{
  "best_metric": 0.8280358910560608,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.04315925766076824,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021579628830384117,
      "grad_norm": 2.413191556930542,
      "learning_rate": 1e-05,
      "loss": 1.0834,
      "step": 1
    },
    {
      "epoch": 0.00021579628830384117,
      "eval_loss": 1.0655946731567383,
      "eval_runtime": 675.3752,
      "eval_samples_per_second": 11.557,
      "eval_steps_per_second": 2.89,
      "step": 1
    },
    {
      "epoch": 0.00043159257660768235,
      "grad_norm": 2.4777073860168457,
      "learning_rate": 2e-05,
      "loss": 1.1134,
      "step": 2
    },
    {
      "epoch": 0.0006473888649115235,
      "grad_norm": 1.5793029069900513,
      "learning_rate": 3e-05,
      "loss": 1.0815,
      "step": 3
    },
    {
      "epoch": 0.0008631851532153647,
      "grad_norm": 1.4530420303344727,
      "learning_rate": 4e-05,
      "loss": 1.1684,
      "step": 4
    },
    {
      "epoch": 0.0010789814415192059,
      "grad_norm": 1.279815673828125,
      "learning_rate": 5e-05,
      "loss": 1.2493,
      "step": 5
    },
    {
      "epoch": 0.001294777729823047,
      "grad_norm": 1.3437328338623047,
      "learning_rate": 6e-05,
      "loss": 1.191,
      "step": 6
    },
    {
      "epoch": 0.0015105740181268882,
      "grad_norm": 1.1805121898651123,
      "learning_rate": 7e-05,
      "loss": 1.019,
      "step": 7
    },
    {
      "epoch": 0.0017263703064307294,
      "grad_norm": 1.2242250442504883,
      "learning_rate": 8e-05,
      "loss": 1.1173,
      "step": 8
    },
    {
      "epoch": 0.0019421665947345706,
      "grad_norm": 1.3150091171264648,
      "learning_rate": 9e-05,
      "loss": 1.1945,
      "step": 9
    },
    {
      "epoch": 0.0021579628830384117,
      "grad_norm": 1.6808185577392578,
      "learning_rate": 0.0001,
      "loss": 1.2729,
      "step": 10
    },
    {
      "epoch": 0.002373759171342253,
      "grad_norm": 1.3021870851516724,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9925,
      "step": 11
    },
    {
      "epoch": 0.002589555459646094,
      "grad_norm": 1.298538327217102,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0451,
      "step": 12
    },
    {
      "epoch": 0.0028053517479499353,
      "grad_norm": 1.1121331453323364,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8971,
      "step": 13
    },
    {
      "epoch": 0.0030211480362537764,
      "grad_norm": 1.0668638944625854,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8683,
      "step": 14
    },
    {
      "epoch": 0.0032369443245576176,
      "grad_norm": 1.093513011932373,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9857,
      "step": 15
    },
    {
      "epoch": 0.0034527406128614588,
      "grad_norm": 1.0205276012420654,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.832,
      "step": 16
    },
    {
      "epoch": 0.0036685369011653,
      "grad_norm": 0.9722862243652344,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.848,
      "step": 17
    },
    {
      "epoch": 0.003884333189469141,
      "grad_norm": 1.036147117614746,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8426,
      "step": 18
    },
    {
      "epoch": 0.004100129477772983,
      "grad_norm": 1.0807719230651855,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7855,
      "step": 19
    },
    {
      "epoch": 0.0043159257660768235,
      "grad_norm": 1.005210280418396,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8581,
      "step": 20
    },
    {
      "epoch": 0.004531722054380665,
      "grad_norm": 1.0059491395950317,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8392,
      "step": 21
    },
    {
      "epoch": 0.004747518342684506,
      "grad_norm": 0.9815653562545776,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7941,
      "step": 22
    },
    {
      "epoch": 0.004963314630988347,
      "grad_norm": 0.9933662414550781,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6769,
      "step": 23
    },
    {
      "epoch": 0.005179110919292188,
      "grad_norm": 1.2250510454177856,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7787,
      "step": 24
    },
    {
      "epoch": 0.00539490720759603,
      "grad_norm": 1.122271180152893,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8755,
      "step": 25
    },
    {
      "epoch": 0.0056107034958998705,
      "grad_norm": 1.0095186233520508,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6196,
      "step": 26
    },
    {
      "epoch": 0.005826499784203712,
      "grad_norm": 1.0971230268478394,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7523,
      "step": 27
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 0.943911612033844,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7192,
