{
  "best_metric": 0.7366492748260498,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3367003367003367,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016835016835016834,
      "grad_norm": 4.344457149505615,
      "learning_rate": 1e-05,
      "loss": 1.8327,
      "step": 1
    },
    {
      "epoch": 0.0016835016835016834,
      "eval_loss": 2.372297525405884,
      "eval_runtime": 17.5595,
      "eval_samples_per_second": 57.006,
      "eval_steps_per_second": 14.294,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 4.559857368469238,
      "learning_rate": 2e-05,
      "loss": 1.9518,
      "step": 2
    },
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 4.749698638916016,
      "learning_rate": 3e-05,
      "loss": 1.992,
      "step": 3
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 4.841248512268066,
      "learning_rate": 4e-05,
      "loss": 1.9492,
      "step": 4
    },
    {
      "epoch": 0.008417508417508417,
      "grad_norm": 4.272185325622559,
      "learning_rate": 5e-05,
      "loss": 1.7927,
      "step": 5
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 4.426045894622803,
      "learning_rate": 6e-05,
      "loss": 1.5661,
      "step": 6
    },
    {
      "epoch": 0.011784511784511785,
      "grad_norm": 5.376197338104248,
      "learning_rate": 7e-05,
      "loss": 1.4635,
      "step": 7
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 3.920807123184204,
      "learning_rate": 8e-05,
      "loss": 1.3036,
      "step": 8
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 3.284846782684326,
      "learning_rate": 9e-05,
      "loss": 1.1707,
      "step": 9
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 3.570317029953003,
      "learning_rate": 0.0001,
      "loss": 1.263,
      "step": 10
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 3.5480268001556396,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.18,
      "step": 11
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 2.7992141246795654,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1856,
      "step": 12
    },
    {
      "epoch": 0.021885521885521887,
      "grad_norm": 2.70453143119812,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0992,
      "step": 13
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.5126028060913086,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1641,
      "step": 14
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 2.3141353130340576,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.878,
      "step": 15
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.473644256591797,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0646,
      "step": 16
    },
    {
      "epoch": 0.02861952861952862,
      "grad_norm": 2.1837191581726074,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9778,
      "step": 17
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.26151704788208,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9038,
      "step": 18
    },
    {
      "epoch": 0.03198653198653199,
      "grad_norm": 2.1908414363861084,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.981,
      "step": 19
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.0420589447021484,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0305,
      "step": 20
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 2.0413763523101807,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.927,
      "step": 21
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.9570962190628052,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9577,
      "step": 22
    },
    {
      "epoch": 0.03872053872053872,
      "grad_norm": 2.001523971557617,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8943,
      "step": 23
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 1.9638859033584595,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.852,
      "step": 24
    },
    {
      "epoch": 0.04208754208754209,
      "grad_norm": 1.729615330696106,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7786,
      "step": 25
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 1.9220117330551147,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7602,
      "step": 26
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 2.247906446456909,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8663,
      "step": 27
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 2.1183836460113525,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9381,
      "step": 28
    },
    {
      "epoch": 0.04882154882154882,
      "grad_norm": 2.046532154083252,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9184,
      "step": 29
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.1741554737091064,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9351,
      "step": 30
    },
    {
      "epoch": 0.05218855218855219,
      "grad_norm": 1.9772783517837524,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8768,
      "step": 31
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 2.0210866928100586,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9189,
      "step": 32
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.9957700967788696,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8419,
      "step": 33
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.9444462060928345,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9348,
      "step": 34
    },
    {
      "epoch": 0.058922558922558925,
      "grad_norm": 1.6899060010910034,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8503,
      "step": 35
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.9348347187042236,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8889,
      "step": 36
    },
    {
      "epoch": 0.06228956228956229,
      "grad_norm": 1.8934228420257568,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8401,
      "step": 37
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.8300187587738037,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8818,
      "step": 38
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 1.948350429534912,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8524,
      "step": 39
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.8289375305175781,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8226,
      "step": 40
    },
    {
      "epoch": 0.06902356902356903,
      "grad_norm": 1.9909924268722534,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9751,
      "step": 41
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.9564872980117798,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7552,
      "step": 42
    },
    {
      "epoch": 0.0723905723905724,
      "grad_norm": 1.9402929544448853,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8015,
      "step": 43
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.1193935871124268,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.819,
      "step": 44
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 1.9750330448150635,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8153,
      "step": 45
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.8374894857406616,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8455,
      "step": 46
    },
    {
      "epoch": 0.07912457912457913,
      "grad_norm": 1.954999566078186,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7939,
      "step": 47
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.7081700563430786,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7501,
      "step": 48
    },
    {
      "epoch": 0.08249158249158249,
      "grad_norm": 1.8316476345062256,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7973,
      "step": 49
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 2.4306771755218506,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8423,
      "step": 50
    },
    {
      "epoch": 0.08417508417508418,
