{
  "best_metric": 0.8106163144111633,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.5706134094151213,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028530670470756064,
      "grad_norm": 2.8206608295440674,
      "learning_rate": 1e-05,
      "loss": 2.7379,
      "step": 1
    },
    {
      "epoch": 0.0028530670470756064,
      "eval_loss": 4.149313926696777,
      "eval_runtime": 43.4302,
      "eval_samples_per_second": 13.585,
      "eval_steps_per_second": 3.408,
      "step": 1
    },
    {
      "epoch": 0.005706134094151213,
      "grad_norm": 3.6581132411956787,
      "learning_rate": 2e-05,
      "loss": 3.3691,
      "step": 2
    },
    {
      "epoch": 0.008559201141226819,
      "grad_norm": 3.8806488513946533,
      "learning_rate": 3e-05,
      "loss": 3.6022,
      "step": 3
    },
    {
      "epoch": 0.011412268188302425,
      "grad_norm": 4.019761085510254,
      "learning_rate": 4e-05,
      "loss": 3.646,
      "step": 4
    },
    {
      "epoch": 0.014265335235378032,
      "grad_norm": 3.4408085346221924,
      "learning_rate": 5e-05,
      "loss": 3.3077,
      "step": 5
    },
    {
      "epoch": 0.017118402282453638,
      "grad_norm": 3.2818191051483154,
      "learning_rate": 6e-05,
      "loss": 2.9734,
      "step": 6
    },
    {
      "epoch": 0.019971469329529243,
      "grad_norm": 2.9324183464050293,
      "learning_rate": 7e-05,
      "loss": 2.631,
      "step": 7
    },
    {
      "epoch": 0.02282453637660485,
      "grad_norm": 2.66923451423645,
      "learning_rate": 8e-05,
      "loss": 2.2061,
      "step": 8
    },
    {
      "epoch": 0.025677603423680456,
      "grad_norm": 2.870007038116455,
      "learning_rate": 9e-05,
      "loss": 1.8335,
      "step": 9
    },
    {
      "epoch": 0.028530670470756064,
      "grad_norm": 3.183505058288574,
      "learning_rate": 0.0001,
      "loss": 1.4807,
      "step": 10
    },
    {
      "epoch": 0.03138373751783167,
      "grad_norm": 3.2284963130950928,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4377,
      "step": 11
    },
    {
      "epoch": 0.034236804564907276,
      "grad_norm": 2.239410161972046,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3554,
      "step": 12
    },
    {
      "epoch": 0.037089871611982884,
      "grad_norm": 1.7223660945892334,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.2205,
      "step": 13
    },
    {
      "epoch": 0.039942938659058486,
      "grad_norm": 1.5697674751281738,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1455,
      "step": 14
    },
    {
      "epoch": 0.042796005706134094,
      "grad_norm": 1.2276450395584106,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1327,
      "step": 15
    },
    {
      "epoch": 0.0456490727532097,
      "grad_norm": 1.1973907947540283,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0617,
      "step": 16
    },
    {
      "epoch": 0.04850213980028531,
      "grad_norm": 1.3317774534225464,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9903,
      "step": 17
    },
    {
      "epoch": 0.05135520684736091,
      "grad_norm": 1.129556655883789,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9934,
      "step": 18
    },
    {
      "epoch": 0.05420827389443652,
      "grad_norm": 1.3102591037750244,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1285,
      "step": 19
    },
    {
      "epoch": 0.05706134094151213,
      "grad_norm": 1.1068060398101807,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9679,
      "step": 20
    },
    {
      "epoch": 0.05991440798858773,
      "grad_norm": 1.2037957906723022,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9852,
      "step": 21
    },
    {
      "epoch": 0.06276747503566334,
      "grad_norm": 1.0800535678863525,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0607,
      "step": 22
    },
    {
      "epoch": 0.06562054208273894,
      "grad_norm": 1.1186648607254028,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9884,
      "step": 23
    },
    {
      "epoch": 0.06847360912981455,
      "grad_norm": 0.9974199533462524,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9329,
      "step": 24
    },
    {
      "epoch": 0.07132667617689016,
      "grad_norm": 0.8157842755317688,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8843,
      "step": 25
    },
    {
      "epoch": 0.07417974322396577,
      "grad_norm": 0.8818031549453735,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9332,
      "step": 26
    },
    {
      "epoch": 0.07703281027104136,
      "grad_norm": 0.9537537693977356,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9615,
      "step": 27
    },
    {
      "epoch": 0.07988587731811697,
      "grad_norm": 0.8752272725105286,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9114,
