{
  "best_metric": 3.023913860321045,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.182648401826484,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009132420091324201,
      "grad_norm": 0.9068623185157776,
      "learning_rate": 1e-05,
      "loss": 3.2522,
      "step": 1
    },
    {
      "epoch": 0.0009132420091324201,
      "eval_loss": 3.5445830821990967,
      "eval_runtime": 32.3947,
      "eval_samples_per_second": 56.954,
      "eval_steps_per_second": 14.262,
      "step": 1
    },
    {
      "epoch": 0.0018264840182648401,
      "grad_norm": 1.1281156539916992,
      "learning_rate": 2e-05,
      "loss": 3.2655,
      "step": 2
    },
    {
      "epoch": 0.0027397260273972603,
      "grad_norm": 1.3832942247390747,
      "learning_rate": 3e-05,
      "loss": 3.2842,
      "step": 3
    },
    {
      "epoch": 0.0036529680365296802,
      "grad_norm": 1.478695273399353,
      "learning_rate": 4e-05,
      "loss": 3.2225,
      "step": 4
    },
    {
      "epoch": 0.0045662100456621,
      "grad_norm": 1.4202985763549805,
      "learning_rate": 5e-05,
      "loss": 3.2515,
      "step": 5
    },
    {
      "epoch": 0.005479452054794521,
      "grad_norm": 1.3425511121749878,
      "learning_rate": 6e-05,
      "loss": 3.2595,
      "step": 6
    },
    {
      "epoch": 0.006392694063926941,
      "grad_norm": 1.5727847814559937,
      "learning_rate": 7e-05,
      "loss": 3.2168,
      "step": 7
    },
    {
      "epoch": 0.0073059360730593605,
      "grad_norm": 1.7487390041351318,
      "learning_rate": 8e-05,
      "loss": 3.2257,
      "step": 8
    },
    {
      "epoch": 0.00821917808219178,
      "grad_norm": 1.5392392873764038,
      "learning_rate": 9e-05,
      "loss": 3.291,
      "step": 9
    },
    {
      "epoch": 0.0091324200913242,
      "grad_norm": 1.3491345643997192,
      "learning_rate": 0.0001,
      "loss": 3.281,
      "step": 10
    },
    {
      "epoch": 0.01004566210045662,
      "grad_norm": 1.273455262184143,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.4268,
      "step": 11
    },
    {
      "epoch": 0.010958904109589041,
      "grad_norm": 1.4522420167922974,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.0992,
      "step": 12
    },
    {
      "epoch": 0.011872146118721462,
      "grad_norm": 1.4894245862960815,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.2222,
      "step": 13
    },
    {
      "epoch": 0.012785388127853882,
      "grad_norm": 1.2837435007095337,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.312,
      "step": 14
    },
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 1.24583899974823,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.2017,
      "step": 15
    },
    {
      "epoch": 0.014611872146118721,
      "grad_norm": 1.3837201595306396,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.3885,
      "step": 16
    },
    {
      "epoch": 0.015525114155251141,
      "grad_norm": 1.1372686624526978,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.1788,
      "step": 17
    },
    {
      "epoch": 0.01643835616438356,
      "grad_norm": 1.1797319650650024,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.1617,
      "step": 18
    },
    {
      "epoch": 0.017351598173515982,
      "grad_norm": 1.166347622871399,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.0896,
      "step": 19
    },
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 1.1477808952331543,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.0875,
      "step": 20
    },
    {
      "epoch": 0.019178082191780823,
      "grad_norm": 1.1526598930358887,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.1399,
      "step": 21
    },
    {
      "epoch": 0.02009132420091324,
      "grad_norm": 1.3330358266830444,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.0634,
      "step": 22
    },
    {
      "epoch": 0.021004566210045664,
      "grad_norm": 1.1741523742675781,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.1905,
      "step": 23
    },
    {
      "epoch": 0.021917808219178082,
      "grad_norm": 1.3173130750656128,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.1599,
      "step": 24
    },
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 1.198370337486267,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.0383,
      "step": 25
    },
    {
      "epoch": 0.023744292237442923,
      "grad_norm": 1.218273639678955,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.0519,
      "step": 26
    },
    {
      "epoch": 0.024657534246575342,
      "grad_norm": 1.3507483005523682,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.9643,
      "step": 27
    },
    {
      "epoch": 0.025570776255707764,
      "grad_norm": 1.446865439414978,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.0647,
      "step": 28
    },
    {
      "epoch": 0.026484018264840183,
      "grad_norm": 1.4162113666534424,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8765,
      "step": 29
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 1.3771593570709229,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.0771,
      "step": 30
    },
    {
      "epoch": 0.028310502283105023,
      "grad_norm": 1.3835033178329468,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.082,
      "step": 31
    },
    {
      "epoch": 0.029223744292237442,
