{
  "best_metric": 0.49369120597839355,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.033716862645930795,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000168584313229654,
      "grad_norm": 0.8446885943412781,
      "learning_rate": 1e-05,
      "loss": 2.4589,
      "step": 1
    },
    {
      "epoch": 0.000168584313229654,
      "eval_loss": 0.733188807964325,
      "eval_runtime": 501.3377,
      "eval_samples_per_second": 19.927,
      "eval_steps_per_second": 4.983,
      "step": 1
    },
    {
      "epoch": 0.000337168626459308,
      "grad_norm": 1.128057599067688,
      "learning_rate": 2e-05,
      "loss": 2.4424,
      "step": 2
    },
    {
      "epoch": 0.0005057529396889619,
      "grad_norm": 1.060372233390808,
      "learning_rate": 3e-05,
      "loss": 2.4162,
      "step": 3
    },
    {
      "epoch": 0.000674337252918616,
      "grad_norm": 1.0101962089538574,
      "learning_rate": 4e-05,
      "loss": 2.5502,
      "step": 4
    },
    {
      "epoch": 0.0008429215661482699,
      "grad_norm": 0.8344566822052002,
      "learning_rate": 5e-05,
      "loss": 2.4003,
      "step": 5
    },
    {
      "epoch": 0.0010115058793779238,
      "grad_norm": 0.686334490776062,
      "learning_rate": 6e-05,
      "loss": 2.3091,
      "step": 6
    },
    {
      "epoch": 0.0011800901926075778,
      "grad_norm": 0.6290477514266968,
      "learning_rate": 7e-05,
      "loss": 2.5455,
      "step": 7
    },
    {
      "epoch": 0.001348674505837232,
      "grad_norm": 0.8258002996444702,
      "learning_rate": 8e-05,
      "loss": 2.2644,
      "step": 8
    },
    {
      "epoch": 0.0015172588190668858,
      "grad_norm": 0.8897196054458618,
      "learning_rate": 9e-05,
      "loss": 2.3285,
      "step": 9
    },
    {
      "epoch": 0.0016858431322965398,
      "grad_norm": 0.755355179309845,
      "learning_rate": 0.0001,
      "loss": 2.3636,
      "step": 10
    },
    {
      "epoch": 0.0018544274455261937,
      "grad_norm": 0.8041962385177612,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.4549,
      "step": 11
    },
    {
      "epoch": 0.0020230117587558476,
      "grad_norm": 0.79832923412323,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.5006,
      "step": 12
    },
    {
      "epoch": 0.002191596071985502,
      "grad_norm": 0.6866098642349243,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.1726,
      "step": 13
    },
    {
      "epoch": 0.0023601803852151557,
      "grad_norm": 0.6489931344985962,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.3821,
      "step": 14
    },
    {
      "epoch": 0.0025287646984448096,
      "grad_norm": 0.6004131436347961,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3175,
      "step": 15
    },
    {
      "epoch": 0.002697349011674464,
      "grad_norm": 0.5578266382217407,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1954,
      "step": 16
    },
    {
      "epoch": 0.0028659333249041177,
      "grad_norm": 0.5519734025001526,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.2698,
      "step": 17
    },
    {
      "epoch": 0.0030345176381337715,
      "grad_norm": 0.5718574523925781,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.2127,
      "step": 18
    },
    {
      "epoch": 0.003203101951363426,
      "grad_norm": 0.5708631873130798,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.2722,
      "step": 19
    },
    {
      "epoch": 0.0033716862645930797,
      "grad_norm": 0.5642829537391663,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.2539,
      "step": 20
    },
    {
      "epoch": 0.0035402705778227335,
      "grad_norm": 0.5512787699699402,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.3325,
      "step": 21
    },
    {
      "epoch": 0.0037088548910523874,
      "grad_norm": 0.5757512450218201,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.4383,
      "step": 22
    },
    {
      "epoch": 0.0038774392042820417,
      "grad_norm": 0.5427912473678589,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.2283,
      "step": 23
    },
    {
      "epoch": 0.004046023517511695,
      "grad_norm": 0.6425997018814087,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.1959,
      "step": 24
    },
    {
      "epoch": 0.004214607830741349,
      "grad_norm": 0.5762646794319153,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.1836,
      "step": 25
    },
    {
      "epoch": 0.004383192143971004,
      "grad_norm": 0.6113796234130859,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.2452,
      "step": 26
    },
    {
      "epoch": 0.004551776457200657,
      "grad_norm": 0.5812516212463379,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.0035,
      "step": 27
    },
    {
      "epoch": 0.004720360770430311,
      "grad_norm": 0.5970272421836853,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.2464,
      "step": 28
