{
  "best_metric": 2.518922805786133,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.011518746760352474,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.759373380176237e-05,
      "grad_norm": 0.7170475721359253,
      "learning_rate": 1e-05,
      "loss": 2.6032,
      "step": 1
    },
    {
      "epoch": 5.759373380176237e-05,
      "eval_loss": 2.9131555557250977,
      "eval_runtime": 2223.3799,
      "eval_samples_per_second": 13.152,
      "eval_steps_per_second": 3.288,
      "step": 1
    },
    {
      "epoch": 0.00011518746760352474,
      "grad_norm": 0.7894652485847473,
      "learning_rate": 2e-05,
      "loss": 2.6143,
      "step": 2
    },
    {
      "epoch": 0.0001727812014052871,
      "grad_norm": 0.8453594446182251,
      "learning_rate": 3e-05,
      "loss": 2.5765,
      "step": 3
    },
    {
      "epoch": 0.00023037493520704948,
      "grad_norm": 0.9536886215209961,
      "learning_rate": 4e-05,
      "loss": 2.7557,
      "step": 4
    },
    {
      "epoch": 0.00028796866900881183,
      "grad_norm": 0.992527961730957,
      "learning_rate": 5e-05,
      "loss": 2.712,
      "step": 5
    },
    {
      "epoch": 0.0003455624028105742,
      "grad_norm": 1.0349737405776978,
      "learning_rate": 6e-05,
      "loss": 2.5483,
      "step": 6
    },
    {
      "epoch": 0.00040315613661233657,
      "grad_norm": 0.9625363349914551,
      "learning_rate": 7e-05,
      "loss": 2.6037,
      "step": 7
    },
    {
      "epoch": 0.00046074987041409897,
      "grad_norm": 1.0632476806640625,
      "learning_rate": 8e-05,
      "loss": 2.5947,
      "step": 8
    },
    {
      "epoch": 0.0005183436042158614,
      "grad_norm": 0.9896149039268494,
      "learning_rate": 9e-05,
      "loss": 2.6343,
      "step": 9
    },
    {
      "epoch": 0.0005759373380176237,
      "grad_norm": 1.5522687435150146,
      "learning_rate": 0.0001,
      "loss": 2.5878,
      "step": 10
    },
    {
      "epoch": 0.000633531071819386,
      "grad_norm": 1.3630777597427368,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.4873,
      "step": 11
    },
    {
      "epoch": 0.0006911248056211485,
      "grad_norm": 0.9351599216461182,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4615,
      "step": 12
    },
    {
      "epoch": 0.0007487185394229107,
      "grad_norm": 0.9125726222991943,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.6002,
      "step": 13
    },
    {
      "epoch": 0.0008063122732246731,
      "grad_norm": 0.9601115584373474,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.5393,
      "step": 14
    },
    {
      "epoch": 0.0008639060070264355,
      "grad_norm": 0.8136438727378845,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.5858,
      "step": 15
    },
    {
      "epoch": 0.0009214997408281979,
      "grad_norm": 0.7342498898506165,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.5106,
      "step": 16
    },
    {
      "epoch": 0.0009790934746299602,
      "grad_norm": 0.8548296689987183,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.5394,
      "step": 17
    },
    {
      "epoch": 0.0010366872084317227,
      "grad_norm": 0.7524362802505493,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.4546,
      "step": 18
    },
    {
      "epoch": 0.001094280942233485,
      "grad_norm": 0.7919866442680359,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.7383,
      "step": 19
    },
    {
      "epoch": 0.0011518746760352473,
      "grad_norm": 0.8206016421318054,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.5678,
      "step": 20
    },
    {
      "epoch": 0.0012094684098370098,
      "grad_norm": 0.7629212141036987,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.5016,
      "step": 21
    },
    {
      "epoch": 0.001267062143638772,
      "grad_norm": 0.8226024508476257,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.6541,
      "step": 22
    },
    {
      "epoch": 0.0013246558774405344,
      "grad_norm": 0.9207586050033569,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.6506,
      "step": 23
    },
    {
      "epoch": 0.001382249611242297,
      "grad_norm": 0.9256036281585693,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.7124,
      "step": 24
    },
    {
      "epoch": 0.0014398433450440592,
      "grad_norm": 1.0836950540542603,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.5113,
      "step": 25
    },
    {
      "epoch": 0.0014974370788458215,
      "grad_norm": 0.8101277351379395,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.6021,
      "step": 26
    },
    {
      "epoch": 0.001555030812647584,
      "grad_norm": 0.8740267157554626,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.4684,
      "step": 27
    },
    {
      "epoch": 0.0016126245464493463,
      "grad_norm": 1.0666667222976685,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.7615,
      "step": 28