      "step": 28
    },
    {
      "epoch": 0.08273894436519258,
      "grad_norm": 0.9026284217834473,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9529,
      "step": 29
    },
    {
      "epoch": 0.08559201141226819,
      "grad_norm": 0.8090780377388,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8805,
      "step": 30
    },
    {
      "epoch": 0.0884450784593438,
      "grad_norm": 0.8183196783065796,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.846,
      "step": 31
    },
    {
      "epoch": 0.0912981455064194,
      "grad_norm": 0.9700990915298462,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9721,
      "step": 32
    },
    {
      "epoch": 0.09415121255349501,
      "grad_norm": 0.8337361216545105,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9714,
      "step": 33
    },
    {
      "epoch": 0.09700427960057062,
      "grad_norm": 0.9228287935256958,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9185,
      "step": 34
    },
    {
      "epoch": 0.09985734664764621,
      "grad_norm": 0.7186618447303772,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8642,
      "step": 35
    },
    {
      "epoch": 0.10271041369472182,
      "grad_norm": 0.837884783744812,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8712,
      "step": 36
    },
    {
      "epoch": 0.10556348074179743,
      "grad_norm": 0.812001645565033,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8692,
      "step": 37
    },
    {
      "epoch": 0.10841654778887304,
      "grad_norm": 0.8492826223373413,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0114,
      "step": 38
    },
    {
      "epoch": 0.11126961483594865,
      "grad_norm": 0.8208444118499756,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9496,
      "step": 39
    },
    {
      "epoch": 0.11412268188302425,
      "grad_norm": 0.789992094039917,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9733,
      "step": 40
    },
    {
      "epoch": 0.11697574893009986,
      "grad_norm": 0.805285632610321,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8374,
      "step": 41
    },
    {
      "epoch": 0.11982881597717546,
      "grad_norm": 0.7742743492126465,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9841,
      "step": 42
    },
    {
      "epoch": 0.12268188302425106,
      "grad_norm": 0.7224770784378052,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8248,
      "step": 43
    },
    {
      "epoch": 0.12553495007132667,
      "grad_norm": 0.795933187007904,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9302,
      "step": 44
    },
    {
      "epoch": 0.12838801711840228,
      "grad_norm": 0.7371643781661987,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8446,
      "step": 45
    },
    {
      "epoch": 0.1312410841654779,
      "grad_norm": 0.8046213984489441,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9879,
      "step": 46
    },
    {
      "epoch": 0.1340941512125535,
      "grad_norm": 0.6577298641204834,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8729,
      "step": 47
    },
    {
      "epoch": 0.1369472182596291,
      "grad_norm": 0.7137817144393921,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9309,
      "step": 48
    },
    {
      "epoch": 0.1398002853067047,
      "grad_norm": 0.853975236415863,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9765,
      "step": 49
    },
    {
      "epoch": 0.14265335235378032,
      "grad_norm": 0.9340161681175232,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9603,
      "step": 50
    },
    {
      "epoch": 0.14265335235378032,
      "eval_loss": 0.9249671101570129,
      "eval_runtime": 44.1701,
      "eval_samples_per_second": 13.357,
      "eval_steps_per_second": 3.351,
      "step": 50
    },
    {
      "epoch": 0.14550641940085593,
      "grad_norm": 1.1661717891693115,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0809,
      "step": 51
    },
    {
      "epoch": 0.14835948644793154,
      "grad_norm": 0.8443463444709778,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8387,
      "step": 52
    },
    {
      "epoch": 0.15121255349500715,
      "grad_norm": 0.7115589380264282,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8515,
      "step": 53
    },
    {
      "epoch": 0.15406562054208273,
      "grad_norm": 0.7389591932296753,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8808,
      "step": 54
    },
    {
      "epoch": 0.15691868758915833,
      "grad_norm": 0.6824779510498047,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8899,
      "step": 55
    },
    {
      "epoch": 0.15977175463623394,
      "grad_norm": 0.7354793548583984,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7746,
      "step": 56
    },
    {
      "epoch": 0.16262482168330955,