      "eval_loss": 0.9268580079078674,
      "eval_runtime": 17.5631,
      "eval_samples_per_second": 56.995,
      "eval_steps_per_second": 14.291,
      "step": 50
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 3.4986860752105713,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2164,
      "step": 51
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 3.1427040100097656,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1006,
      "step": 52
    },
    {
      "epoch": 0.08922558922558922,
      "grad_norm": 2.469325542449951,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1304,
      "step": 53
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.970203161239624,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9661,
      "step": 54
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.8259844779968262,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9878,
      "step": 55
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.9692765474319458,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8895,
      "step": 56
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 2.031215190887451,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9089,
      "step": 57
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 2.151510238647461,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.847,
      "step": 58
    },
    {
      "epoch": 0.09932659932659933,
      "grad_norm": 1.9801528453826904,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9048,
      "step": 59
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.6576982736587524,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8299,
      "step": 60
    },
    {
      "epoch": 0.1026936026936027,
      "grad_norm": 1.642683506011963,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9419,
      "step": 61
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 1.7137136459350586,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8952,
      "step": 62
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 1.4606491327285767,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7688,
      "step": 63
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.5353506803512573,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8586,
      "step": 64
    },
    {
      "epoch": 0.10942760942760943,
      "grad_norm": 1.6863253116607666,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8147,
      "step": 65
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.4657721519470215,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8841,
      "step": 66
    },
    {
      "epoch": 0.1127946127946128,
      "grad_norm": 1.492482304573059,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8886,
      "step": 67
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.5304661989212036,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7021,
      "step": 68
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 1.5507373809814453,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7782,
      "step": 69
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.6308273077011108,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8405,
      "step": 70
    },
    {
      "epoch": 0.11952861952861953,
      "grad_norm": 1.5226702690124512,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7479,
      "step": 71
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.5649571418762207,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7766,
      "step": 72
    },
    {
      "epoch": 0.12289562289562289,
      "grad_norm": 1.5798249244689941,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8096,
      "step": 73
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 1.7768361568450928,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9015,
      "step": 74
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 1.4791433811187744,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7105,
      "step": 75
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 1.6911453008651733,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8887,
      "step": 76
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.6520248651504517,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7838,
      "step": 77
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 1.7401238679885864,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9002,
      "step": 78
    },
    {
      "epoch": 0.132996632996633,
      "grad_norm": 1.5868674516677856,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7389,
      "step": 79
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.6427090167999268,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7696,
      "step": 80
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.5060991048812866,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6928,
      "step": 81
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.4474501609802246,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7405,
      "step": 82
    },
    {
      "epoch": 0.13973063973063973,
      "grad_norm": 1.6056426763534546,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8239,
      "step": 83
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 1.5527349710464478,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7655,
      "step": 84
    },
    {
      "epoch": 0.14309764309764308,
      "grad_norm": 1.5461704730987549,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7212,
      "step": 85
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.710639238357544,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7636,
      "step": 86
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 1.5907717943191528,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6059,
      "step": 87
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.7331855297088623,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6574,
      "step": 88
    },
    {
      "epoch": 0.14983164983164984,
      "grad_norm": 1.5404057502746582,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6831,
      "step": 89
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.7522305250167847,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8159,
      "step": 90
    },
    {
      "epoch": 0.1531986531986532,
      "grad_norm": 1.6588091850280762,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7997,
      "step": 91
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.6053378582000732,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7951,
      "step": 92
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 1.6175459623336792,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7115,
      "step": 93
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 1.777561068534851,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7281,
      "step": 94
    },
    {
      "epoch": 0.15993265993265993,
      "grad_norm": 2.041378974914551,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.752,
      "step": 95
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 1.7569489479064941,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7516,
      "step": 96
    },
    {
      "epoch": 0.1632996632996633,
      "grad_norm": 1.7243311405181885,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6843,
      "step": 97
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 1.7971991300582886,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7182,
      "step": 98
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.6935278177261353,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7107,
      "step": 99
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 2.100818395614624,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8399,
      "step": 100
    },
    {
      "epoch": 0.16835016835016836,
      "eval_loss": 0.8277133107185364,
      "eval_runtime": 17.5459,
      "eval_samples_per_second": 57.05,
      "eval_steps_per_second": 14.305,