    },
    {
      "epoch": 0.004888945083659966,
      "grad_norm": 0.5797311067581177,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1759,
      "step": 29
    },
    {
      "epoch": 0.005057529396889619,
      "grad_norm": 0.5593490600585938,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0388,
      "step": 30
    },
    {
      "epoch": 0.005226113710119273,
      "grad_norm": 0.6758949160575867,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.4452,
      "step": 31
    },
    {
      "epoch": 0.005394698023348928,
      "grad_norm": 0.628873348236084,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.2271,
      "step": 32
    },
    {
      "epoch": 0.005563282336578581,
      "grad_norm": 0.6257683038711548,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.0502,
      "step": 33
    },
    {
      "epoch": 0.005731866649808235,
      "grad_norm": 0.6716228127479553,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.3595,
      "step": 34
    },
    {
      "epoch": 0.00590045096303789,
      "grad_norm": 0.6931543350219727,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.3094,
      "step": 35
    },
    {
      "epoch": 0.006069035276267543,
      "grad_norm": 0.6866590976715088,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.4051,
      "step": 36
    },
    {
      "epoch": 0.006237619589497197,
      "grad_norm": 0.6935346722602844,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.2688,
      "step": 37
    },
    {
      "epoch": 0.006406203902726852,
      "grad_norm": 0.7251343727111816,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.5859,
      "step": 38
    },
    {
      "epoch": 0.006574788215956505,
      "grad_norm": 0.797118604183197,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.3242,
      "step": 39
    },
    {
      "epoch": 0.006743372529186159,
      "grad_norm": 0.8028149604797363,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.359,
      "step": 40
    },
    {
      "epoch": 0.006911956842415813,
      "grad_norm": 0.8518650531768799,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.3734,
      "step": 41
    },
    {
      "epoch": 0.007080541155645467,
      "grad_norm": 0.8653883934020996,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4176,
      "step": 42
    },
    {
      "epoch": 0.007249125468875121,
      "grad_norm": 0.9246017932891846,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.2629,
      "step": 43
    },
    {
      "epoch": 0.007417709782104775,
      "grad_norm": 0.9891728758811951,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.4381,
      "step": 44
    },
    {
      "epoch": 0.007586294095334429,
      "grad_norm": 0.9486820697784424,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.0758,
      "step": 45
    },
    {
      "epoch": 0.007754878408564083,
      "grad_norm": 1.175518274307251,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.0869,
      "step": 46
    },
    {
      "epoch": 0.007923462721793737,
      "grad_norm": 1.268325686454773,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.5444,
      "step": 47
    },
    {
      "epoch": 0.00809204703502339,
      "grad_norm": 1.300034523010254,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0648,
      "step": 48
    },
    {
      "epoch": 0.008260631348253045,
      "grad_norm": 1.632925271987915,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.2911,
      "step": 49
    },
    {
      "epoch": 0.008429215661482699,
      "grad_norm": 1.7452927827835083,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.1801,
      "step": 50
    },
    {
      "epoch": 0.008429215661482699,
      "eval_loss": 0.5852961540222168,
      "eval_runtime": 503.6954,
      "eval_samples_per_second": 19.833,
      "eval_steps_per_second": 4.959,
      "step": 50
    },
    {
      "epoch": 0.008597799974712352,
      "grad_norm": 1.6072931289672852,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.2302,
      "step": 51
    },
    {
      "epoch": 0.008766384287942007,
      "grad_norm": 1.4194364547729492,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.1396,
      "step": 52
    },
    {
      "epoch": 0.00893496860117166,
      "grad_norm": 1.2845665216445923,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.1345,
      "step": 53
    },
    {
      "epoch": 0.009103552914401314,
      "grad_norm": 0.8845593333244324,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.0498,
      "step": 54
    },
    {
      "epoch": 0.00927213722763097,
      "grad_norm": 0.6109545826911926,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.9017,
      "step": 55
    },
    {
      "epoch": 0.009440721540860623,
      "grad_norm": 0.5546384453773499,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.9024,
      "step": 56
    },
    {
      "epoch": 0.009609305854090276,