      "grad_norm": 1.330958366394043,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.1529,
      "step": 32
    },
    {
      "epoch": 0.030136986301369864,
      "grad_norm": 1.3230454921722412,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.9249,
      "step": 33
    },
    {
      "epoch": 0.031050228310502283,
      "grad_norm": 1.443698525428772,
      "learning_rate": 9.611448774886924e-05,
      "loss": 3.0653,
      "step": 34
    },
    {
      "epoch": 0.0319634703196347,
      "grad_norm": 1.4325252771377563,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.995,
      "step": 35
    },
    {
      "epoch": 0.03287671232876712,
      "grad_norm": 1.4370254278182983,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.1017,
      "step": 36
    },
    {
      "epoch": 0.033789954337899546,
      "grad_norm": 1.44560968875885,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.941,
      "step": 37
    },
    {
      "epoch": 0.034703196347031964,
      "grad_norm": 1.492517113685608,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.1078,
      "step": 38
    },
    {
      "epoch": 0.03561643835616438,
      "grad_norm": 1.5231863260269165,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.9672,
      "step": 39
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 1.6273531913757324,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.0558,
      "step": 40
    },
    {
      "epoch": 0.03744292237442922,
      "grad_norm": 1.6793463230133057,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.1755,
      "step": 41
    },
    {
      "epoch": 0.038356164383561646,
      "grad_norm": 1.674794316291809,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.8346,
      "step": 42
    },
    {
      "epoch": 0.039269406392694065,
      "grad_norm": 1.8198087215423584,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.1409,
      "step": 43
    },
    {
      "epoch": 0.04018264840182648,
      "grad_norm": 2.1863255500793457,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.0302,
      "step": 44
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 1.8364160060882568,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.8498,
      "step": 45
    },
    {
      "epoch": 0.04200913242009133,
      "grad_norm": 2.2227354049682617,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.0885,
      "step": 46
    },
    {
      "epoch": 0.042922374429223746,
      "grad_norm": 2.2997303009033203,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.2166,
      "step": 47
    },
    {
      "epoch": 0.043835616438356165,
      "grad_norm": 2.5768418312072754,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.0516,
      "step": 48
    },
    {
      "epoch": 0.04474885844748858,
      "grad_norm": 3.761918306350708,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.5271,
      "step": 49
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 11.200986862182617,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.6347,
      "step": 50
    },
    {
      "epoch": 0.045662100456621,
      "eval_loss": 3.376133441925049,
      "eval_runtime": 32.4398,
      "eval_samples_per_second": 56.875,
      "eval_steps_per_second": 14.242,
      "step": 50
    },
    {
      "epoch": 0.04657534246575343,
      "grad_norm": 4.808338165283203,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.5087,
      "step": 51
    },
    {
      "epoch": 0.047488584474885846,
      "grad_norm": 5.594576358795166,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.5913,
      "step": 52
    },
    {
      "epoch": 0.048401826484018265,
      "grad_norm": 5.090969085693359,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.4399,
      "step": 53
    },
    {
      "epoch": 0.049315068493150684,
      "grad_norm": 4.2716264724731445,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.2379,
      "step": 54
    },
    {
      "epoch": 0.0502283105022831,
      "grad_norm": 2.886751890182495,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.1248,
      "step": 55
    },
    {
      "epoch": 0.05114155251141553,
      "grad_norm": 1.7806824445724487,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.2299,
      "step": 56
    },
    {
      "epoch": 0.052054794520547946,
      "grad_norm": 1.282745361328125,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.1423,
      "step": 57
    },
    {
      "epoch": 0.052968036529680365,
      "grad_norm": 1.1537902355194092,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.9739,
      "step": 58
    },
    {
      "epoch": 0.053881278538812784,
      "grad_norm": 1.1167031526565552,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.1321,
      "step": 59
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 1.0587337017059326,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.0294,
      "step": 60
    },
    {
      "epoch": 0.05570776255707763,
      "grad_norm": 1.1291835308074951,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.1252,
      "step": 61
    },
    {
      "epoch": 0.05662100456621005,
      "grad_norm": 1.1141999959945679,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.0831,
      "step": 62
    },
    {
      "epoch": 0.057534246575342465,
      "grad_norm": 1.3142082691192627,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.0741,
      "step": 63