      "grad_norm": 0.6750243306159973,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8867,
      "step": 57
    },
    {
      "epoch": 0.16547788873038516,
      "grad_norm": 0.6514561772346497,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8335,
      "step": 58
    },
    {
      "epoch": 0.16833095577746077,
      "grad_norm": 0.643688976764679,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9054,
      "step": 59
    },
    {
      "epoch": 0.17118402282453637,
      "grad_norm": 0.6959644556045532,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.787,
      "step": 60
    },
    {
      "epoch": 0.17403708987161198,
      "grad_norm": 0.6906078457832336,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9249,
      "step": 61
    },
    {
      "epoch": 0.1768901569186876,
      "grad_norm": 0.7009598612785339,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8613,
      "step": 62
    },
    {
      "epoch": 0.1797432239657632,
      "grad_norm": 0.659328818321228,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8546,
      "step": 63
    },
    {
      "epoch": 0.1825962910128388,
      "grad_norm": 0.6799964904785156,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8223,
      "step": 64
    },
    {
      "epoch": 0.18544935805991442,
      "grad_norm": 0.6839357614517212,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9005,
      "step": 65
    },
    {
      "epoch": 0.18830242510699002,
      "grad_norm": 0.8038961887359619,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8816,
      "step": 66
    },
    {
      "epoch": 0.19115549215406563,
      "grad_norm": 0.6944898366928101,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8705,
      "step": 67
    },
    {
      "epoch": 0.19400855920114124,
      "grad_norm": 0.5753250122070312,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.803,
      "step": 68
    },
    {
      "epoch": 0.19686162624821682,
      "grad_norm": 0.5940936207771301,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8499,
      "step": 69
    },
    {
      "epoch": 0.19971469329529243,
      "grad_norm": 0.6289452314376831,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8193,
      "step": 70
    },
    {
      "epoch": 0.20256776034236804,
      "grad_norm": 0.6901584267616272,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8862,
      "step": 71
    },
    {
      "epoch": 0.20542082738944364,
      "grad_norm": 0.5757665038108826,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7784,
      "step": 72
    },
    {
      "epoch": 0.20827389443651925,
      "grad_norm": 0.6261290907859802,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8328,
      "step": 73
    },
    {
      "epoch": 0.21112696148359486,
      "grad_norm": 0.5607548952102661,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8451,
      "step": 74
    },
    {
      "epoch": 0.21398002853067047,
      "grad_norm": 0.6211503148078918,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8332,
      "step": 75
    },
    {
      "epoch": 0.21683309557774608,
      "grad_norm": 0.6851415038108826,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8162,
      "step": 76
    },
    {
      "epoch": 0.21968616262482168,
      "grad_norm": 0.6376487612724304,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8454,
      "step": 77
    },
    {
      "epoch": 0.2225392296718973,
      "grad_norm": 0.5932267904281616,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8648,
      "step": 78
    },
    {
      "epoch": 0.2253922967189729,
      "grad_norm": 0.561345636844635,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8219,
      "step": 79
    },
    {
      "epoch": 0.2282453637660485,
      "grad_norm": 0.6728673577308655,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8943,
      "step": 80
    },
    {
      "epoch": 0.23109843081312412,
      "grad_norm": 0.6630651950836182,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9114,
      "step": 81
    },
    {
      "epoch": 0.23395149786019973,
      "grad_norm": 0.5759665966033936,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8647,
      "step": 82
    },
    {
      "epoch": 0.23680456490727533,
      "grad_norm": 0.6728373169898987,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9246,
      "step": 83
    },
    {
      "epoch": 0.2396576319543509,
      "grad_norm": 0.6087666749954224,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8902,
      "step": 84
    },
    {
      "epoch": 0.24251069900142652,
      "grad_norm": 0.6265033483505249,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8392,
      "step": 85
    },
    {
      "epoch": 0.24536376604850213,
      "grad_norm": 0.6346978545188904,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8818,
      "step": 86
    },