      "step": 28
    },
    {
      "epoch": 0.0062580923608113945,
      "grad_norm": 1.030330777168274,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6543,
      "step": 29
    },
    {
      "epoch": 0.006473888649115235,
      "grad_norm": 1.1400978565216064,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7854,
      "step": 30
    },
    {
      "epoch": 0.006689684937419077,
      "grad_norm": 1.099284291267395,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7065,
      "step": 31
    },
    {
      "epoch": 0.0069054812257229176,
      "grad_norm": 1.3802725076675415,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8292,
      "step": 32
    },
    {
      "epoch": 0.007121277514026759,
      "grad_norm": 1.4111284017562866,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7206,
      "step": 33
    },
    {
      "epoch": 0.0073370738023306,
      "grad_norm": 1.442323088645935,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.733,
      "step": 34
    },
    {
      "epoch": 0.0075528700906344415,
      "grad_norm": 1.4485353231430054,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9427,
      "step": 35
    },
    {
      "epoch": 0.007768666378938282,
      "grad_norm": 1.7094073295593262,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8843,
      "step": 36
    },
    {
      "epoch": 0.007984462667242124,
      "grad_norm": 1.7114619016647339,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8731,
      "step": 37
    },
    {
      "epoch": 0.008200258955545965,
      "grad_norm": 1.5875271558761597,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8692,
      "step": 38
    },
    {
      "epoch": 0.008416055243849805,
      "grad_norm": 1.5211230516433716,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7471,
      "step": 39
    },
    {
      "epoch": 0.008631851532153647,
      "grad_norm": 1.7656561136245728,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.812,
      "step": 40
    },
    {
      "epoch": 0.008847647820457489,
      "grad_norm": 2.0013887882232666,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8988,
      "step": 41
    },
    {
      "epoch": 0.00906344410876133,
      "grad_norm": 1.7183932065963745,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8773,
      "step": 42
    },
    {
      "epoch": 0.00927924039706517,
      "grad_norm": 1.8096790313720703,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7677,
      "step": 43
    },
    {
      "epoch": 0.009495036685369012,
      "grad_norm": 2.1633992195129395,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0052,
      "step": 44
    },
    {
      "epoch": 0.009710832973672853,
      "grad_norm": 2.079282283782959,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8494,
      "step": 45
    },
    {
      "epoch": 0.009926629261976695,
      "grad_norm": 2.253206253051758,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8745,
      "step": 46
    },
    {
      "epoch": 0.010142425550280535,
      "grad_norm": 2.5258116722106934,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7857,
      "step": 47
    },
    {
      "epoch": 0.010358221838584376,
      "grad_norm": 2.443507671356201,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6552,
      "step": 48
    },
    {
      "epoch": 0.010574018126888218,
      "grad_norm": 3.2455050945281982,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7939,
      "step": 49
    },
    {
      "epoch": 0.01078981441519206,
      "grad_norm": 3.454012632369995,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7532,
      "step": 50
    },
    {
      "epoch": 0.01078981441519206,
      "eval_loss": 0.9306937456130981,
      "eval_runtime": 678.5355,
      "eval_samples_per_second": 11.503,
      "eval_steps_per_second": 2.877,
      "step": 50
    },
    {
      "epoch": 0.0110056107034959,
      "grad_norm": 1.3545910120010376,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0495,
      "step": 51
    },
    {
      "epoch": 0.011221406991799741,
      "grad_norm": 1.7121601104736328,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1718,
      "step": 52
    },
    {
      "epoch": 0.011437203280103583,
      "grad_norm": 0.9250155687332153,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0514,
      "step": 53
    },
    {
      "epoch": 0.011652999568407424,
      "grad_norm": 0.8007225394248962,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.136,
      "step": 54
    },
    {
      "epoch": 0.011868795856711264,
      "grad_norm": 0.7891473174095154,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.0739,
      "step": 55
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 0.8593912720680237,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1275,
      "step": 56
    },
    {
      "epoch": 0.012300388433318947,