    },
    {
      "epoch": 0.0016702182802511088,
      "grad_norm": 1.0761654376983643,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.409,
      "step": 29
    },
    {
      "epoch": 0.001727812014052871,
      "grad_norm": 1.089020013809204,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.483,
      "step": 30
    },
    {
      "epoch": 0.0017854057478546334,
      "grad_norm": 0.8331020474433899,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.6895,
      "step": 31
    },
    {
      "epoch": 0.0018429994816563959,
      "grad_norm": 0.9163645505905151,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.5083,
      "step": 32
    },
    {
      "epoch": 0.0019005932154581582,
      "grad_norm": 0.9700943231582642,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.4691,
      "step": 33
    },
    {
      "epoch": 0.0019581869492599204,
      "grad_norm": 1.1764390468597412,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.5448,
      "step": 34
    },
    {
      "epoch": 0.0020157806830616827,
      "grad_norm": 1.0879583358764648,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.5489,
      "step": 35
    },
    {
      "epoch": 0.0020733744168634455,
      "grad_norm": 0.8972739577293396,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.6502,
      "step": 36
    },
    {
      "epoch": 0.0021309681506652078,
      "grad_norm": 0.968291163444519,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.6547,
      "step": 37
    },
    {
      "epoch": 0.00218856188446697,
      "grad_norm": 0.8638512492179871,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.5946,
      "step": 38
    },
    {
      "epoch": 0.0022461556182687323,
      "grad_norm": 0.8816486597061157,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5559,
      "step": 39
    },
    {
      "epoch": 0.0023037493520704946,
      "grad_norm": 0.9396282434463501,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.7452,
      "step": 40
    },
    {
      "epoch": 0.002361343085872257,
      "grad_norm": 0.9555278420448303,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.7742,
      "step": 41
    },
    {
      "epoch": 0.0024189368196740196,
      "grad_norm": 1.1094987392425537,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.7289,
      "step": 42
    },
    {
      "epoch": 0.002476530553475782,
      "grad_norm": 1.0985658168792725,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.4903,
      "step": 43
    },
    {
      "epoch": 0.002534124287277544,
      "grad_norm": 1.0876129865646362,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.6188,
      "step": 44
    },
    {
      "epoch": 0.0025917180210793065,
      "grad_norm": 1.3442291021347046,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.6538,
      "step": 45
    },
    {
      "epoch": 0.002649311754881069,
      "grad_norm": 1.114464282989502,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.7823,
      "step": 46
    },
    {
      "epoch": 0.0027069054886828315,
      "grad_norm": 1.2330148220062256,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.786,
      "step": 47
    },
    {
      "epoch": 0.002764499222484594,
      "grad_norm": 1.3404490947723389,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.778,
      "step": 48
    },
    {
      "epoch": 0.002822092956286356,
      "grad_norm": 1.5088051557540894,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.9409,
      "step": 49
    },
    {
      "epoch": 0.0028796866900881184,
      "grad_norm": 1.598839521408081,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.3496,
      "step": 50
    },
    {
      "epoch": 0.0028796866900881184,
      "eval_loss": 2.6991066932678223,
      "eval_runtime": 2234.0069,
      "eval_samples_per_second": 13.09,
      "eval_steps_per_second": 3.273,
      "step": 50
    },
    {
      "epoch": 0.0029372804238898807,
      "grad_norm": 1.6337782144546509,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.3371,
      "step": 51
    },
    {
      "epoch": 0.002994874157691643,
      "grad_norm": 1.1443219184875488,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.3791,
      "step": 52
    },
    {
      "epoch": 0.0030524678914934057,
      "grad_norm": 0.8088019490242004,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.5005,
      "step": 53
    },
    {
      "epoch": 0.003110061625295168,
      "grad_norm": 0.5856528282165527,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.4488,
      "step": 54
    },
    {
      "epoch": 0.0031676553590969303,
      "grad_norm": 0.5685175657272339,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.448,
      "step": 55
    },
    {
      "epoch": 0.0032252490928986926,
      "grad_norm": 0.526979386806488,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.5782,
      "step": 56
    },
    {
      "epoch": 0.003282842826700455,