    {
      "epoch": 0.24821683309557774,
      "grad_norm": 0.6025899052619934,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8599,
      "step": 87
    },
    {
      "epoch": 0.25106990014265335,
      "grad_norm": 0.6798688173294067,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.911,
      "step": 88
    },
    {
      "epoch": 0.25392296718972895,
      "grad_norm": 0.7372167110443115,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8818,
      "step": 89
    },
    {
      "epoch": 0.25677603423680456,
      "grad_norm": 0.5854942202568054,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8399,
      "step": 90
    },
    {
      "epoch": 0.25962910128388017,
      "grad_norm": 0.5913036465644836,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8468,
      "step": 91
    },
    {
      "epoch": 0.2624821683309558,
      "grad_norm": 0.6685941815376282,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8783,
      "step": 92
    },
    {
      "epoch": 0.2653352353780314,
      "grad_norm": 0.6349655389785767,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8571,
      "step": 93
    },
    {
      "epoch": 0.268188302425107,
      "grad_norm": 0.64983069896698,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9095,
      "step": 94
    },
    {
      "epoch": 0.2710413694721826,
      "grad_norm": 0.6685841083526611,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9156,
      "step": 95
    },
    {
      "epoch": 0.2738944365192582,
      "grad_norm": 0.5913763046264648,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8178,
      "step": 96
    },
    {
      "epoch": 0.2767475035663338,
      "grad_norm": 0.6005918979644775,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8983,
      "step": 97
    },
    {
      "epoch": 0.2796005706134094,
      "grad_norm": 0.7201871871948242,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.86,
      "step": 98
    },
    {
      "epoch": 0.28245363766048504,
      "grad_norm": 0.664374828338623,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.8672,
      "step": 99
    },
    {
      "epoch": 0.28530670470756064,
      "grad_norm": 0.7693825960159302,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9811,
      "step": 100
    },
    {
      "epoch": 0.28530670470756064,
      "eval_loss": 0.8536361455917358,
      "eval_runtime": 44.1608,
      "eval_samples_per_second": 13.36,
      "eval_steps_per_second": 3.351,
      "step": 100
    },
    {
      "epoch": 0.28815977175463625,
      "grad_norm": 0.6372659802436829,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9242,
      "step": 101
    },
    {
      "epoch": 0.29101283880171186,
      "grad_norm": 0.5737109184265137,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8144,
      "step": 102
    },
    {
      "epoch": 0.29386590584878747,
      "grad_norm": 0.5579484105110168,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8182,
      "step": 103
    },
    {
      "epoch": 0.2967189728958631,
      "grad_norm": 0.568458616733551,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8433,
      "step": 104
    },
    {
      "epoch": 0.2995720399429387,
      "grad_norm": 0.5116366147994995,
      "learning_rate": 5e-05,
      "loss": 0.7758,
      "step": 105
    },
    {
      "epoch": 0.3024251069900143,
      "grad_norm": 0.5226439237594604,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7562,
      "step": 106
    },
    {
      "epoch": 0.30527817403708984,
      "grad_norm": 0.49772965908050537,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7731,
      "step": 107
    },
    {
      "epoch": 0.30813124108416545,
      "grad_norm": 0.5513703227043152,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7431,
      "step": 108
    },
    {
      "epoch": 0.31098430813124106,
      "grad_norm": 0.5564998388290405,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7916,
      "step": 109
    },
    {
      "epoch": 0.31383737517831667,
      "grad_norm": 0.5604222416877747,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7938,
      "step": 110
    },
    {
      "epoch": 0.3166904422253923,
      "grad_norm": 0.48893120884895325,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7092,
      "step": 111
    },
    {
      "epoch": 0.3195435092724679,
      "grad_norm": 0.5532459020614624,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7602,
      "step": 112
    },
    {
      "epoch": 0.3223965763195435,
      "grad_norm": 0.5639341473579407,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8138,
      "step": 113
    },
    {
      "epoch": 0.3252496433666191,
      "grad_norm": 0.5560553669929504,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7551,
      "step": 114
    },
    {
      "epoch": 0.3281027104136947,