      "grad_norm": 0.6557427048683167,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.0121,
      "step": 57
    },
    {
      "epoch": 0.009777890167319931,
      "grad_norm": 0.6916495561599731,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.0961,
      "step": 58
    },
    {
      "epoch": 0.009946474480549585,
      "grad_norm": 0.8916401863098145,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.9969,
      "step": 59
    },
    {
      "epoch": 0.010115058793779238,
      "grad_norm": 0.7155196666717529,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.9971,
      "step": 60
    },
    {
      "epoch": 0.010283643107008893,
      "grad_norm": 0.6390310525894165,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.8875,
      "step": 61
    },
    {
      "epoch": 0.010452227420238547,
      "grad_norm": 0.6162652373313904,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.0048,
      "step": 62
    },
    {
      "epoch": 0.0106208117334682,
      "grad_norm": 0.658968985080719,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.9843,
      "step": 63
    },
    {
      "epoch": 0.010789396046697855,
      "grad_norm": 0.5488035082817078,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.1789,
      "step": 64
    },
    {
      "epoch": 0.010957980359927509,
      "grad_norm": 0.5768880248069763,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.0342,
      "step": 65
    },
    {
      "epoch": 0.011126564673157162,
      "grad_norm": 0.6004833579063416,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.1909,
      "step": 66
    },
    {
      "epoch": 0.011295148986386817,
      "grad_norm": 0.5959315299987793,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1024,
      "step": 67
    },
    {
      "epoch": 0.01146373329961647,
      "grad_norm": 0.568739652633667,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9843,
      "step": 68
    },
    {
      "epoch": 0.011632317612846124,
      "grad_norm": 0.5773057341575623,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.0,
      "step": 69
    },
    {
      "epoch": 0.01180090192607578,
      "grad_norm": 0.541660487651825,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.9902,
      "step": 70
    },
    {
      "epoch": 0.011969486239305433,
      "grad_norm": 0.5854316353797913,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.9918,
      "step": 71
    },
    {
      "epoch": 0.012138070552535086,
      "grad_norm": 0.5584428310394287,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.9419,
      "step": 72
    },
    {
      "epoch": 0.012306654865764741,
      "grad_norm": 0.5365278124809265,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.0853,
      "step": 73
    },
    {
      "epoch": 0.012475239178994395,
      "grad_norm": 0.5717236995697021,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.0404,
      "step": 74
    },
    {
      "epoch": 0.012643823492224048,
      "grad_norm": 0.5793030261993408,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.1286,
      "step": 75
    },
    {
      "epoch": 0.012812407805453703,
      "grad_norm": 0.589328944683075,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.9509,
      "step": 76
    },
    {
      "epoch": 0.012980992118683357,
      "grad_norm": 0.5952832102775574,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.9658,
      "step": 77
    },
    {
      "epoch": 0.01314957643191301,
      "grad_norm": 0.5512946844100952,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.9435,
      "step": 78
    },
    {
      "epoch": 0.013318160745142664,
      "grad_norm": 0.6114044189453125,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.0572,
      "step": 79
    },
    {
      "epoch": 0.013486745058372319,
      "grad_norm": 0.5982967019081116,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.149,
      "step": 80
    },
    {
      "epoch": 0.013655329371601972,
      "grad_norm": 0.5906240344047546,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.1401,
      "step": 81
    },
    {
      "epoch": 0.013823913684831626,
      "grad_norm": 0.6063304543495178,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.0977,
      "step": 82
    },
    {
      "epoch": 0.01399249799806128,
      "grad_norm": 0.5979247093200684,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.8334,
      "step": 83
    },
    {
      "epoch": 0.014161082311290934,
      "grad_norm": 0.7278677225112915,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.0423,
      "step": 84
    },
    {
      "epoch": 0.014329666624520588,
      "grad_norm": 0.6524538993835449,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.1623,
      "step": 85
    },
    {
      "epoch": 0.014498250937750243,
      "grad_norm": 0.6671821475028992,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0076,
      "step": 86
    },
    {