      "grad_norm": 0.8084666728973389,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.089,
      "step": 57
    },
    {
      "epoch": 0.012516184721622789,
      "grad_norm": 0.8374934196472168,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.0676,
      "step": 58
    },
    {
      "epoch": 0.012731981009926629,
      "grad_norm": 0.8531233668327332,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.976,
      "step": 59
    },
    {
      "epoch": 0.01294777729823047,
      "grad_norm": 1.1237266063690186,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9765,
      "step": 60
    },
    {
      "epoch": 0.013163573586534312,
      "grad_norm": 1.0431387424468994,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8075,
      "step": 61
    },
    {
      "epoch": 0.013379369874838154,
      "grad_norm": 0.8855105638504028,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7682,
      "step": 62
    },
    {
      "epoch": 0.013595166163141994,
      "grad_norm": 0.8714329600334167,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9432,
      "step": 63
    },
    {
      "epoch": 0.013810962451445835,
      "grad_norm": 0.9492474794387817,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8939,
      "step": 64
    },
    {
      "epoch": 0.014026758739749677,
      "grad_norm": 0.9305364489555359,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8649,
      "step": 65
    },
    {
      "epoch": 0.014242555028053518,
      "grad_norm": 0.8418351411819458,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9874,
      "step": 66
    },
    {
      "epoch": 0.014458351316357358,
      "grad_norm": 0.8882650136947632,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7991,
      "step": 67
    },
    {
      "epoch": 0.0146741476046612,
      "grad_norm": 0.8612756133079529,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8838,
      "step": 68
    },
    {
      "epoch": 0.014889943892965041,
      "grad_norm": 0.8121587038040161,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7883,
      "step": 69
    },
    {
      "epoch": 0.015105740181268883,
      "grad_norm": 0.7825753688812256,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6864,
      "step": 70
    },
    {
      "epoch": 0.015321536469572723,
      "grad_norm": 0.8124627470970154,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8094,
      "step": 71
    },
    {
      "epoch": 0.015537332757876565,
      "grad_norm": 0.861950695514679,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8263,
      "step": 72
    },
    {
      "epoch": 0.015753129046180404,
      "grad_norm": 0.86571204662323,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7727,
      "step": 73
    },
    {
      "epoch": 0.015968925334484248,
      "grad_norm": 0.9495205879211426,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8357,
      "step": 74
    },
    {
      "epoch": 0.016184721622788088,
      "grad_norm": 0.9630606174468994,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.797,
      "step": 75
    },
    {
      "epoch": 0.01640051791109193,
      "grad_norm": 1.0568230152130127,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7622,
      "step": 76
    },
    {
      "epoch": 0.01661631419939577,
      "grad_norm": 1.0038645267486572,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7112,
      "step": 77
    },
    {
      "epoch": 0.01683211048769961,
      "grad_norm": 1.1523643732070923,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8911,
      "step": 78
    },
    {
      "epoch": 0.017047906776003454,
      "grad_norm": 0.9733881950378418,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6935,
      "step": 79
    },
    {
      "epoch": 0.017263703064307294,
      "grad_norm": 1.147025465965271,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7109,
      "step": 80
    },
    {
      "epoch": 0.017479499352611134,
      "grad_norm": 1.0425084829330444,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7402,
      "step": 81
    },
    {
      "epoch": 0.017695295640914977,
      "grad_norm": 1.2669419050216675,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8334,
      "step": 82
    },
    {
      "epoch": 0.017911091929218817,
      "grad_norm": 1.0476404428482056,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6399,
      "step": 83
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 1.2373251914978027,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7233,
      "step": 84
    },
    {
      "epoch": 0.0183426845058265,
      "grad_norm": 1.4001257419586182,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8271,
      "step": 85
    },
    {
      "epoch": 0.01855848079413034,
      "grad_norm": 1.5242249965667725,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8391,
      "step": 86
    },
    {