      "grad_norm": 0.5836735963821411,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7906,
      "step": 115
    },
    {
      "epoch": 0.3309557774607703,
      "grad_norm": 0.5324416756629944,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.773,
      "step": 116
    },
    {
      "epoch": 0.3338088445078459,
      "grad_norm": 0.5423099398612976,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7556,
      "step": 117
    },
    {
      "epoch": 0.33666191155492153,
      "grad_norm": 0.5241405367851257,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7773,
      "step": 118
    },
    {
      "epoch": 0.33951497860199714,
      "grad_norm": 0.557428240776062,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7699,
      "step": 119
    },
    {
      "epoch": 0.34236804564907275,
      "grad_norm": 0.5748732686042786,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8508,
      "step": 120
    },
    {
      "epoch": 0.34522111269614836,
      "grad_norm": 0.5305575728416443,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7178,
      "step": 121
    },
    {
      "epoch": 0.34807417974322397,
      "grad_norm": 0.5929769277572632,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7837,
      "step": 122
    },
    {
      "epoch": 0.3509272467902996,
      "grad_norm": 0.5834765434265137,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8526,
      "step": 123
    },
    {
      "epoch": 0.3537803138373752,
      "grad_norm": 0.5835703611373901,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7617,
      "step": 124
    },
    {
      "epoch": 0.3566333808844508,
      "grad_norm": 0.5153204798698425,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7819,
      "step": 125
    },
    {
      "epoch": 0.3594864479315264,
      "grad_norm": 0.5779784321784973,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.77,
      "step": 126
    },
    {
      "epoch": 0.362339514978602,
      "grad_norm": 0.558480441570282,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8116,
      "step": 127
    },
    {
      "epoch": 0.3651925820256776,
      "grad_norm": 0.5660077929496765,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8643,
      "step": 128
    },
    {
      "epoch": 0.3680456490727532,
      "grad_norm": 0.5619089007377625,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8233,
      "step": 129
    },
    {
      "epoch": 0.37089871611982883,
      "grad_norm": 0.6005686521530151,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.9129,
      "step": 130
    },
    {
      "epoch": 0.37375178316690444,
      "grad_norm": 0.5624315142631531,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8375,
      "step": 131
    },
    {
      "epoch": 0.37660485021398005,
      "grad_norm": 0.5434154272079468,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7463,
      "step": 132
    },
    {
      "epoch": 0.37945791726105566,
      "grad_norm": 0.572571337223053,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8205,
      "step": 133
    },
    {
      "epoch": 0.38231098430813126,
      "grad_norm": 0.5621212720870972,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8013,
      "step": 134
    },
    {
      "epoch": 0.38516405135520687,
      "grad_norm": 0.6352572441101074,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8555,
      "step": 135
    },
    {
      "epoch": 0.3880171184022825,
      "grad_norm": 0.5184199213981628,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8288,
      "step": 136
    },
    {
      "epoch": 0.3908701854493581,
      "grad_norm": 0.5439362525939941,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8105,
      "step": 137
    },
    {
      "epoch": 0.39372325249643364,
      "grad_norm": 0.5452216863632202,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7665,
      "step": 138
    },
    {
      "epoch": 0.39657631954350925,
      "grad_norm": 0.6083769202232361,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.917,
      "step": 139
    },
    {
      "epoch": 0.39942938659058486,
      "grad_norm": 0.5530957579612732,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8073,
      "step": 140
    },
    {
      "epoch": 0.40228245363766046,
      "grad_norm": 0.5009734034538269,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7821,
      "step": 141
    },
    {
      "epoch": 0.4051355206847361,
      "grad_norm": 0.59010910987854,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8469,
      "step": 142
    },
    {
      "epoch": 0.4079885877318117,
      "grad_norm": 0.5742310285568237,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8457,
      "step": 143
    },
    {
      "epoch": 0.4108416547788873,
      "grad_norm": 0.5146201848983765,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7676,
      "step": 144