      "step": 100
    },
    {
      "epoch": 0.17003367003367004,
      "grad_norm": 2.1283490657806396,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9779,
      "step": 101
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 2.0497095584869385,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9605,
      "step": 102
    },
    {
      "epoch": 0.1734006734006734,
      "grad_norm": 1.9842888116836548,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9533,
      "step": 103
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 1.9111071825027466,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8849,
      "step": 104
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 1.7113656997680664,
      "learning_rate": 5e-05,
      "loss": 0.8496,
      "step": 105
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 1.7323176860809326,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8561,
      "step": 106
    },
    {
      "epoch": 0.18013468013468015,
      "grad_norm": 1.6348509788513184,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8805,
      "step": 107
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.575493574142456,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8199,
      "step": 108
    },
    {
      "epoch": 0.1835016835016835,
      "grad_norm": 1.4189974069595337,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8009,
      "step": 109
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.437255620956421,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8203,
      "step": 110
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 1.5010749101638794,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7025,
      "step": 111
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 1.5750865936279297,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8776,
      "step": 112
    },
    {
      "epoch": 0.19023569023569023,
      "grad_norm": 1.421027421951294,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7985,
      "step": 113
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 1.5161536931991577,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.831,
      "step": 114
    },
    {
      "epoch": 0.1936026936026936,
      "grad_norm": 1.4222854375839233,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7318,
      "step": 115
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 1.4862648248672485,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7526,
      "step": 116
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 1.3348816633224487,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6988,
      "step": 117
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 1.4456006288528442,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7277,
      "step": 118
    },
    {
      "epoch": 0.20033670033670034,
      "grad_norm": 1.4563487768173218,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6961,
      "step": 119
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.368796944618225,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6821,
      "step": 120
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 1.4485459327697754,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7799,
      "step": 121
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 1.4459701776504517,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7281,
      "step": 122
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 1.447265625,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.717,
      "step": 123
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 1.4635508060455322,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.766,
      "step": 124
    },
    {
      "epoch": 0.21043771043771045,
      "grad_norm": 1.4395512342453003,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7754,
      "step": 125
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.366001844406128,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6534,
      "step": 126
    },
    {
      "epoch": 0.2138047138047138,
      "grad_norm": 1.4238622188568115,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7424,
      "step": 127
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 1.5306339263916016,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7513,
      "step": 128
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 1.4926470518112183,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7959,
      "step": 129
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 1.4433307647705078,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7022,
      "step": 130
    },
    {
      "epoch": 0.22053872053872053,
      "grad_norm": 1.4791374206542969,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6538,
      "step": 131
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.4287264347076416,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6852,
      "step": 132
    },
    {
      "epoch": 0.2239057239057239,
      "grad_norm": 1.4698001146316528,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6495,
      "step": 133
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 1.5329447984695435,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7901,
      "step": 134
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.589925765991211,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7507,
      "step": 135
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 1.5763044357299805,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7807,
      "step": 136
    },
    {
      "epoch": 0.23063973063973064,
      "grad_norm": 1.4397014379501343,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.631,
      "step": 137
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 1.511014699935913,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6267,
      "step": 138
    },
    {
      "epoch": 0.234006734006734,
      "grad_norm": 1.4697332382202148,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.626,
      "step": 139
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 1.5686163902282715,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.686,
      "step": 140
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 1.4750709533691406,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5807,
      "step": 141
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 1.4001365900039673,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6296,
      "step": 142
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 1.5306497812271118,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.717,
      "step": 143
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.7043498754501343,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7339,
      "step": 144
    },
    {
      "epoch": 0.2441077441077441,
      "grad_norm": 1.524138331413269,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6473,
      "step": 145
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 1.604480266571045,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6711,
      "step": 146
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 1.741590976715088,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6064,
      "step": 147
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 1.7959448099136353,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6728,
      "step": 148
    },
    {
      "epoch": 0.25084175084175087,
      "grad_norm": 1.7553412914276123,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6027,
      "step": 149
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 2.1622414588928223,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6971,
      "step": 150
    },
    {
      "epoch": 0.25252525252525254,
      "eval_loss": 0.7632071375846863,
      "eval_runtime": 17.6978,
      "eval_samples_per_second": 56.561,
      "eval_steps_per_second": 14.183,
      "step": 150
    },
    {
      "epoch": 0.2542087542087542,
