{
  "best_metric": 0.6579892635345459,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 1.4678899082568808,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007339449541284404,
      "grad_norm": 1.2558354139328003,
      "learning_rate": 1e-05,
      "loss": 0.9112,
      "step": 1
    },
    {
      "epoch": 0.007339449541284404,
      "eval_loss": 1.086421012878418,
      "eval_runtime": 7.422,
      "eval_samples_per_second": 30.989,
      "eval_steps_per_second": 7.815,
      "step": 1
    },
    {
      "epoch": 0.014678899082568808,
      "grad_norm": 1.3153743743896484,
      "learning_rate": 2e-05,
      "loss": 0.9991,
      "step": 2
    },
    {
      "epoch": 0.022018348623853212,
      "grad_norm": 1.2754677534103394,
      "learning_rate": 3e-05,
      "loss": 1.0084,
      "step": 3
    },
    {
      "epoch": 0.029357798165137616,
      "grad_norm": 1.09935462474823,
      "learning_rate": 4e-05,
      "loss": 0.8748,
      "step": 4
    },
    {
      "epoch": 0.03669724770642202,
      "grad_norm": 0.9235318899154663,
      "learning_rate": 5e-05,
      "loss": 0.9293,
      "step": 5
    },
    {
      "epoch": 0.044036697247706424,
      "grad_norm": 0.8946143388748169,
      "learning_rate": 6e-05,
      "loss": 0.6866,
      "step": 6
    },
    {
      "epoch": 0.05137614678899083,
      "grad_norm": 0.7832019329071045,
      "learning_rate": 7e-05,
      "loss": 0.8417,
      "step": 7
    },
    {
      "epoch": 0.05871559633027523,
      "grad_norm": 0.6342179179191589,
      "learning_rate": 8e-05,
      "loss": 0.8374,
      "step": 8
    },
    {
      "epoch": 0.06605504587155964,
      "grad_norm": 0.8697676062583923,
      "learning_rate": 9e-05,
      "loss": 0.8561,
      "step": 9
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": 0.6957120895385742,
      "learning_rate": 0.0001,
      "loss": 0.7363,
      "step": 10
    },
    {
      "epoch": 0.08073394495412844,
      "grad_norm": 0.7035614252090454,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6709,
      "step": 11
    },
    {
      "epoch": 0.08807339449541285,
      "grad_norm": 0.7856741547584534,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7045,
      "step": 12
    },
    {
      "epoch": 0.09541284403669725,
      "grad_norm": 0.6767359972000122,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7028,
      "step": 13
    },
    {
      "epoch": 0.10275229357798166,
      "grad_norm": 0.6897175312042236,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8113,
      "step": 14
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 0.6219428181648254,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7361,
      "step": 15
    },
    {
      "epoch": 0.11743119266055047,
      "grad_norm": 0.5864216685295105,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7374,
      "step": 16
    },
    {
      "epoch": 0.12477064220183487,
      "grad_norm": 0.5672091245651245,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6956,
      "step": 17
    },
    {
      "epoch": 0.13211009174311927,
      "grad_norm": 0.679236650466919,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8077,
      "step": 18
    },
    {
      "epoch": 0.13944954128440368,
      "grad_norm": 0.533450186252594,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7256,
      "step": 19
    },
    {
      "epoch": 0.14678899082568808,
      "grad_norm": 0.5469915270805359,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7653,
      "step": 20
    },
    {
      "epoch": 0.15412844036697249,
      "grad_norm": 0.5419031381607056,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6857,
      "step": 21
    },
    {
      "epoch": 0.1614678899082569,
      "grad_norm": 0.570133626461029,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7016,
      "step": 22
    },
    {
      "epoch": 0.1688073394495413,
      "grad_norm": 0.5922853946685791,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7305,
      "step": 23
    },
    {
      "epoch": 0.1761467889908257,
      "grad_norm": 0.5787784457206726,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7127,
      "step": 24
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 0.638210117816925,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7038,
      "step": 25
    },
    {
      "epoch": 0.1908256880733945,
      "grad_norm": 0.7027117013931274,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8599,
      "step": 26
    },
    {
      "epoch": 0.1981651376146789,
      "grad_norm": 0.6234266757965088,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9354,
      "step": 27
    },
    {
      "epoch": 0.20550458715596331,
      "grad_norm": 0.6509023904800415,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8259,
      "step": 28
    },
    {