    },
    {
      "epoch": 0.4136947218259629,
      "grad_norm": 0.5184577703475952,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7556,
      "step": 145
    },
    {
      "epoch": 0.4165477888730385,
      "grad_norm": 0.5953947305679321,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8611,
      "step": 146
    },
    {
      "epoch": 0.4194008559201141,
      "grad_norm": 0.6210939884185791,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9244,
      "step": 147
    },
    {
      "epoch": 0.4222539229671897,
      "grad_norm": 0.6574196219444275,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9008,
      "step": 148
    },
    {
      "epoch": 0.42510699001426533,
      "grad_norm": 0.6447862386703491,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.7754,
      "step": 149
    },
    {
      "epoch": 0.42796005706134094,
      "grad_norm": 0.7485756278038025,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.0092,
      "step": 150
    },
    {
      "epoch": 0.42796005706134094,
      "eval_loss": 0.8171741962432861,
      "eval_runtime": 44.1497,
      "eval_samples_per_second": 13.364,
      "eval_steps_per_second": 3.352,
      "step": 150
    },
    {
      "epoch": 0.43081312410841655,
      "grad_norm": 0.5700702667236328,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9303,
      "step": 151
    },
    {
      "epoch": 0.43366619115549215,
      "grad_norm": 0.575224757194519,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7833,
      "step": 152
    },
    {
      "epoch": 0.43651925820256776,
      "grad_norm": 0.5173659920692444,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7368,
      "step": 153
    },
    {
      "epoch": 0.43937232524964337,
      "grad_norm": 0.5536710023880005,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7566,
      "step": 154
    },
    {
      "epoch": 0.442225392296719,
      "grad_norm": 0.5315050482749939,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7811,
      "step": 155
    },
    {
      "epoch": 0.4450784593437946,
      "grad_norm": 0.48669135570526123,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7595,
      "step": 156
    },
    {
      "epoch": 0.4479315263908702,
      "grad_norm": 0.4830872416496277,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7647,
      "step": 157
    },
    {
      "epoch": 0.4507845934379458,
      "grad_norm": 0.46836602687835693,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7413,
      "step": 158
    },
    {
      "epoch": 0.4536376604850214,
      "grad_norm": 0.5494118332862854,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7709,
      "step": 159
    },
    {
      "epoch": 0.456490727532097,
      "grad_norm": 0.5451878905296326,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7237,
      "step": 160
    },
    {
      "epoch": 0.4593437945791726,
      "grad_norm": 0.5122568011283875,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7954,
      "step": 161
    },
    {
      "epoch": 0.46219686162624823,
      "grad_norm": 0.5174070000648499,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8143,
      "step": 162
    },
    {
      "epoch": 0.46504992867332384,
      "grad_norm": 0.5335931777954102,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8442,
      "step": 163
    },
    {
      "epoch": 0.46790299572039945,
      "grad_norm": 0.5346239805221558,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.749,
      "step": 164
    },
    {
      "epoch": 0.47075606276747506,
      "grad_norm": 0.48148801922798157,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7459,
      "step": 165
    },
    {
      "epoch": 0.47360912981455067,
      "grad_norm": 0.4737273156642914,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7159,
      "step": 166
    },
    {
      "epoch": 0.4764621968616263,
      "grad_norm": 0.5133868455886841,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7445,
      "step": 167
    },
    {
      "epoch": 0.4793152639087018,
      "grad_norm": 0.49175402522087097,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7474,
      "step": 168
    },
    {
      "epoch": 0.48216833095577744,
      "grad_norm": 0.5137914419174194,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7677,
      "step": 169
    },
    {
      "epoch": 0.48502139800285304,
      "grad_norm": 0.5042280554771423,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7493,
      "step": 170
    },
    {
      "epoch": 0.48787446504992865,
      "grad_norm": 0.49010539054870605,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7746,
      "step": 171
    },
    {
      "epoch": 0.49072753209700426,
      "grad_norm": 0.53193199634552,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7909,
      "step": 172
    },
    {
      "epoch": 0.49358059914407987,