      "epoch": 0.014666835250979896,
      "grad_norm": 0.6858904957771301,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.1103,
      "step": 87
    },
    {
      "epoch": 0.01483541956420955,
      "grad_norm": 0.6992663741111755,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9078,
      "step": 88
    },
    {
      "epoch": 0.015004003877439205,
      "grad_norm": 0.7036033272743225,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.133,
      "step": 89
    },
    {
      "epoch": 0.015172588190668858,
      "grad_norm": 0.7181443572044373,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0406,
      "step": 90
    },
    {
      "epoch": 0.015341172503898512,
      "grad_norm": 0.7958605289459229,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.1708,
      "step": 91
    },
    {
      "epoch": 0.015509756817128167,
      "grad_norm": 0.8366865515708923,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.0042,
      "step": 92
    },
    {
      "epoch": 0.01567834113035782,
      "grad_norm": 0.9116945862770081,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.2093,
      "step": 93
    },
    {
      "epoch": 0.015846925443587474,
      "grad_norm": 0.8905110955238342,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.1819,
      "step": 94
    },
    {
      "epoch": 0.016015509756817127,
      "grad_norm": 0.9613068103790283,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.0145,
      "step": 95
    },
    {
      "epoch": 0.01618409407004678,
      "grad_norm": 1.0233409404754639,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.0892,
      "step": 96
    },
    {
      "epoch": 0.016352678383276437,
      "grad_norm": 1.155967116355896,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.0616,
      "step": 97
    },
    {
      "epoch": 0.01652126269650609,
      "grad_norm": 1.035759687423706,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.8554,
      "step": 98
    },
    {
      "epoch": 0.016689847009735744,
      "grad_norm": 1.0789740085601807,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.6287,
      "step": 99
    },
    {
      "epoch": 0.016858431322965398,
      "grad_norm": 1.503014087677002,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.1146,
      "step": 100
    },
    {
      "epoch": 0.016858431322965398,
      "eval_loss": 0.526066243648529,
      "eval_runtime": 504.2099,
      "eval_samples_per_second": 19.813,
      "eval_steps_per_second": 4.954,
      "step": 100
    },
    {
      "epoch": 0.01702701563619505,
      "grad_norm": 0.8459106683731079,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.8019,
      "step": 101
    },
    {
      "epoch": 0.017195599949424704,
      "grad_norm": 0.7669229507446289,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.8365,
      "step": 102
    },
    {
      "epoch": 0.01736418426265436,
      "grad_norm": 0.8305338025093079,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.0039,
      "step": 103
    },
    {
      "epoch": 0.017532768575884015,
      "grad_norm": 0.7221812009811401,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.7513,
      "step": 104
    },
    {
      "epoch": 0.017701352889113668,
      "grad_norm": 0.6130006313323975,
      "learning_rate": 5e-05,
      "loss": 1.9366,
      "step": 105
    },
    {
      "epoch": 0.01786993720234332,
      "grad_norm": 0.5634207725524902,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.8949,
      "step": 106
    },
    {
      "epoch": 0.018038521515572975,
      "grad_norm": 0.5072348117828369,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.9874,
      "step": 107
    },
    {
      "epoch": 0.01820710582880263,
      "grad_norm": 0.5250314474105835,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.0263,
      "step": 108
    },
    {
      "epoch": 0.018375690142032285,
      "grad_norm": 0.5274400115013123,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.9786,
      "step": 109
    },
    {
      "epoch": 0.01854427445526194,
      "grad_norm": 0.5674232840538025,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.9715,
      "step": 110
    },
    {
      "epoch": 0.018712858768491592,
      "grad_norm": 0.5594687461853027,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.8128,
      "step": 111
    },
    {
      "epoch": 0.018881443081721246,
      "grad_norm": 0.6089913845062256,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.9679,
      "step": 112
    },
    {
      "epoch": 0.0190500273949509,
      "grad_norm": 0.5950120687484741,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.9994,
      "step": 113
    },
    {
      "epoch": 0.019218611708180552,
      "grad_norm": 0.600623369216919,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9543,
      "step": 114
    },
    {
      "epoch": 0.01938719602141021,