      "grad_norm": 0.5659884810447693,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.4081,
      "step": 57
    },
    {
      "epoch": 0.0033404365605022176,
      "grad_norm": 0.72710120677948,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.3907,
      "step": 58
    },
    {
      "epoch": 0.00339803029430398,
      "grad_norm": 0.6161883473396301,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.4955,
      "step": 59
    },
    {
      "epoch": 0.003455624028105742,
      "grad_norm": 0.5779476165771484,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.4728,
      "step": 60
    },
    {
      "epoch": 0.0035132177619075044,
      "grad_norm": 0.5841222405433655,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.3109,
      "step": 61
    },
    {
      "epoch": 0.0035708114957092667,
      "grad_norm": 0.6573259830474854,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.3457,
      "step": 62
    },
    {
      "epoch": 0.003628405229511029,
      "grad_norm": 0.6386032104492188,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.5604,
      "step": 63
    },
    {
      "epoch": 0.0036859989633127917,
      "grad_norm": 0.875916600227356,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.5234,
      "step": 64
    },
    {
      "epoch": 0.003743592697114554,
      "grad_norm": 0.7411782145500183,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.4897,
      "step": 65
    },
    {
      "epoch": 0.0038011864309163163,
      "grad_norm": 0.7257915735244751,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.6656,
      "step": 66
    },
    {
      "epoch": 0.0038587801647180786,
      "grad_norm": 0.7597258687019348,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.606,
      "step": 67
    },
    {
      "epoch": 0.003916373898519841,
      "grad_norm": 0.7834044694900513,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.4246,
      "step": 68
    },
    {
      "epoch": 0.003973967632321603,
      "grad_norm": 0.6901299953460693,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.4062,
      "step": 69
    },
    {
      "epoch": 0.0040315613661233655,
      "grad_norm": 0.7225314378738403,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.5329,
      "step": 70
    },
    {
      "epoch": 0.004089155099925128,
      "grad_norm": 0.8313844203948975,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.3974,
      "step": 71
    },
    {
      "epoch": 0.004146748833726891,
      "grad_norm": 0.6948657035827637,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.4274,
      "step": 72
    },
    {
      "epoch": 0.004204342567528653,
      "grad_norm": 0.7491827011108398,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.4154,
      "step": 73
    },
    {
      "epoch": 0.0042619363013304155,
      "grad_norm": 0.7103192210197449,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.5059,
      "step": 74
    },
    {
      "epoch": 0.004319530035132178,
      "grad_norm": 0.7131175994873047,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.5827,
      "step": 75
    },
    {
      "epoch": 0.00437712376893394,
      "grad_norm": 0.7724280953407288,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.5181,
      "step": 76
    },
    {
      "epoch": 0.004434717502735702,
      "grad_norm": 0.7166052460670471,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.5591,
      "step": 77
    },
    {
      "epoch": 0.004492311236537465,
      "grad_norm": 0.8257824182510376,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.6382,
      "step": 78
    },
    {
      "epoch": 0.004549904970339227,
      "grad_norm": 0.8268933892250061,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.5281,
      "step": 79
    },
    {
      "epoch": 0.004607498704140989,
      "grad_norm": 0.8044147491455078,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.645,
      "step": 80
    },
    {
      "epoch": 0.0046650924379427515,
      "grad_norm": 0.7255849242210388,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.4818,
      "step": 81
    },
    {
      "epoch": 0.004722686171744514,
      "grad_norm": 0.9489415287971497,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.4306,
      "step": 82
    },
    {
      "epoch": 0.004780279905546277,
      "grad_norm": 0.8799511790275574,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.5471,
      "step": 83
    },
    {
      "epoch": 0.004837873639348039,
      "grad_norm": 0.9726818203926086,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.4289,
      "step": 84
    },
    {
      "epoch": 0.0048954673731498016,
      "grad_norm": 0.7881313562393188,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.4266,
      "step": 85
    },
    {
      "epoch": 0.004953061106951564,
      "grad_norm": 0.9222921133041382,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6424,
      "step": 86
    },
    {