      "epoch": 0.018774277082434183,
      "grad_norm": 1.8136906623840332,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.875,
      "step": 87
    },
    {
      "epoch": 0.018990073370738023,
      "grad_norm": 1.3434827327728271,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.801,
      "step": 88
    },
    {
      "epoch": 0.019205869659041863,
      "grad_norm": 1.4556819200515747,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8511,
      "step": 89
    },
    {
      "epoch": 0.019421665947345707,
      "grad_norm": 1.447807788848877,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7754,
      "step": 90
    },
    {
      "epoch": 0.019637462235649546,
      "grad_norm": 1.694348692893982,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8615,
      "step": 91
    },
    {
      "epoch": 0.01985325852395339,
      "grad_norm": 1.7129417657852173,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9201,
      "step": 92
    },
    {
      "epoch": 0.02006905481225723,
      "grad_norm": 1.9709275960922241,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9069,
      "step": 93
    },
    {
      "epoch": 0.02028485110056107,
      "grad_norm": 1.809097170829773,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.872,
      "step": 94
    },
    {
      "epoch": 0.020500647388864913,
      "grad_norm": 1.7297813892364502,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8408,
      "step": 95
    },
    {
      "epoch": 0.020716443677168753,
      "grad_norm": 2.2419145107269287,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7551,
      "step": 96
    },
    {
      "epoch": 0.020932239965472593,
      "grad_norm": 2.187922954559326,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.869,
      "step": 97
    },
    {
      "epoch": 0.021148036253776436,
      "grad_norm": 2.4042584896087646,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6992,
      "step": 98
    },
    {
      "epoch": 0.021363832542080276,
      "grad_norm": 2.500338077545166,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7114,
      "step": 99
    },
    {
      "epoch": 0.02157962883038412,
      "grad_norm": 2.6961820125579834,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.656,
      "step": 100
    },
    {
      "epoch": 0.02157962883038412,
      "eval_loss": 0.8603187203407288,
      "eval_runtime": 677.9248,
      "eval_samples_per_second": 11.513,
      "eval_steps_per_second": 2.879,
      "step": 100
    },
    {
      "epoch": 0.02179542511868796,
      "grad_norm": 1.1089110374450684,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.1093,
      "step": 101
    },
    {
      "epoch": 0.0220112214069918,
      "grad_norm": 1.106166124343872,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.0278,
      "step": 102
    },
    {
      "epoch": 0.022227017695295642,
      "grad_norm": 1.1203964948654175,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.0022,
      "step": 103
    },
    {
      "epoch": 0.022442813983599482,
      "grad_norm": 0.7232309579849243,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.092,
      "step": 104
    },
    {
      "epoch": 0.022658610271903322,
      "grad_norm": 0.7233337163925171,
      "learning_rate": 5e-05,
      "loss": 0.9655,
      "step": 105
    },
    {
      "epoch": 0.022874406560207165,
      "grad_norm": 0.8149043917655945,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.139,
      "step": 106
    },
    {
      "epoch": 0.023090202848511005,
      "grad_norm": 0.7843315601348877,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0493,
      "step": 107
    },
    {
      "epoch": 0.02330599913681485,
      "grad_norm": 0.7392372488975525,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.904,
      "step": 108
    },
    {
      "epoch": 0.02352179542511869,
      "grad_norm": 0.8629333972930908,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.0813,
      "step": 109
    },
    {
      "epoch": 0.023737591713422528,
      "grad_norm": 0.8519977331161499,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9022,
      "step": 110
    },
    {
      "epoch": 0.02395338800172637,
      "grad_norm": 0.8973418474197388,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.0171,
      "step": 111
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 1.1018964052200317,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8564,
      "step": 112
    },
    {
      "epoch": 0.02438498057833405,
      "grad_norm": 0.9234106540679932,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.0673,
      "step": 113
    },
    {
      "epoch": 0.024600776866637895,
      "grad_norm": 0.7985190153121948,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8832,
      "step": 114
    },
    {
      "epoch": 0.024816573154941735,