      "grad_norm": 0.4820551872253418,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7281,
      "step": 173
    },
    {
      "epoch": 0.4964336661911555,
      "grad_norm": 0.5256730318069458,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.742,
      "step": 174
    },
    {
      "epoch": 0.4992867332382311,
      "grad_norm": 0.560324490070343,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8516,
      "step": 175
    },
    {
      "epoch": 0.5021398002853067,
      "grad_norm": 0.5003674030303955,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7528,
      "step": 176
    },
    {
      "epoch": 0.5049928673323824,
      "grad_norm": 0.5666238069534302,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.8352,
      "step": 177
    },
    {
      "epoch": 0.5078459343794579,
      "grad_norm": 0.5036215782165527,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7726,
      "step": 178
    },
    {
      "epoch": 0.5106990014265336,
      "grad_norm": 0.546686589717865,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8265,
      "step": 179
    },
    {
      "epoch": 0.5135520684736091,
      "grad_norm": 0.5211116075515747,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.78,
      "step": 180
    },
    {
      "epoch": 0.5164051355206848,
      "grad_norm": 0.4995884597301483,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7503,
      "step": 181
    },
    {
      "epoch": 0.5192582025677603,
      "grad_norm": 0.5615956783294678,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.724,
      "step": 182
    },
    {
      "epoch": 0.5221112696148359,
      "grad_norm": 0.5525692701339722,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7672,
      "step": 183
    },
    {
      "epoch": 0.5249643366619116,
      "grad_norm": 0.5694366693496704,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7983,
      "step": 184
    },
    {
      "epoch": 0.5278174037089871,
      "grad_norm": 0.60936439037323,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8689,
      "step": 185
    },
    {
      "epoch": 0.5306704707560628,
      "grad_norm": 0.5191695094108582,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.766,
      "step": 186
    },
    {
      "epoch": 0.5335235378031383,
      "grad_norm": 0.5712020397186279,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8133,
      "step": 187
    },
    {
      "epoch": 0.536376604850214,
      "grad_norm": 0.5859020948410034,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8284,
      "step": 188
    },
    {
      "epoch": 0.5392296718972895,
      "grad_norm": 0.5594853162765503,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8554,
      "step": 189
    },
    {
      "epoch": 0.5420827389443652,
      "grad_norm": 0.5850356817245483,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8202,
      "step": 190
    },
    {
      "epoch": 0.5449358059914408,
      "grad_norm": 0.589401125907898,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8693,
      "step": 191
    },
    {
      "epoch": 0.5477888730385164,
      "grad_norm": 0.5658154487609863,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8356,
      "step": 192
    },
    {
      "epoch": 0.550641940085592,
      "grad_norm": 0.5932813286781311,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8056,
      "step": 193
    },
    {
      "epoch": 0.5534950071326676,
      "grad_norm": 0.6718538403511047,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8202,
      "step": 194
    },
    {
      "epoch": 0.5563480741797432,
      "grad_norm": 0.6296520233154297,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8217,
      "step": 195
    },
    {
      "epoch": 0.5592011412268189,
      "grad_norm": 0.5864626169204712,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8572,
      "step": 196
    },
    {
      "epoch": 0.5620542082738944,
      "grad_norm": 0.6147605776786804,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8115,
      "step": 197
    },
    {
      "epoch": 0.5649072753209701,
      "grad_norm": 0.7953529357910156,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9369,
      "step": 198
    },
    {
      "epoch": 0.5677603423680456,
      "grad_norm": 0.6609671711921692,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.8994,
      "step": 199
    },
    {
      "epoch": 0.5706134094151213,
      "grad_norm": 0.8376245498657227,
      "learning_rate": 0.0,
      "loss": 0.9733,
      "step": 200
    },
    {
      "epoch": 0.5706134094151213,
      "eval_loss": 0.8106163144111633,
      "eval_runtime": 44.1677,
      "eval_samples_per_second": 13.358,
      "eval_steps_per_second": 3.351,
      "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": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}