      "grad_norm": 1.8006595373153687,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9582,
      "step": 151
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 1.7452774047851562,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8445,
      "step": 152
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 1.657069444656372,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7849,
      "step": 153
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 1.8111995458602905,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.899,
      "step": 154
    },
    {
      "epoch": 0.2609427609427609,
      "grad_norm": 1.6609547138214111,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.9086,
      "step": 155
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 1.761616587638855,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7595,
      "step": 156
    },
    {
      "epoch": 0.26430976430976433,
      "grad_norm": 1.6796464920043945,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8219,
      "step": 157
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 1.5108773708343506,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7362,
      "step": 158
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 1.5235345363616943,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7772,
      "step": 159
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 1.5320680141448975,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7596,
      "step": 160
    },
    {
      "epoch": 0.27104377104377103,
      "grad_norm": 1.510825514793396,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7124,
      "step": 161
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.4945927858352661,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7582,
      "step": 162
    },
    {
      "epoch": 0.27441077441077444,
      "grad_norm": 1.4497345685958862,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8063,
      "step": 163
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 1.503874659538269,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.833,
      "step": 164
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.4625698328018188,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8029,
      "step": 165
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 1.424583911895752,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6634,
      "step": 166
    },
    {
      "epoch": 0.28114478114478114,
      "grad_norm": 1.444604754447937,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6646,
      "step": 167
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 1.399767279624939,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7342,
      "step": 168
    },
    {
      "epoch": 0.2845117845117845,
      "grad_norm": 1.4893559217453003,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7788,
      "step": 169
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 1.4600625038146973,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7136,
      "step": 170
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 1.3619142770767212,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6373,
      "step": 171
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 1.3781132698059082,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7422,
      "step": 172
    },
    {
      "epoch": 0.29124579124579125,
      "grad_norm": 1.4753018617630005,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7707,
      "step": 173
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 1.6195520162582397,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7053,
      "step": 174
    },
    {
      "epoch": 0.2946127946127946,
      "grad_norm": 1.4694888591766357,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6559,
      "step": 175
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.3780499696731567,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6372,
      "step": 176
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 1.429612398147583,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7175,
      "step": 177
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 1.4105802774429321,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7358,
      "step": 178
    },
    {
      "epoch": 0.30134680134680136,
      "grad_norm": 1.3942468166351318,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6912,
      "step": 179
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.4551000595092773,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6991,
      "step": 180
    },
    {
      "epoch": 0.3047138047138047,
      "grad_norm": 1.5984594821929932,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.621,
      "step": 181
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 1.4579471349716187,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6393,
      "step": 182
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 1.4946399927139282,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7075,
      "step": 183
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 1.5560321807861328,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7958,
      "step": 184
    },
    {
      "epoch": 0.3114478114478115,
      "grad_norm": 1.5716874599456787,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6644,
      "step": 185
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 1.4193757772445679,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6942,
      "step": 186
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 1.5917426347732544,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7648,
      "step": 187
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 1.5423691272735596,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6325,
      "step": 188
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.5988414287567139,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7345,
      "step": 189
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 1.5703312158584595,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7532,
      "step": 190
    },
    {
      "epoch": 0.32154882154882153,
      "grad_norm": 1.6625339984893799,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6719,
      "step": 191
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 1.8440299034118652,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8739,
      "step": 192
    },
    {
      "epoch": 0.32491582491582494,
      "grad_norm": 1.6666868925094604,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7696,
      "step": 193
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 1.737694501876831,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7303,
      "step": 194
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 1.7202603816986084,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6411,
      "step": 195
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 1.625827431678772,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6209,
      "step": 196
    },
    {
      "epoch": 0.33164983164983164,
      "grad_norm": 1.694730281829834,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6299,
      "step": 197
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.3129141330718994,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6568,
      "step": 198
    },
    {
      "epoch": 0.335016835016835,
      "grad_norm": 1.9081711769104004,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7086,
      "step": 199
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.569549083709717,
      "learning_rate": 0.0,
      "loss": 0.9439,
      "step": 200
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.7366492748260498,
      "eval_runtime": 17.6239,
      "eval_samples_per_second": 56.798,
      "eval_steps_per_second": 14.242,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.54569648635904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}