      "grad_norm": 0.5748342275619507,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.2005,
      "step": 115
    },
    {
      "epoch": 0.019555780334639863,
      "grad_norm": 0.578003466129303,
      "learning_rate": 4.095597328339452e-05,
      "loss": 2.0207,
      "step": 116
    },
    {
      "epoch": 0.019724364647869516,
      "grad_norm": 0.5588600635528564,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.9704,
      "step": 117
    },
    {
      "epoch": 0.01989294896109917,
      "grad_norm": 0.5894056558609009,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.9467,
      "step": 118
    },
    {
      "epoch": 0.020061533274328823,
      "grad_norm": 0.530829131603241,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.9117,
      "step": 119
    },
    {
      "epoch": 0.020230117587558476,
      "grad_norm": 0.5551753640174866,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.0052,
      "step": 120
    },
    {
      "epoch": 0.020398701900788133,
      "grad_norm": 0.5634602904319763,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.1341,
      "step": 121
    },
    {
      "epoch": 0.020567286214017787,
      "grad_norm": 0.5533777475357056,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.9628,
      "step": 122
    },
    {
      "epoch": 0.02073587052724744,
      "grad_norm": 0.5677472949028015,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.9898,
      "step": 123
    },
    {
      "epoch": 0.020904454840477094,
      "grad_norm": 0.5726702213287354,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9436,
      "step": 124
    },
    {
      "epoch": 0.021073039153706747,
      "grad_norm": 0.6019315719604492,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.0885,
      "step": 125
    },
    {
      "epoch": 0.0212416234669364,
      "grad_norm": 0.5663155913352966,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.8675,
      "step": 126
    },
    {
      "epoch": 0.021410207780166054,
      "grad_norm": 0.6067866086959839,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.1002,
      "step": 127
    },
    {
      "epoch": 0.02157879209339571,
      "grad_norm": 0.593870222568512,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.8943,
      "step": 128
    },
    {
      "epoch": 0.021747376406625364,
      "grad_norm": 0.5843802690505981,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.988,
      "step": 129
    },
    {
      "epoch": 0.021915960719855018,
      "grad_norm": 0.584688127040863,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.9009,
      "step": 130
    },
    {
      "epoch": 0.02208454503308467,
      "grad_norm": 0.7039766311645508,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.2012,
      "step": 131
    },
    {
      "epoch": 0.022253129346314324,
      "grad_norm": 0.6203482747077942,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.0764,
      "step": 132
    },
    {
      "epoch": 0.022421713659543978,
      "grad_norm": 0.6596606969833374,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.2828,
      "step": 133
    },
    {
      "epoch": 0.022590297972773635,
      "grad_norm": 0.6507753133773804,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.1802,
      "step": 134
    },
    {
      "epoch": 0.022758882286003288,
      "grad_norm": 0.642286479473114,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.943,
      "step": 135
    },
    {
      "epoch": 0.02292746659923294,
      "grad_norm": 0.7154486775398254,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.1437,
      "step": 136
    },
    {
      "epoch": 0.023096050912462595,
      "grad_norm": 0.698128879070282,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.1588,
      "step": 137
    },
    {
      "epoch": 0.02326463522569225,
      "grad_norm": 0.7401313185691833,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.1049,
      "step": 138
    },
    {
      "epoch": 0.023433219538921902,
      "grad_norm": 0.775383710861206,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.1959,
      "step": 139
    },
    {
      "epoch": 0.02360180385215156,
      "grad_norm": 0.8397006392478943,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.1508,
      "step": 140
    },
    {
      "epoch": 0.023770388165381212,
      "grad_norm": 0.7125548720359802,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.7221,
      "step": 141
    },
    {
      "epoch": 0.023938972478610866,
      "grad_norm": 0.8500107526779175,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.1389,
      "step": 142
    },
    {
      "epoch": 0.02410755679184052,
      "grad_norm": 0.9977157115936279,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.084,
      "step": 143
    },
    {
      "epoch": 0.024276141105070172,
      "grad_norm": 0.9876620769500732,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.2093,
      "step": 144
    },
