9.068759265665384e-06,
      "loss": 41.1519,
      "step": 163
    },
    {
      "epoch": 0.05534463848814646,
      "grad_norm": 0.43533748388290405,
      "learning_rate": 8.599558442598998e-06,
      "loss": 41.15,
      "step": 164
    },
    {
      "epoch": 0.05568210579600101,
      "grad_norm": 0.4950281083583832,
      "learning_rate": 8.141676086873572e-06,
      "loss": 41.1272,
      "step": 165
    },
    {
      "epoch": 0.056019573103855566,
      "grad_norm": 0.4795650541782379,
      "learning_rate": 7.695237378953223e-06,
      "loss": 41.1493,
      "step": 166
    },
    {
      "epoch": 0.056357040411710115,
      "grad_norm": 0.4915917217731476,
      "learning_rate": 7.260364370723044e-06,
      "loss": 41.1196,
      "step": 167
    },
    {
      "epoch": 0.05669450771956467,
      "grad_norm": 0.4055745303630829,
      "learning_rate": 6.837175952121306e-06,
      "loss": 41.1402,
      "step": 168
    },
    {
      "epoch": 0.05703197502741922,
      "grad_norm": 0.49207720160484314,
      "learning_rate": 6.425787818636131e-06,
      "loss": 41.1113,
      "step": 169
    },
    {
      "epoch": 0.057369442335273774,
      "grad_norm": 0.47562989592552185,
      "learning_rate": 6.026312439675552e-06,
      "loss": 41.1312,
      "step": 170
    },
    {
      "epoch": 0.05770690964312832,
      "grad_norm": 0.44024497270584106,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 41.131,
      "step": 171
    },
    {
      "epoch": 0.05804437695098287,
      "grad_norm": 0.44389140605926514,
      "learning_rate": 5.263533508961827e-06,
      "loss": 41.1162,
      "step": 172
    },
    {
      "epoch": 0.058381844258837426,
      "grad_norm": 0.47130900621414185,
      "learning_rate": 4.900438493352055e-06,
      "loss": 41.0935,
      "step": 173
    },
    {
      "epoch": 0.058719311566691974,
      "grad_norm": 0.3634178042411804,
      "learning_rate": 4.549673247541875e-06,
      "loss": 41.1265,
      "step": 174
    },
    {
      "epoch": 0.05905677887454653,
      "grad_norm": 0.46501460671424866,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 41.1487,
      "step": 175
    },
    {
      "epoch": 0.05939424618240108,
      "grad_norm": 0.48243266344070435,
      "learning_rate": 3.885512251130763e-06,
      "loss": 41.1137,
      "step": 176
    },
    {
      "epoch": 0.059731713490255633,
      "grad_norm": 0.5185329914093018,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 41.1177,
      "step": 177
    },
    {
      "epoch": 0.06006918079811018,
      "grad_norm": 0.4704861044883728,
      "learning_rate": 3.271776770026963e-06,
      "loss": 41.1081,
      "step": 178
    },
    {
      "epoch": 0.06040664810596474,
      "grad_norm": 0.5224180221557617,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 41.1057,
      "step": 179
    },
    {
      "epoch": 0.060744115413819286,
      "grad_norm": 0.4637226164340973,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 41.0788,
      "step": 180
    },
    {
      "epoch": 0.06108158272167384,
      "grad_norm": 0.5957618355751038,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.1321,
      "step": 181
    },
    {
      "epoch": 0.06141905002952839,
      "grad_norm": 0.5218991637229919,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 41.1001,
      "step": 182
    },
    {
      "epoch": 0.06175651733738294,
      "grad_norm": 0.4695798456668854,
      "learning_rate": 1.962316193157593e-06,
      "loss": 41.1399,
      "step": 183
    },
    {
      "epoch": 0.06209398464523749,
      "grad_norm": 0.5807790160179138,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 41.0777,
      "step": 184
    },
    {
      "epoch": 0.06243145195309204,
      "grad_norm": 0.4845099151134491,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 41.0807,
      "step": 185
    },
    {
      "epoch": 0.06276891926094659,
      "grad_norm": 0.6070156097412109,
      "learning_rate": 1.333670137599713e-06,
      "loss": 41.0779,
      "step": 186
    },
    {
      "epoch": 0.06310638656880115,
      "grad_norm": 0.6996654868125916,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 41.0459,
      "step": 187
    },
    {
      "epoch": 0.0634438538766557,
      "grad_norm": 0.5513322353363037,
      "learning_rate": 9.810017062595322e-07,
      "loss": 41.0886,
      "step": 188
    },
    {
      "epoch": 0.06378132118451026,
      "grad_norm": 0.6235438585281372,
      "learning_rate": 8.247462563808817e-07,
      "loss": 41.1055,
      "step": 189
    },
    {
      "epoch": 0.0641187884923648,
      "grad_norm": 0.6210430264472961,
      "learning_rate": 6.819348298638839e-07,
      "loss": 41.0386,
      "step": 190
    },
    {
      "epoch": 0.06445625580021935,
      "grad_norm": 0.6518939733505249,
      "learning_rate": 5.526064699265753e-07,
      "loss": 41.0434,
      "step": 191
    },
    {
      "epoch": 0.06479372310807391,
      "grad_norm": 0.7172924876213074,
      "learning_rate": 4.367965336512403e-07,
      "loss": 41.0925,
      "step": 192
    },
    {
      "epoch": 0.06513119041592846,
      "grad_norm": 0.6605562567710876,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 41.0225,
      "step": 193
    },
    {
      "epoch": 0.065468657723783,
      "grad_norm": 0.695184051990509,
      "learning_rate": 2.458548727494292e-07,
      "loss": 41.065,
      "step": 194
    },
    {
      "epoch": 0.06580612503163756,
      "grad_norm": 0.778633713722229,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 41.0745,
      "step": 195
    },
    {
      "epoch": 0.06614359233949212,
      "grad_norm": 0.95775306224823,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 41.0172,
      "step": 196
    },
    {
      "epoch": 0.06648105964734666,
      "grad_norm": 0.8663340210914612,
      "learning_rate": 6.150154258476315e-08,
      "loss": 41.0097,
      "step": 197
    },
    {
      "epoch": 0.06681852695520121,
      "grad_norm": 1.067402958869934,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 40.9849,
      "step": 198
    },
    {
      "epoch": 0.06715599426305577,
      "grad_norm": 1.4724292755126953,
      "learning_rate": 6.834750376549792e-09,
      "loss": 41.0145,
      "step": 199
    },
    {
      "epoch": 0.06749346157091032,
      "grad_norm": 1.7189046144485474,
      "learning_rate": 0.0,
      "loss": 40.8855,
      "step": 200
    },
    {
      "epoch": 0.06749346157091032,
      "eval_loss": 10.275985717773438,
      "eval_runtime": 10.36,
      "eval_samples_per_second": 481.755,
      "eval_steps_per_second": 120.463,
      "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": 42961836441600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}