      "grad_norm": 0.8727723360061646,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9246,
      "step": 115
    },
    {
      "epoch": 0.025032369443245578,
      "grad_norm": 0.7970044612884521,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8867,
      "step": 116
    },
    {
      "epoch": 0.025248165731549418,
      "grad_norm": 0.8688997626304626,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9637,
      "step": 117
    },
    {
      "epoch": 0.025463962019853258,
      "grad_norm": 0.9784425497055054,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9145,
      "step": 118
    },
    {
      "epoch": 0.0256797583081571,
      "grad_norm": 0.8824965953826904,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9074,
      "step": 119
    },
    {
      "epoch": 0.02589555459646094,
      "grad_norm": 0.8492420315742493,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7582,
      "step": 120
    },
    {
      "epoch": 0.02611135088476478,
      "grad_norm": 0.8725212216377258,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7837,
      "step": 121
    },
    {
      "epoch": 0.026327147173068624,
      "grad_norm": 0.8608531355857849,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7997,
      "step": 122
    },
    {
      "epoch": 0.026542943461372464,
      "grad_norm": 0.8319887518882751,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8176,
      "step": 123
    },
    {
      "epoch": 0.026758739749676307,
      "grad_norm": 0.9366618990898132,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6593,
      "step": 124
    },
    {
      "epoch": 0.026974536037980147,
      "grad_norm": 0.852107048034668,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7941,
      "step": 125
    },
    {
      "epoch": 0.027190332326283987,
      "grad_norm": 0.9025298953056335,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8114,
      "step": 126
    },
    {
      "epoch": 0.02740612861458783,
      "grad_norm": 0.9413577318191528,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7405,
      "step": 127
    },
    {
      "epoch": 0.02762192490289167,
      "grad_norm": 0.9036081433296204,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7128,
      "step": 128
    },
    {
      "epoch": 0.02783772119119551,
      "grad_norm": 0.8255434036254883,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6682,
      "step": 129
    },
    {
      "epoch": 0.028053517479499353,
      "grad_norm": 0.9848359823226929,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7559,
      "step": 130
    },
    {
      "epoch": 0.028269313767803193,
      "grad_norm": 0.9902356863021851,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7821,
      "step": 131
    },
    {
      "epoch": 0.028485110056107037,
      "grad_norm": 1.054074764251709,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8453,
      "step": 132
    },
    {
      "epoch": 0.028700906344410877,
      "grad_norm": 1.061506986618042,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7477,
      "step": 133
    },
    {
      "epoch": 0.028916702632714716,
      "grad_norm": 1.0569781064987183,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8079,
      "step": 134
    },
    {
      "epoch": 0.02913249892101856,
      "grad_norm": 1.1609337329864502,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7927,
      "step": 135
    },
    {
      "epoch": 0.0293482952093224,
      "grad_norm": 1.181168794631958,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7241,
      "step": 136
    },
    {
      "epoch": 0.02956409149762624,
      "grad_norm": 1.619036316871643,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.776,
      "step": 137
    },
    {
      "epoch": 0.029779887785930083,
      "grad_norm": 1.331146001815796,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8912,
      "step": 138
    },
    {
      "epoch": 0.029995684074233923,
      "grad_norm": 1.4182469844818115,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8669,
      "step": 139
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 1.5601855516433716,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8814,
      "step": 140
    },
    {
      "epoch": 0.030427276650841606,
      "grad_norm": 1.6656060218811035,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7781,
      "step": 141
    },
    {
      "epoch": 0.030643072939145446,
      "grad_norm": 1.5459718704223633,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7903,
      "step": 142
    },
    {
      "epoch": 0.03085886922744929,
      "grad_norm": 1.5884653329849243,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7738,
      "step": 143
    },
    {
      "epoch": 0.03107466551575313,
      "grad_norm": 1.749447226524353,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6743,
      "step": 144
    },