      "epoch": 0.21284403669724772,
      "grad_norm": 0.6378542184829712,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8374,
      "step": 29
    },
    {
      "epoch": 0.22018348623853212,
      "grad_norm": 0.6379691958427429,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8669,
      "step": 30
    },
    {
      "epoch": 0.22752293577981653,
      "grad_norm": 0.6336305737495422,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.826,
      "step": 31
    },
    {
      "epoch": 0.23486238532110093,
      "grad_norm": 0.6773037314414978,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9538,
      "step": 32
    },
    {
      "epoch": 0.24220183486238533,
      "grad_norm": 0.7563718557357788,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9694,
      "step": 33
    },
    {
      "epoch": 0.24954128440366974,
      "grad_norm": 1.450920820236206,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2884,
      "step": 34
    },
    {
      "epoch": 0.25688073394495414,
      "grad_norm": 0.45205074548721313,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5391,
      "step": 35
    },
    {
      "epoch": 0.26422018348623855,
      "grad_norm": 0.4610302746295929,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5379,
      "step": 36
    },
    {
      "epoch": 0.27155963302752295,
      "grad_norm": 0.43490421772003174,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5828,
      "step": 37
    },
    {
      "epoch": 0.27889908256880735,
      "grad_norm": 0.440649151802063,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6633,
      "step": 38
    },
    {
      "epoch": 0.28623853211009176,
      "grad_norm": 0.39390572905540466,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5561,
      "step": 39
    },
    {
      "epoch": 0.29357798165137616,
      "grad_norm": 0.38463252782821655,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.593,
      "step": 40
    },
    {
      "epoch": 0.30091743119266057,
      "grad_norm": 0.582129955291748,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5935,
      "step": 41
    },
    {
      "epoch": 0.30825688073394497,
      "grad_norm": 0.39041706919670105,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7517,
      "step": 42
    },
    {
      "epoch": 0.3155963302752294,
      "grad_norm": 0.398325115442276,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7902,
      "step": 43
    },
    {
      "epoch": 0.3229357798165138,
      "grad_norm": 0.3442983031272888,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4754,
      "step": 44
    },
    {
      "epoch": 0.3302752293577982,
      "grad_norm": 0.37911897897720337,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5692,
      "step": 45
    },
    {
      "epoch": 0.3376146788990826,
      "grad_norm": 0.40420764684677124,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.625,
      "step": 46
    },
    {
      "epoch": 0.344954128440367,
      "grad_norm": 0.4506022036075592,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6983,
      "step": 47
    },
    {
      "epoch": 0.3522935779816514,
      "grad_norm": 0.415752649307251,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7061,
      "step": 48
    },
    {
      "epoch": 0.3596330275229358,
      "grad_norm": 0.42149221897125244,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6839,
      "step": 49
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 0.4243476390838623,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5976,
      "step": 50
    },
    {
      "epoch": 0.3669724770642202,
      "eval_loss": 0.7088869214057922,
      "eval_runtime": 7.4157,
      "eval_samples_per_second": 31.015,
      "eval_steps_per_second": 7.821,
      "step": 50
    },
    {
      "epoch": 0.3743119266055046,
      "grad_norm": 0.4554750621318817,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6627,
      "step": 51
    },
    {
      "epoch": 0.381651376146789,
      "grad_norm": 0.4366817772388458,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6671,
      "step": 52
    },
    {
      "epoch": 0.3889908256880734,
      "grad_norm": 0.4233996868133545,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6793,
      "step": 53
    },
    {
      "epoch": 0.3963302752293578,
      "grad_norm": 0.4846845269203186,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6805,
      "step": 54
    },
    {
      "epoch": 0.4036697247706422,
      "grad_norm": 0.5277559161186218,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6534,
      "step": 55
    },
    {
      "epoch": 0.41100917431192663,
      "grad_norm": 0.44435515999794006,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7174,
      "step": 56
    },
    {
      "epoch": 0.41834862385321103,