      "epoch": 0.005010654840753326,
      "grad_norm": 0.904137134552002,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.6367,
      "step": 87
    },
    {
      "epoch": 0.005068248574555088,
      "grad_norm": 0.9748932719230652,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.4309,
      "step": 88
    },
    {
      "epoch": 0.005125842308356851,
      "grad_norm": 0.8864166140556335,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.6286,
      "step": 89
    },
    {
      "epoch": 0.005183436042158613,
      "grad_norm": 0.9451360702514648,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.5607,
      "step": 90
    },
    {
      "epoch": 0.005241029775960375,
      "grad_norm": 0.924784243106842,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.5112,
      "step": 91
    },
    {
      "epoch": 0.005298623509762138,
      "grad_norm": 0.8883122205734253,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.4076,
      "step": 92
    },
    {
      "epoch": 0.0053562172435639,
      "grad_norm": 1.016377329826355,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.5929,
      "step": 93
    },
    {
      "epoch": 0.005413810977365663,
      "grad_norm": 1.010695457458496,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4111,
      "step": 94
    },
    {
      "epoch": 0.005471404711167425,
      "grad_norm": 1.0585623979568481,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.7093,
      "step": 95
    },
    {
      "epoch": 0.005528998444969188,
      "grad_norm": 0.9867178201675415,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.627,
      "step": 96
    },
    {
      "epoch": 0.00558659217877095,
      "grad_norm": 1.0128202438354492,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.7881,
      "step": 97
    },
    {
      "epoch": 0.005644185912572712,
      "grad_norm": 3.2039148807525635,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.6294,
      "step": 98
    },
    {
      "epoch": 0.0057017796463744745,
      "grad_norm": 1.3363120555877686,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.9821,
      "step": 99
    },
    {
      "epoch": 0.005759373380176237,
      "grad_norm": 2.1359691619873047,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.0078,
      "step": 100
    },
    {
      "epoch": 0.005759373380176237,
      "eval_loss": 2.563858985900879,
      "eval_runtime": 2234.0753,
      "eval_samples_per_second": 13.09,
      "eval_steps_per_second": 3.272,
      "step": 100
    },
    {
      "epoch": 0.005816967113977999,
      "grad_norm": 0.6629051566123962,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.3898,
      "step": 101
    },
    {
      "epoch": 0.005874560847779761,
      "grad_norm": 0.6988205909729004,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.5751,
      "step": 102
    },
    {
      "epoch": 0.005932154581581524,
      "grad_norm": 0.6619424819946289,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.5121,
      "step": 103
    },
    {
      "epoch": 0.005989748315383286,
      "grad_norm": 0.5685223937034607,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.4177,
      "step": 104
    },
    {
      "epoch": 0.006047342049185049,
      "grad_norm": 0.5902212262153625,
      "learning_rate": 5e-05,
      "loss": 2.5871,
      "step": 105
    },
    {
      "epoch": 0.006104935782986811,
      "grad_norm": 0.6995246410369873,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.6188,
      "step": 106
    },
    {
      "epoch": 0.006162529516788574,
      "grad_norm": 0.5604093670845032,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.6178,
      "step": 107
    },
    {
      "epoch": 0.006220123250590336,
      "grad_norm": 0.5511941909790039,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.4634,
      "step": 108
    },
    {
      "epoch": 0.006277716984392098,
      "grad_norm": 0.5805381536483765,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.2979,
      "step": 109
    },
    {
      "epoch": 0.0063353107181938605,
      "grad_norm": 0.5909259915351868,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.5077,
      "step": 110
    },
    {
      "epoch": 0.006392904451995623,
      "grad_norm": 0.5975538492202759,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.5591,
      "step": 111
    },
    {
      "epoch": 0.006450498185797385,
      "grad_norm": 0.6008089184761047,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.3155,
      "step": 112
    },
    {
      "epoch": 0.006508091919599147,
      "grad_norm": 0.5987680554389954,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.4527,
      "step": 113
    },
    {
      "epoch": 0.00656568565340091,
      "grad_norm": 0.6279982924461365,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.4053,
      "step": 114
    },
    {
      "epoch": 0.006623279387202672,
      "grad_norm": 0.6691924929618835,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.6205,