    },
    {
      "epoch": 0.058447488584474884,
      "grad_norm": 1.1393654346466064,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.221,
      "step": 64
    },
    {
      "epoch": 0.0593607305936073,
      "grad_norm": 1.150147795677185,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.257,
      "step": 65
    },
    {
      "epoch": 0.06027397260273973,
      "grad_norm": 1.06666898727417,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.2591,
      "step": 66
    },
    {
      "epoch": 0.06118721461187215,
      "grad_norm": 1.019217610359192,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.0847,
      "step": 67
    },
    {
      "epoch": 0.062100456621004566,
      "grad_norm": 1.023451805114746,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.0742,
      "step": 68
    },
    {
      "epoch": 0.06301369863013699,
      "grad_norm": 1.0833603143692017,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.0772,
      "step": 69
    },
    {
      "epoch": 0.0639269406392694,
      "grad_norm": 1.134100317955017,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.2349,
      "step": 70
    },
    {
      "epoch": 0.06484018264840183,
      "grad_norm": 1.0719058513641357,
      "learning_rate": 7.66515864363997e-05,
      "loss": 3.0077,
      "step": 71
    },
    {
      "epoch": 0.06575342465753424,
      "grad_norm": 1.0817437171936035,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.954,
      "step": 72
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 1.079461932182312,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.7787,
      "step": 73
    },
    {
      "epoch": 0.06757990867579909,
      "grad_norm": 1.149514079093933,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.1859,
      "step": 74
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.0964784622192383,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.0383,
      "step": 75
    },
    {
      "epoch": 0.06940639269406393,
      "grad_norm": 1.0799715518951416,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.9711,
      "step": 76
    },
    {
      "epoch": 0.07031963470319634,
      "grad_norm": 1.116867184638977,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.0287,
      "step": 77
    },
    {
      "epoch": 0.07123287671232877,
      "grad_norm": 1.1790772676467896,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.0856,
      "step": 78
    },
    {
      "epoch": 0.07214611872146119,
      "grad_norm": 1.1719294786453247,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.8277,
      "step": 79
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 1.1619611978530884,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.0837,
      "step": 80
    },
    {
      "epoch": 0.07397260273972603,
      "grad_norm": 1.2149782180786133,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.9401,
      "step": 81
    },
    {
      "epoch": 0.07488584474885844,
      "grad_norm": 1.288072943687439,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.9792,
      "step": 82
    },
    {
      "epoch": 0.07579908675799087,
      "grad_norm": 1.226742148399353,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.9903,
      "step": 83
    },
    {
      "epoch": 0.07671232876712329,
      "grad_norm": 1.2244426012039185,
      "learning_rate": 6.701465872208216e-05,
      "loss": 3.0023,
      "step": 84
    },
    {
      "epoch": 0.0776255707762557,
      "grad_norm": 1.3277724981307983,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.011,
      "step": 85
    },
    {
      "epoch": 0.07853881278538813,
      "grad_norm": 1.3661189079284668,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.0236,
      "step": 86
    },
    {
      "epoch": 0.07945205479452055,
      "grad_norm": 1.337944507598877,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.0388,
      "step": 87
    },
    {
      "epoch": 0.08036529680365297,
      "grad_norm": 1.5280866622924805,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.9955,
      "step": 88
    },
    {
      "epoch": 0.08127853881278539,
      "grad_norm": 1.4344313144683838,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.1413,
      "step": 89
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 1.4747999906539917,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.8809,
      "step": 90
    },
    {
      "epoch": 0.08310502283105023,
      "grad_norm": 1.4497511386871338,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.8993,
      "step": 91
    },
    {
      "epoch": 0.08401826484018265,
      "grad_norm": 1.5439262390136719,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.8546,
      "step": 92
    },
    {
      "epoch": 0.08493150684931507,
      "grad_norm": 1.6409767866134644,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.6857,
      "step": 93
    },
    {
      "epoch": 0.08584474885844749,
      "grad_norm": 1.9150443077087402,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.0404,
      "step": 94
    },
    {
      "epoch": 0.0867579908675799,
      "grad_norm": 1.8457553386688232,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.9445,
      "step": 95
    },
    {
      "epoch": 0.08767123287671233,
      "grad_norm": 3.1176164150238037,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.9672,
      "step": 96
    },
    {