      "grad_norm": 0.5242100358009338,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.657,
      "step": 57
    },
    {
      "epoch": 0.42568807339449544,
      "grad_norm": 0.5298843383789062,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7244,
      "step": 58
    },
    {
      "epoch": 0.43302752293577984,
      "grad_norm": 0.4963929355144501,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6922,
      "step": 59
    },
    {
      "epoch": 0.44036697247706424,
      "grad_norm": 0.5238680839538574,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7058,
      "step": 60
    },
    {
      "epoch": 0.44770642201834865,
      "grad_norm": 0.4960371255874634,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6866,
      "step": 61
    },
    {
      "epoch": 0.45504587155963305,
      "grad_norm": 0.5246888995170593,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7938,
      "step": 62
    },
    {
      "epoch": 0.46238532110091746,
      "grad_norm": 0.6266915798187256,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7852,
      "step": 63
    },
    {
      "epoch": 0.46972477064220186,
      "grad_norm": 0.6021617650985718,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7495,
      "step": 64
    },
    {
      "epoch": 0.47706422018348627,
      "grad_norm": 0.6005452275276184,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9072,
      "step": 65
    },
    {
      "epoch": 0.48440366972477067,
      "grad_norm": 0.6301631331443787,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9484,
      "step": 66
    },
    {
      "epoch": 0.4917431192660551,
      "grad_norm": 0.708684504032135,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0716,
      "step": 67
    },
    {
      "epoch": 0.4990825688073395,
      "grad_norm": 1.0204704999923706,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2479,
      "step": 68
    },
    {
      "epoch": 0.5064220183486239,
      "grad_norm": 0.4011888802051544,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5483,
      "step": 69
    },
    {
      "epoch": 0.5137614678899083,
      "grad_norm": 0.4205548167228699,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6581,
      "step": 70
    },
    {
      "epoch": 0.5211009174311927,
      "grad_norm": 0.4061049818992615,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5984,
      "step": 71
    },
    {
      "epoch": 0.5284403669724771,
      "grad_norm": 0.3665936291217804,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5462,
      "step": 72
    },
    {
      "epoch": 0.5357798165137615,
      "grad_norm": 0.35719403624534607,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5123,
      "step": 73
    },
    {
      "epoch": 0.5431192660550459,
      "grad_norm": 0.34069886803627014,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.591,
      "step": 74
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 0.349661648273468,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.59,
      "step": 75
    },
    {
      "epoch": 0.5577981651376147,
      "grad_norm": 0.3346997797489166,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6076,
      "step": 76
    },
    {
      "epoch": 0.5651376146788991,
      "grad_norm": 0.3229953646659851,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5744,
      "step": 77
    },
    {
      "epoch": 0.5724770642201835,
      "grad_norm": 0.3252444267272949,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5252,
      "step": 78
    },
    {
      "epoch": 0.5798165137614679,
      "grad_norm": 0.36729884147644043,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6329,
      "step": 79
    },
    {
      "epoch": 0.5871559633027523,
      "grad_norm": 0.4011584222316742,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.552,
      "step": 80
    },
    {
      "epoch": 0.5944954128440367,
      "grad_norm": 0.45007458329200745,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.652,
      "step": 81
    },
    {
      "epoch": 0.6018348623853211,
      "grad_norm": 0.3779699206352234,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5618,
      "step": 82
    },
    {
      "epoch": 0.6091743119266055,
      "grad_norm": 0.4151765704154968,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6455,
      "step": 83
    },
    {
      "epoch": 0.6165137614678899,
      "grad_norm": 0.38377100229263306,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6509,
      "step": 84
    },
    {
      "epoch": 0.6238532110091743,
      "grad_norm": 0.37402817606925964,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6037,
      "step": 85
    },
    {
      "epoch": 0.6311926605504588,
      "grad_norm": 0.37692010402679443,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5985,
      "step": 86
    },
    {
      "epoch": 0.6385321100917432,