      "step": 115
    },
    {
      "epoch": 0.006680873121004435,
      "grad_norm": 0.6834997534751892,
      "learning_rate": 4.095597328339452e-05,
      "loss": 2.4693,
      "step": 116
    },
    {
      "epoch": 0.006738466854806197,
      "grad_norm": 0.8012089729309082,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.4526,
      "step": 117
    },
    {
      "epoch": 0.00679606058860796,
      "grad_norm": 0.6886681914329529,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.4285,
      "step": 118
    },
    {
      "epoch": 0.006853654322409722,
      "grad_norm": 0.6909232139587402,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.525,
      "step": 119
    },
    {
      "epoch": 0.006911248056211484,
      "grad_norm": 0.6752573251724243,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.5565,
      "step": 120
    },
    {
      "epoch": 0.006968841790013247,
      "grad_norm": 0.7299994230270386,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.5772,
      "step": 121
    },
    {
      "epoch": 0.007026435523815009,
      "grad_norm": 0.7452417016029358,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.5982,
      "step": 122
    },
    {
      "epoch": 0.007084029257616771,
      "grad_norm": 0.7477314472198486,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.5512,
      "step": 123
    },
    {
      "epoch": 0.0071416229914185335,
      "grad_norm": 0.7010685205459595,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.6239,
      "step": 124
    },
    {
      "epoch": 0.007199216725220296,
      "grad_norm": 0.8408722877502441,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.3303,
      "step": 125
    },
    {
      "epoch": 0.007256810459022058,
      "grad_norm": 0.7118111252784729,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.505,
      "step": 126
    },
    {
      "epoch": 0.007314404192823821,
      "grad_norm": 0.7402850985527039,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.4801,
      "step": 127
    },
    {
      "epoch": 0.0073719979266255835,
      "grad_norm": 0.839127779006958,
      "learning_rate": 3.144013755408895e-05,
      "loss": 2.4652,
      "step": 128
    },
    {
      "epoch": 0.007429591660427346,
      "grad_norm": 0.9870427846908569,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.496,
      "step": 129
    },
    {
      "epoch": 0.007487185394229108,
      "grad_norm": 0.7441486716270447,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.4219,
      "step": 130
    },
    {
      "epoch": 0.00754477912803087,
      "grad_norm": 0.7723474502563477,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.6824,
      "step": 131
    },
    {
      "epoch": 0.007602372861832633,
      "grad_norm": 0.7063377499580383,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.6526,
      "step": 132
    },
    {
      "epoch": 0.007659966595634395,
      "grad_norm": 0.9693397879600525,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.4893,
      "step": 133
    },
    {
      "epoch": 0.007717560329436157,
      "grad_norm": 0.7927699685096741,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.5255,
      "step": 134
    },
    {
      "epoch": 0.0077751540632379195,
      "grad_norm": 0.8411989212036133,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.3769,
      "step": 135
    },
    {
      "epoch": 0.007832747797039682,
      "grad_norm": 0.746304988861084,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.5229,
      "step": 136
    },
    {
      "epoch": 0.007890341530841444,
      "grad_norm": 0.7938131093978882,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.5797,
      "step": 137
    },
    {
      "epoch": 0.007947935264643206,
      "grad_norm": 0.8366580009460449,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.6705,
      "step": 138
    },
    {
      "epoch": 0.008005528998444969,
      "grad_norm": 0.8715227246284485,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.5942,
      "step": 139
    },
    {
      "epoch": 0.008063122732246731,
      "grad_norm": 0.804695725440979,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.4821,
      "step": 140
    },
    {
      "epoch": 0.008120716466048493,
      "grad_norm": 0.888326108455658,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.377,
      "step": 141
    },
    {
      "epoch": 0.008178310199850256,
      "grad_norm": 0.9786155223846436,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.6569,
      "step": 142
    },
    {
      "epoch": 0.008235903933652018,
      "grad_norm": 0.8907448053359985,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.5606,
      "step": 143
    },
    {
      "epoch": 0.008293497667453782,
      "grad_norm": 0.8716773390769958,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.6428,
      "step": 144
    },
    {