    {
      "epoch": 0.024444725418299826,
      "grad_norm": 1.0406392812728882,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.1157,
      "step": 145
    },
    {
      "epoch": 0.024613309731529483,
      "grad_norm": 0.9986876845359802,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.744,
      "step": 146
    },
    {
      "epoch": 0.024781894044759136,
      "grad_norm": 1.2198210954666138,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.8887,
      "step": 147
    },
    {
      "epoch": 0.02495047835798879,
      "grad_norm": 1.200136661529541,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.913,
      "step": 148
    },
    {
      "epoch": 0.025119062671218443,
      "grad_norm": 1.2255388498306274,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.673,
      "step": 149
    },
    {
      "epoch": 0.025287646984448096,
      "grad_norm": 1.8769245147705078,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.3211,
      "step": 150
    },
    {
      "epoch": 0.025287646984448096,
      "eval_loss": 0.4997311234474182,
      "eval_runtime": 504.4517,
      "eval_samples_per_second": 19.804,
      "eval_steps_per_second": 4.952,
      "step": 150
    },
    {
      "epoch": 0.02545623129767775,
      "grad_norm": 0.49811846017837524,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.6809,
      "step": 151
    },
    {
      "epoch": 0.025624815610907407,
      "grad_norm": 0.5585156083106995,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.0032,
      "step": 152
    },
    {
      "epoch": 0.02579339992413706,
      "grad_norm": 0.5610803365707397,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.7669,
      "step": 153
    },
    {
      "epoch": 0.025961984237366714,
      "grad_norm": 0.5621859431266785,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.9028,
      "step": 154
    },
    {
      "epoch": 0.026130568550596367,
      "grad_norm": 0.5679500699043274,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.9731,
      "step": 155
    },
    {
      "epoch": 0.02629915286382602,
      "grad_norm": 0.5851702690124512,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.892,
      "step": 156
    },
    {
      "epoch": 0.026467737177055674,
      "grad_norm": 0.5525903701782227,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.8571,
      "step": 157
    },
    {
      "epoch": 0.026636321490285327,
      "grad_norm": 0.5482596158981323,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.9758,
      "step": 158
    },
    {
      "epoch": 0.026804905803514984,
      "grad_norm": 0.5632185339927673,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.9185,
      "step": 159
    },
    {
      "epoch": 0.026973490116744638,
      "grad_norm": 0.543819785118103,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.8691,
      "step": 160
    },
    {
      "epoch": 0.02714207442997429,
      "grad_norm": 0.5464532971382141,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.907,
      "step": 161
    },
    {
      "epoch": 0.027310658743203944,
      "grad_norm": 0.5549024343490601,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.846,
      "step": 162
    },
    {
      "epoch": 0.027479243056433598,
      "grad_norm": 0.5390320420265198,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.0051,
      "step": 163
    },
    {
      "epoch": 0.02764782736966325,
      "grad_norm": 0.5453265905380249,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.8533,
      "step": 164
    },
    {
      "epoch": 0.027816411682892908,
      "grad_norm": 0.5573222041130066,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.9489,
      "step": 165
    },
    {
      "epoch": 0.02798499599612256,
      "grad_norm": 0.5626527667045593,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.0381,
      "step": 166
    },
    {
      "epoch": 0.028153580309352215,
      "grad_norm": 0.5534669756889343,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.0412,
      "step": 167
    },
    {
      "epoch": 0.02832216462258187,
      "grad_norm": 0.5500248670578003,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.9099,
      "step": 168
    },
    {
      "epoch": 0.028490748935811522,
      "grad_norm": 0.5509589314460754,
      "learning_rate": 6.425787818636131e-06,
      "loss": 2.0256,
      "step": 169
    },
    {
      "epoch": 0.028659333249041175,
      "grad_norm": 0.5385216474533081,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.781,
      "step": 170
    },
    {
      "epoch": 0.028827917562270832,
      "grad_norm": 0.542852520942688,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.0085,
      "step": 171
    },
    {
      "epoch": 0.028996501875500486,
      "grad_norm": 0.5554140210151672,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.9373,
      "step": 172
    },
    {
      "epoch": 0.02916508618873014,