      "grad_norm": 0.41290709376335144,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6323,
      "step": 87
    },
    {
      "epoch": 0.6458715596330276,
      "grad_norm": 0.3961733877658844,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6209,
      "step": 88
    },
    {
      "epoch": 0.653211009174312,
      "grad_norm": 0.42742016911506653,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6982,
      "step": 89
    },
    {
      "epoch": 0.6605504587155964,
      "grad_norm": 0.41686034202575684,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6753,
      "step": 90
    },
    {
      "epoch": 0.6678899082568808,
      "grad_norm": 0.42225784063339233,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6742,
      "step": 91
    },
    {
      "epoch": 0.6752293577981652,
      "grad_norm": 0.4660816192626953,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6776,
      "step": 92
    },
    {
      "epoch": 0.6825688073394496,
      "grad_norm": 0.46300622820854187,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7878,
      "step": 93
    },
    {
      "epoch": 0.689908256880734,
      "grad_norm": 0.529586672782898,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7751,
      "step": 94
    },
    {
      "epoch": 0.6972477064220184,
      "grad_norm": 0.4861275851726532,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6899,
      "step": 95
    },
    {
      "epoch": 0.7045871559633028,
      "grad_norm": 0.6364589929580688,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7222,
      "step": 96
    },
    {
      "epoch": 0.7119266055045872,
      "grad_norm": 0.5608426332473755,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6716,
      "step": 97
    },
    {
      "epoch": 0.7192660550458716,
      "grad_norm": 0.5894444584846497,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8161,
      "step": 98
    },
    {
      "epoch": 0.726605504587156,
      "grad_norm": 0.5440137386322021,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7928,
      "step": 99
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.5815492868423462,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8976,
      "step": 100
    },
    {
      "epoch": 0.7339449541284404,
      "eval_loss": 0.6700910329818726,
      "eval_runtime": 7.442,
      "eval_samples_per_second": 30.906,
      "eval_steps_per_second": 7.794,
      "step": 100
    },
    {
      "epoch": 0.7412844036697248,
      "grad_norm": 0.7427303194999695,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0826,
      "step": 101
    },
    {
      "epoch": 0.7486238532110092,
      "grad_norm": 0.9419289827346802,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.0229,
      "step": 102
    },
    {
      "epoch": 0.7559633027522936,
      "grad_norm": 0.3607136309146881,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5229,
      "step": 103
    },
    {
      "epoch": 0.763302752293578,
      "grad_norm": 0.352348268032074,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5156,
      "step": 104
    },
    {
      "epoch": 0.7706422018348624,
      "grad_norm": 0.3576844036579132,
      "learning_rate": 5e-05,
      "loss": 0.604,
      "step": 105
    },
    {
      "epoch": 0.7779816513761468,
      "grad_norm": 0.3728982210159302,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5871,
      "step": 106
    },
    {
      "epoch": 0.7853211009174312,
      "grad_norm": 0.34228596091270447,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6223,
      "step": 107
    },
    {
      "epoch": 0.7926605504587156,
      "grad_norm": 0.3442189395427704,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6205,
      "step": 108
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.33720663189888,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6099,
      "step": 109
    },
    {
      "epoch": 0.8073394495412844,
      "grad_norm": 0.3589037358760834,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5712,
      "step": 110
    },
    {
      "epoch": 0.8146788990825689,
      "grad_norm": 0.33918699622154236,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.484,
      "step": 111
    },
    {
      "epoch": 0.8220183486238533,
      "grad_norm": 0.29655900597572327,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4308,
      "step": 112
    },
    {
      "epoch": 0.8293577981651377,
      "grad_norm": 0.32902243733406067,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5141,
      "step": 113
    },
    {
      "epoch": 0.8366972477064221,
      "grad_norm": 0.3348574936389923,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6005,
      "step": 114
    },
    {
      "epoch": 0.8440366972477065,
      "grad_norm": 0.3530728220939636,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.604,