      "epoch": 0.008351091401255544,
      "grad_norm": 1.1320457458496094,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.7148,
      "step": 145
    },
    {
      "epoch": 0.008408685135057306,
      "grad_norm": 0.8441630601882935,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.6229,
      "step": 146
    },
    {
      "epoch": 0.008466278868859069,
      "grad_norm": 1.0586692094802856,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.8884,
      "step": 147
    },
    {
      "epoch": 0.008523872602660831,
      "grad_norm": 1.0624706745147705,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.826,
      "step": 148
    },
    {
      "epoch": 0.008581466336462593,
      "grad_norm": 1.1296426057815552,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.7406,
      "step": 149
    },
    {
      "epoch": 0.008639060070264356,
      "grad_norm": 1.3106721639633179,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.1303,
      "step": 150
    },
    {
      "epoch": 0.008639060070264356,
      "eval_loss": 2.525747537612915,
      "eval_runtime": 2233.9155,
      "eval_samples_per_second": 13.09,
      "eval_steps_per_second": 3.273,
      "step": 150
    },
    {
      "epoch": 0.008696653804066118,
      "grad_norm": 0.393518328666687,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.2137,
      "step": 151
    },
    {
      "epoch": 0.00875424753786788,
      "grad_norm": 0.48413583636283875,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.4272,
      "step": 152
    },
    {
      "epoch": 0.008811841271669642,
      "grad_norm": 0.524556040763855,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.4413,
      "step": 153
    },
    {
      "epoch": 0.008869435005471405,
      "grad_norm": 0.535805344581604,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.5207,
      "step": 154
    },
    {
      "epoch": 0.008927028739273167,
      "grad_norm": 0.614208996295929,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.5324,
      "step": 155
    },
    {
      "epoch": 0.00898462247307493,
      "grad_norm": 0.546839714050293,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.4983,
      "step": 156
    },
    {
      "epoch": 0.009042216206876692,
      "grad_norm": 0.7105114459991455,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 2.3348,
      "step": 157
    },
    {
      "epoch": 0.009099809940678454,
      "grad_norm": 0.5840356945991516,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.4984,
      "step": 158
    },
    {
      "epoch": 0.009157403674480216,
      "grad_norm": 0.5872077941894531,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.3904,
      "step": 159
    },
    {
      "epoch": 0.009214997408281978,
      "grad_norm": 0.5953437685966492,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.577,
      "step": 160
    },
    {
      "epoch": 0.00927259114208374,
      "grad_norm": 0.5791707634925842,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 2.388,
      "step": 161
    },
    {
      "epoch": 0.009330184875885503,
      "grad_norm": 0.5926764011383057,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.4526,
      "step": 162
    },
    {
      "epoch": 0.009387778609687265,
      "grad_norm": 0.6173063516616821,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.4749,
      "step": 163
    },
    {
      "epoch": 0.009445372343489028,
      "grad_norm": 0.7021114826202393,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.5927,
      "step": 164
    },
    {
      "epoch": 0.00950296607729079,
      "grad_norm": 0.6273760199546814,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.3481,
      "step": 165
    },
    {
      "epoch": 0.009560559811092554,
      "grad_norm": 0.6793805956840515,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.4615,
      "step": 166
    },
    {
      "epoch": 0.009618153544894316,
      "grad_norm": 0.6272901296615601,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.3848,
      "step": 167
    },
    {
      "epoch": 0.009675747278696079,
      "grad_norm": 0.5837368965148926,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.4603,
      "step": 168
    },
    {
      "epoch": 0.00973334101249784,
      "grad_norm": 0.7735977172851562,
      "learning_rate": 6.425787818636131e-06,
      "loss": 2.4649,
      "step": 169
    },
    {
      "epoch": 0.009790934746299603,
      "grad_norm": 0.6814642548561096,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.5238,
      "step": 170
    },
    {
      "epoch": 0.009848528480101365,
      "grad_norm": 0.6705578565597534,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.3928,
      "step": 171
    },
    {
      "epoch": 0.009906122213903128,
      "grad_norm": 0.7523506879806519,
      "learning_rate": 5.263533508961827e-06,
      "loss": 2.5566,
      "step": 172
    },
    {
      "epoch": 0.00996371594770489,