    {
      "epoch": 0.03129046180405697,
      "grad_norm": 1.6413766145706177,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7247,
      "step": 145
    },
    {
      "epoch": 0.03150625809236081,
      "grad_norm": 2.0422089099884033,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7707,
      "step": 146
    },
    {
      "epoch": 0.03172205438066465,
      "grad_norm": 2.1430230140686035,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8553,
      "step": 147
    },
    {
      "epoch": 0.031937850668968495,
      "grad_norm": 2.3078126907348633,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7766,
      "step": 148
    },
    {
      "epoch": 0.03215364695727233,
      "grad_norm": 2.4988832473754883,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6228,
      "step": 149
    },
    {
      "epoch": 0.032369443245576175,
      "grad_norm": 2.9421193599700928,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7389,
      "step": 150
    },
    {
      "epoch": 0.032369443245576175,
      "eval_loss": 0.8280358910560608,
      "eval_runtime": 678.9937,
      "eval_samples_per_second": 11.495,
      "eval_steps_per_second": 2.875,
      "step": 150
    },
    {
      "epoch": 0.03258523953388002,
      "grad_norm": 0.872905433177948,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9125,
      "step": 151
    },
    {
      "epoch": 0.03280103582218386,
      "grad_norm": 1.1274447441101074,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.2306,
      "step": 152
    },
    {
      "epoch": 0.0330168321104877,
      "grad_norm": 1.0097324848175049,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8715,
      "step": 153
    },
    {
      "epoch": 0.03323262839879154,
      "grad_norm": 0.7326030135154724,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.1397,
      "step": 154
    },
    {
      "epoch": 0.033448424687095385,
      "grad_norm": 0.6830773949623108,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.1135,
      "step": 155
    },
    {
      "epoch": 0.03366422097539922,
      "grad_norm": 0.6737636923789978,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.0113,
      "step": 156
    },
    {
      "epoch": 0.033880017263703065,
      "grad_norm": 0.7146831154823303,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.0513,
      "step": 157
    },
    {
      "epoch": 0.03409581355200691,
      "grad_norm": 0.8453826904296875,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0005,
      "step": 158
    },
    {
      "epoch": 0.034311609840310744,
      "grad_norm": 0.7282570600509644,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.1542,
      "step": 159
    },
    {
      "epoch": 0.03452740612861459,
      "grad_norm": 0.9833396673202515,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.8986,
      "step": 160
    },
    {
      "epoch": 0.03474320241691843,
      "grad_norm": 1.014146089553833,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.0759,
      "step": 161
    },
    {
      "epoch": 0.03495899870522227,
      "grad_norm": 0.9076318740844727,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.814,
      "step": 162
    },
    {
      "epoch": 0.03517479499352611,
      "grad_norm": 1.0671011209487915,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8264,
      "step": 163
    },
    {
      "epoch": 0.035390591281829954,
      "grad_norm": 0.7813157439231873,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8726,
      "step": 164
    },
    {
      "epoch": 0.03560638757013379,
      "grad_norm": 0.9080982804298401,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.889,
      "step": 165
    },
    {
      "epoch": 0.035822183858437634,
      "grad_norm": 0.7913566827774048,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.9313,
      "step": 166
    },
    {
      "epoch": 0.03603798014674148,
      "grad_norm": 0.8537078499794006,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.872,
      "step": 167
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 0.9215819835662842,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.9565,
      "step": 168
    },
    {
      "epoch": 0.03646957272334916,
      "grad_norm": 0.7894816994667053,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8151,
      "step": 169
    },
    {
      "epoch": 0.036685369011653,
      "grad_norm": 0.8004231452941895,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7782,
      "step": 170
    },
    {
      "epoch": 0.036901165299956844,
      "grad_norm": 0.8006337881088257,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8399,
      "step": 171
    },
    {
      "epoch": 0.03711696158826068,
      "grad_norm": 0.7936356663703918,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7826,
      "step": 172
    },
    {
      "epoch": 0.037332757876564523,