      "step": 115
    },
    {
      "epoch": 0.8513761467889909,
      "grad_norm": 0.3687516748905182,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5234,
      "step": 116
    },
    {
      "epoch": 0.8587155963302753,
      "grad_norm": 0.4044620394706726,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6196,
      "step": 117
    },
    {
      "epoch": 0.8660550458715597,
      "grad_norm": 0.36522620916366577,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5693,
      "step": 118
    },
    {
      "epoch": 0.8733944954128441,
      "grad_norm": 0.39524418115615845,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6652,
      "step": 119
    },
    {
      "epoch": 0.8807339449541285,
      "grad_norm": 0.42344722151756287,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6308,
      "step": 120
    },
    {
      "epoch": 0.8880733944954129,
      "grad_norm": 0.3990527391433716,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5709,
      "step": 121
    },
    {
      "epoch": 0.8954128440366973,
      "grad_norm": 0.4004659950733185,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6474,
      "step": 122
    },
    {
      "epoch": 0.9027522935779817,
      "grad_norm": 0.408437043428421,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6141,
      "step": 123
    },
    {
      "epoch": 0.9100917431192661,
      "grad_norm": 0.42973485589027405,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6075,
      "step": 124
    },
    {
      "epoch": 0.9174311926605505,
      "grad_norm": 0.45113319158554077,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6327,
      "step": 125
    },
    {
      "epoch": 0.9247706422018349,
      "grad_norm": 0.46148020029067993,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6761,
      "step": 126
    },
    {
      "epoch": 0.9321100917431193,
      "grad_norm": 0.44988685846328735,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.779,
      "step": 127
    },
    {
      "epoch": 0.9394495412844037,
      "grad_norm": 0.5196802020072937,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7935,
      "step": 128
    },
    {
      "epoch": 0.9467889908256881,
      "grad_norm": 0.5013748407363892,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7125,
      "step": 129
    },
    {
      "epoch": 0.9541284403669725,
      "grad_norm": 0.5056673884391785,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6905,
      "step": 130
    },
    {
      "epoch": 0.9614678899082569,
      "grad_norm": 0.5008897185325623,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7209,
      "step": 131
    },
    {
      "epoch": 0.9688073394495413,
      "grad_norm": 0.5691271424293518,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.9628,
      "step": 132
    },
    {
      "epoch": 0.9761467889908257,
      "grad_norm": 0.5279262661933899,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7152,
      "step": 133
    },
    {
      "epoch": 0.9834862385321101,
      "grad_norm": 0.5786201357841492,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8762,
      "step": 134
    },
    {
      "epoch": 0.9908256880733946,
      "grad_norm": 0.7210801243782043,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9938,
      "step": 135
    },
    {
      "epoch": 0.998165137614679,
      "grad_norm": 0.8217911720275879,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.0176,
      "step": 136
    },
    {
      "epoch": 1.0055045871559634,
      "grad_norm": 2.510568141937256,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.364,
      "step": 137
    },
    {
      "epoch": 1.0128440366972478,
      "grad_norm": 0.30809783935546875,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4239,
      "step": 138
    },
    {
      "epoch": 1.0201834862385322,
      "grad_norm": 0.32342445850372314,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5568,
      "step": 139
    },
    {
      "epoch": 1.0275229357798166,
      "grad_norm": 0.31456756591796875,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.527,
      "step": 140
    },
    {
      "epoch": 1.034862385321101,
      "grad_norm": 0.3119969367980957,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5716,
      "step": 141
    },
    {
      "epoch": 1.0422018348623854,
      "grad_norm": 0.32050958275794983,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5697,
      "step": 142
    },
    {
      "epoch": 1.0495412844036698,
      "grad_norm": 0.31600016355514526,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5514,
      "step": 143
    },
    {
      "epoch": 1.0568807339449542,
      "grad_norm": 0.3156934082508087,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5765,
      "step": 144
    },
    {
      "epoch": 1.0642201834862386,