      "grad_norm": 0.7953758835792542,
      "learning_rate": 4.900438493352055e-06,
      "loss": 2.339,
      "step": 173
    },
    {
      "epoch": 0.010021309681506652,
      "grad_norm": 0.6759893298149109,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.329,
      "step": 174
    },
    {
      "epoch": 0.010078903415308415,
      "grad_norm": 0.731402575969696,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.4195,
      "step": 175
    },
    {
      "epoch": 0.010136497149110177,
      "grad_norm": 0.6653828024864197,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.5194,
      "step": 176
    },
    {
      "epoch": 0.01019409088291194,
      "grad_norm": 0.7519419193267822,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.4938,
      "step": 177
    },
    {
      "epoch": 0.010251684616713701,
      "grad_norm": 0.7557494640350342,
      "learning_rate": 3.271776770026963e-06,
      "loss": 2.5591,
      "step": 178
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.7547789812088013,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.3957,
      "step": 179
    },
    {
      "epoch": 0.010366872084317226,
      "grad_norm": 0.7685062885284424,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.4737,
      "step": 180
    },
    {
      "epoch": 0.010424465818118988,
      "grad_norm": 0.7940509915351868,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.566,
      "step": 181
    },
    {
      "epoch": 0.01048205955192075,
      "grad_norm": 0.777790367603302,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.4585,
      "step": 182
    },
    {
      "epoch": 0.010539653285722513,
      "grad_norm": 0.7970550060272217,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.6705,
      "step": 183
    },
    {
      "epoch": 0.010597247019524275,
      "grad_norm": 1.012671709060669,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.4849,
      "step": 184
    },
    {
      "epoch": 0.010654840753326037,
      "grad_norm": 0.8098058700561523,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.6971,
      "step": 185
    },
    {
      "epoch": 0.0107124344871278,
      "grad_norm": 0.7531903386116028,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.4498,
      "step": 186
    },
    {
      "epoch": 0.010770028220929562,
      "grad_norm": 0.8647445440292358,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.406,
      "step": 187
    },
    {
      "epoch": 0.010827621954731326,
      "grad_norm": 0.8539782762527466,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.4549,
      "step": 188
    },
    {
      "epoch": 0.010885215688533088,
      "grad_norm": 1.0440486669540405,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.4328,
      "step": 189
    },
    {
      "epoch": 0.01094280942233485,
      "grad_norm": 1.0142027139663696,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.5427,
      "step": 190
    },
    {
      "epoch": 0.011000403156136613,
      "grad_norm": 0.8213918805122375,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.5524,
      "step": 191
    },
    {
      "epoch": 0.011057996889938375,
      "grad_norm": 0.8356615900993347,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.4497,
      "step": 192
    },
    {
      "epoch": 0.011115590623740138,
      "grad_norm": 0.9210706353187561,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.5542,
      "step": 193
    },
    {
      "epoch": 0.0111731843575419,
      "grad_norm": 0.9797810316085815,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.5766,
      "step": 194
    },
    {
      "epoch": 0.011230778091343662,
      "grad_norm": 0.9915363192558289,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.5885,
      "step": 195
    },
    {
      "epoch": 0.011288371825145424,
      "grad_norm": 1.0298490524291992,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 2.5192,
      "step": 196
    },
    {
      "epoch": 0.011345965558947187,
      "grad_norm": 0.9702001810073853,
      "learning_rate": 6.150154258476315e-08,
      "loss": 2.7111,
      "step": 197
    },
    {
      "epoch": 0.011403559292748949,
      "grad_norm": 1.1697652339935303,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.6424,
      "step": 198
    },
    {
      "epoch": 0.011461153026550711,
      "grad_norm": 1.0527364015579224,
      "learning_rate": 6.834750376549792e-09,
      "loss": 2.6706,
      "step": 199
    },
    {
      "epoch": 0.011518746760352474,
      "grad_norm": 1.4649275541305542,
      "learning_rate": 0.0,
      "loss": 2.8974,
      "step": 200
    },
    {
      "epoch": 0.011518746760352474,
      "eval_loss": 2.518922805786133,
      "eval_runtime": 2235.683,
      "eval_samples_per_second": 13.08,
      "eval_steps_per_second": 3.27,
      "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": 3.028341009332306e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}