      "grad_norm": 0.7953746914863586,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8984,
      "step": 173
    },
    {
      "epoch": 0.03754855416486837,
      "grad_norm": 0.8479154109954834,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6613,
      "step": 174
    },
    {
      "epoch": 0.0377643504531722,
      "grad_norm": 0.8638105392456055,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6928,
      "step": 175
    },
    {
      "epoch": 0.03798014674147605,
      "grad_norm": 0.9321827292442322,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7812,
      "step": 176
    },
    {
      "epoch": 0.03819594302977989,
      "grad_norm": 0.9451383352279663,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7636,
      "step": 177
    },
    {
      "epoch": 0.038411739318083726,
      "grad_norm": 1.1278488636016846,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8585,
      "step": 178
    },
    {
      "epoch": 0.03862753560638757,
      "grad_norm": 0.8583645224571228,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6058,
      "step": 179
    },
    {
      "epoch": 0.03884333189469141,
      "grad_norm": 0.9494765400886536,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6473,
      "step": 180
    },
    {
      "epoch": 0.03905912818299525,
      "grad_norm": 1.228299856185913,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7063,
      "step": 181
    },
    {
      "epoch": 0.03927492447129909,
      "grad_norm": 1.077574610710144,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.803,
      "step": 182
    },
    {
      "epoch": 0.039490720759602936,
      "grad_norm": 1.0873143672943115,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8002,
      "step": 183
    },
    {
      "epoch": 0.03970651704790678,
      "grad_norm": 1.1991524696350098,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7931,
      "step": 184
    },
    {
      "epoch": 0.039922313336210616,
      "grad_norm": 1.448101282119751,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7619,
      "step": 185
    },
    {
      "epoch": 0.04013810962451446,
      "grad_norm": 1.290709137916565,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8084,
      "step": 186
    },
    {
      "epoch": 0.0403539059128183,
      "grad_norm": 1.2573972940444946,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8117,
      "step": 187
    },
    {
      "epoch": 0.04056970220112214,
      "grad_norm": 1.458040475845337,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8218,
      "step": 188
    },
    {
      "epoch": 0.04078549848942598,
      "grad_norm": 1.4004535675048828,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7575,
      "step": 189
    },
    {
      "epoch": 0.041001294777729826,
      "grad_norm": 1.459489345550537,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7617,
      "step": 190
    },
    {
      "epoch": 0.04121709106603366,
      "grad_norm": 1.553012490272522,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.853,
      "step": 191
    },
    {
      "epoch": 0.041432887354337505,
      "grad_norm": 1.4750031232833862,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7688,
      "step": 192
    },
    {
      "epoch": 0.04164868364264135,
      "grad_norm": 1.6668219566345215,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7247,
      "step": 193
    },
    {
      "epoch": 0.041864479930945185,
      "grad_norm": 1.733577013015747,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8201,
      "step": 194
    },
    {
      "epoch": 0.04208027621924903,
      "grad_norm": 1.9310966730117798,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7765,
      "step": 195
    },
    {
      "epoch": 0.04229607250755287,
      "grad_norm": 1.6865826845169067,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7173,
      "step": 196
    },
    {
      "epoch": 0.04251186879585671,
      "grad_norm": 1.9995197057724,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6808,
      "step": 197
    },
    {
      "epoch": 0.04272766508416055,
      "grad_norm": 2.344564437866211,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7213,
      "step": 198
    },
    {
      "epoch": 0.042943461372464395,
      "grad_norm": 2.1751935482025146,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5671,
      "step": 199
    },
    {
      "epoch": 0.04315925766076824,
      "grad_norm": 4.66714334487915,
      "learning_rate": 0.0,
      "loss": 0.7308,
      "step": 200
    },
    {
      "epoch": 0.04315925766076824,
      "eval_loss": 0.8280848264694214,
      "eval_runtime": 679.4945,
      "eval_samples_per_second": 11.486,
      "eval_steps_per_second": 2.873,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.081074662755533e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}