      "grad_norm": 0.3005427122116089,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5349,
      "step": 145
    },
    {
      "epoch": 1.071559633027523,
      "grad_norm": 0.30332130193710327,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5141,
      "step": 146
    },
    {
      "epoch": 1.0788990825688074,
      "grad_norm": 0.31053999066352844,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4676,
      "step": 147
    },
    {
      "epoch": 1.0862385321100918,
      "grad_norm": 0.31160983443260193,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4996,
      "step": 148
    },
    {
      "epoch": 1.0935779816513762,
      "grad_norm": 0.36245542764663696,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5691,
      "step": 149
    },
    {
      "epoch": 1.1009174311926606,
      "grad_norm": 0.36475515365600586,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6714,
      "step": 150
    },
    {
      "epoch": 1.1009174311926606,
      "eval_loss": 0.6579892635345459,
      "eval_runtime": 7.4247,
      "eval_samples_per_second": 30.978,
      "eval_steps_per_second": 7.812,
      "step": 150
    },
    {
      "epoch": 1.108256880733945,
      "grad_norm": 0.34580230712890625,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.51,
      "step": 151
    },
    {
      "epoch": 1.1155963302752294,
      "grad_norm": 0.3720889091491699,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6064,
      "step": 152
    },
    {
      "epoch": 1.1229357798165138,
      "grad_norm": 0.3405211567878723,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.4748,
      "step": 153
    },
    {
      "epoch": 1.1302752293577982,
      "grad_norm": 0.38365665078163147,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6184,
      "step": 154
    },
    {
      "epoch": 1.1376146788990826,
      "grad_norm": 0.38093194365501404,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6226,
      "step": 155
    },
    {
      "epoch": 1.144954128440367,
      "grad_norm": 0.36480769515037537,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5909,
      "step": 156
    },
    {
      "epoch": 1.1522935779816514,
      "grad_norm": 0.3993949890136719,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6368,
      "step": 157
    },
    {
      "epoch": 1.1596330275229358,
      "grad_norm": 0.38528627157211304,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5437,
      "step": 158
    },
    {
      "epoch": 1.1669724770642202,
      "grad_norm": 0.39607447385787964,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5975,
      "step": 159
    },
    {
      "epoch": 1.1743119266055047,
      "grad_norm": 0.39313191175460815,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6011,
      "step": 160
    },
    {
      "epoch": 1.181651376146789,
      "grad_norm": 0.4341736137866974,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5761,
      "step": 161
    },
    {
      "epoch": 1.1889908256880735,
      "grad_norm": 0.43899503350257874,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7982,
      "step": 162
    },
    {
      "epoch": 1.1963302752293579,
      "grad_norm": 0.45237603783607483,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7236,
      "step": 163
    },
    {
      "epoch": 1.2036697247706423,
      "grad_norm": 0.4389019310474396,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6187,
      "step": 164
    },
    {
      "epoch": 1.2110091743119267,
      "grad_norm": 0.4588145613670349,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6758,
      "step": 165
    },
    {
      "epoch": 1.218348623853211,
      "grad_norm": 0.48190125823020935,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7072,
      "step": 166
    },
    {
      "epoch": 1.2256880733944955,
      "grad_norm": 0.515060305595398,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7438,
      "step": 167
    },
    {
      "epoch": 1.2330275229357799,
      "grad_norm": 0.49318620562553406,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6918,
      "step": 168
    },
    {
      "epoch": 1.2403669724770643,
      "grad_norm": 0.6594893932342529,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8079,
      "step": 169
    },
    {
      "epoch": 1.2477064220183487,
      "grad_norm": 0.7526155710220337,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9653,
      "step": 170
    },
    {
      "epoch": 1.255045871559633,
      "grad_norm": 0.41764017939567566,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4752,
      "step": 171
    },
    {
      "epoch": 1.2623853211009175,
      "grad_norm": 0.3623609244823456,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5071,
      "step": 172
    },
    {
      "epoch": 1.269724770642202,