      "grad_norm": 0.5634838342666626,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.8476,
      "step": 173
    },
    {
      "epoch": 0.029333670501959792,
      "grad_norm": 0.5786818861961365,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.0008,
      "step": 174
    },
    {
      "epoch": 0.029502254815189446,
      "grad_norm": 0.8584355115890503,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.9171,
      "step": 175
    },
    {
      "epoch": 0.0296708391284191,
      "grad_norm": 0.591818630695343,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.956,
      "step": 176
    },
    {
      "epoch": 0.029839423441648756,
      "grad_norm": 0.5805782675743103,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.7393,
      "step": 177
    },
    {
      "epoch": 0.03000800775487841,
      "grad_norm": 0.6048120260238647,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.9783,
      "step": 178
    },
    {
      "epoch": 0.030176592068108063,
      "grad_norm": 0.5900549292564392,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.8709,
      "step": 179
    },
    {
      "epoch": 0.030345176381337716,
      "grad_norm": 0.6428003311157227,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.0541,
      "step": 180
    },
    {
      "epoch": 0.03051376069456737,
      "grad_norm": 0.6558092832565308,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.965,
      "step": 181
    },
    {
      "epoch": 0.030682345007797023,
      "grad_norm": 0.6329799890518188,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.8469,
      "step": 182
    },
    {
      "epoch": 0.03085092932102668,
      "grad_norm": 0.6509044170379639,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.8741,
      "step": 183
    },
    {
      "epoch": 0.031019513634256334,
      "grad_norm": 0.641316294670105,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.9808,
      "step": 184
    },
    {
      "epoch": 0.031188097947485987,
      "grad_norm": 0.69351726770401,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.0366,
      "step": 185
    },
    {
      "epoch": 0.03135668226071564,
      "grad_norm": 0.7163324952125549,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.062,
      "step": 186
    },
    {
      "epoch": 0.0315252665739453,
      "grad_norm": 0.7163425087928772,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.0312,
      "step": 187
    },
    {
      "epoch": 0.03169385088717495,
      "grad_norm": 0.7344024181365967,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.037,
      "step": 188
    },
    {
      "epoch": 0.031862435200404604,
      "grad_norm": 0.8359835743904114,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.1176,
      "step": 189
    },
    {
      "epoch": 0.032031019513634254,
      "grad_norm": 0.7753138542175293,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9638,
      "step": 190
    },
    {
      "epoch": 0.03219960382686391,
      "grad_norm": 0.8367087244987488,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.0021,
      "step": 191
    },
    {
      "epoch": 0.03236818814009356,
      "grad_norm": 0.9125208854675293,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.2274,
      "step": 192
    },
    {
      "epoch": 0.03253677245332322,
      "grad_norm": 0.9420064091682434,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.2636,
      "step": 193
    },
    {
      "epoch": 0.032705356766552875,
      "grad_norm": 0.9875706434249878,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.2038,
      "step": 194
    },
    {
      "epoch": 0.032873941079782525,
      "grad_norm": 0.9815607666969299,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.9959,
      "step": 195
    },
    {
      "epoch": 0.03304252539301218,
      "grad_norm": 1.0846351385116577,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.9414,
      "step": 196
    },
    {
      "epoch": 0.03321110970624183,
      "grad_norm": 1.00554358959198,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.8011,
      "step": 197
    },
    {
      "epoch": 0.03337969401947149,
      "grad_norm": 1.1244187355041504,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.6703,
      "step": 198
    },
    {
      "epoch": 0.033548278332701145,
      "grad_norm": 1.2262691259384155,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.6914,
      "step": 199
    },
    {
      "epoch": 0.033716862645930795,
      "grad_norm": 1.559067726135254,
      "learning_rate": 0.0,
      "loss": 2.0574,
      "step": 200
    },
    {
      "epoch": 0.033716862645930795,
      "eval_loss": 0.49369120597839355,
      "eval_runtime": 503.9087,
      "eval_samples_per_second": 19.825,
      "eval_steps_per_second": 4.957,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.535331927148462e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}