      "grad_norm": 0.30031076073646545,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4445,
      "step": 173
    },
    {
      "epoch": 1.2770642201834863,
      "grad_norm": 0.31060296297073364,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5132,
      "step": 174
    },
    {
      "epoch": 1.2844036697247707,
      "grad_norm": 0.3110771179199219,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5592,
      "step": 175
    },
    {
      "epoch": 1.2917431192660551,
      "grad_norm": 0.3495020568370819,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5555,
      "step": 176
    },
    {
      "epoch": 1.2990825688073395,
      "grad_norm": 0.3174368441104889,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4855,
      "step": 177
    },
    {
      "epoch": 1.306422018348624,
      "grad_norm": 0.304007351398468,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.453,
      "step": 178
    },
    {
      "epoch": 1.3137614678899083,
      "grad_norm": 0.33877089619636536,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.513,
      "step": 179
    },
    {
      "epoch": 1.3211009174311927,
      "grad_norm": 0.3292918801307678,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5653,
      "step": 180
    },
    {
      "epoch": 1.3284403669724771,
      "grad_norm": 0.353723406791687,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6152,
      "step": 181
    },
    {
      "epoch": 1.3357798165137615,
      "grad_norm": 0.3540942370891571,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5256,
      "step": 182
    },
    {
      "epoch": 1.343119266055046,
      "grad_norm": 0.35959991812705994,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.5788,
      "step": 183
    },
    {
      "epoch": 1.3504587155963304,
      "grad_norm": 0.3470739424228668,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.532,
      "step": 184
    },
    {
      "epoch": 1.3577981651376148,
      "grad_norm": 0.3544631600379944,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5094,
      "step": 185
    },
    {
      "epoch": 1.3651376146788992,
      "grad_norm": 0.3699917197227478,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5299,
      "step": 186
    },
    {
      "epoch": 1.3724770642201836,
      "grad_norm": 0.3642297387123108,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5009,
      "step": 187
    },
    {
      "epoch": 1.379816513761468,
      "grad_norm": 0.372881144285202,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6032,
      "step": 188
    },
    {
      "epoch": 1.3871559633027524,
      "grad_norm": 0.3867509663105011,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.5966,
      "step": 189
    },
    {
      "epoch": 1.3944954128440368,
      "grad_norm": 0.3632262051105499,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5316,
      "step": 190
    },
    {
      "epoch": 1.4018348623853212,
      "grad_norm": 0.3733455240726471,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5655,
      "step": 191
    },
    {
      "epoch": 1.4091743119266056,
      "grad_norm": 0.38948163390159607,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5313,
      "step": 192
    },
    {
      "epoch": 1.41651376146789,
      "grad_norm": 0.3726772964000702,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5965,
      "step": 193
    },
    {
      "epoch": 1.4238532110091744,
      "grad_norm": 0.43320563435554504,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6174,
      "step": 194
    },
    {
      "epoch": 1.4311926605504588,
      "grad_norm": 0.40359145402908325,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6141,
      "step": 195
    },
    {
      "epoch": 1.4385321100917432,
      "grad_norm": 0.4199419319629669,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6782,
      "step": 196
    },
    {
      "epoch": 1.4458715596330276,
      "grad_norm": 0.44166088104248047,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6382,
      "step": 197
    },
    {
      "epoch": 1.453211009174312,
      "grad_norm": 0.43071234226226807,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6485,
      "step": 198
    },
    {
      "epoch": 1.4605504587155964,
      "grad_norm": 0.4428519904613495,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5968,
      "step": 199
    },
    {
      "epoch": 1.4678899082568808,
      "grad_norm": 0.45782530307769775,
      "learning_rate": 0.0,
      "loss": 0.644,
      "step": 200
    },
    {
      "epoch": 1.4678899082568808,
      "eval_loss": 0.6584349274635315,
      "eval_runtime": 7.4244,
      "eval_samples_per_second": 30.979,
      "eval_steps_per_second": 7.812,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.088494791806157e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}