      "epoch": 0.08858447488584476,
      "grad_norm": 2.4358506202697754,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.2204,
      "step": 97
    },
    {
      "epoch": 0.08949771689497717,
      "grad_norm": 2.7741899490356445,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.3525,
      "step": 98
    },
    {
      "epoch": 0.09041095890410959,
      "grad_norm": 3.765840530395508,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.4315,
      "step": 99
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 7.203201770782471,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.4689,
      "step": 100
    },
    {
      "epoch": 0.091324200913242,
      "eval_loss": 3.204030752182007,
      "eval_runtime": 32.5213,
      "eval_samples_per_second": 56.732,
      "eval_steps_per_second": 14.206,
      "step": 100
    },
    {
      "epoch": 0.09223744292237443,
      "grad_norm": 3.1064207553863525,
      "learning_rate": 5.330452921628497e-05,
      "loss": 3.4169,
      "step": 101
    },
    {
      "epoch": 0.09315068493150686,
      "grad_norm": 3.938171863555908,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.3387,
      "step": 102
    },
    {
      "epoch": 0.09406392694063927,
      "grad_norm": 3.6096322536468506,
      "learning_rate": 5.165316846586541e-05,
      "loss": 3.3848,
      "step": 103
    },
    {
      "epoch": 0.09497716894977169,
      "grad_norm": 3.3269453048706055,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 3.2175,
      "step": 104
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 2.7610254287719727,
      "learning_rate": 5e-05,
      "loss": 3.0796,
      "step": 105
    },
    {
      "epoch": 0.09680365296803653,
      "grad_norm": 2.1624197959899902,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.2041,
      "step": 106
    },
    {
      "epoch": 0.09771689497716896,
      "grad_norm": 1.5809886455535889,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.0594,
      "step": 107
    },
    {
      "epoch": 0.09863013698630137,
      "grad_norm": 1.171734094619751,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.179,
      "step": 108
    },
    {
      "epoch": 0.09954337899543379,
      "grad_norm": 1.0622243881225586,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.1644,
      "step": 109
    },
    {
      "epoch": 0.1004566210045662,
      "grad_norm": 0.9763745665550232,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.1996,
      "step": 110
    },
    {
      "epoch": 0.10136986301369863,
      "grad_norm": 1.0023770332336426,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.0118,
      "step": 111
    },
    {
      "epoch": 0.10228310502283106,
      "grad_norm": 0.9458981156349182,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.0865,
      "step": 112
    },
    {
      "epoch": 0.10319634703196347,
      "grad_norm": 0.9863345623016357,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.0516,
      "step": 113
    },
    {
      "epoch": 0.10410958904109589,
      "grad_norm": 0.9894965291023254,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.0284,
      "step": 114
    },
    {
      "epoch": 0.1050228310502283,
      "grad_norm": 1.008941411972046,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.0521,
      "step": 115
    },
    {
      "epoch": 0.10593607305936073,
      "grad_norm": 1.0216481685638428,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.0811,
      "step": 116
    },
    {
      "epoch": 0.10684931506849316,
      "grad_norm": 0.9790635108947754,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.0093,
      "step": 117
    },
    {
      "epoch": 0.10776255707762557,
      "grad_norm": 1.0701838731765747,
      "learning_rate": 3.933501846281267e-05,
      "loss": 3.1578,
      "step": 118
    },
    {
      "epoch": 0.108675799086758,
      "grad_norm": 0.9842221736907959,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.9717,
      "step": 119
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 1.0447992086410522,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.1135,
      "step": 120
    },
    {
      "epoch": 0.11050228310502283,
      "grad_norm": 0.9919024705886841,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.0546,
      "step": 121
    },
    {
      "epoch": 0.11141552511415526,
      "grad_norm": 1.03241765499115,
      "learning_rate": 3.612985456190778e-05,
      "loss": 3.1275,
      "step": 122
    },
    {
      "epoch": 0.11232876712328767,
      "grad_norm": 1.0224878787994385,
      "learning_rate": 3.533749813077677e-05,
      "loss": 3.0389,
      "step": 123
    },
    {
      "epoch": 0.1132420091324201,
      "grad_norm": 1.0672824382781982,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.0965,
      "step": 124
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 1.0666608810424805,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.9358,
      "step": 125
    },
    {
      "epoch": 0.11506849315068493,
      "grad_norm": 1.0773050785064697,
      "learning_rate": 3.298534127791785e-05,
      "loss": 3.0865,
      "step": 126
    },
    {
      "epoch": 0.11598173515981736,
      "grad_norm": 1.1034908294677734,
      "learning_rate": 3.221030765387417e-05,
      "loss": 3.0675,
      "step": 127
    },
    {
      "epoch": 0.11689497716894977,
      "grad_norm": 1.128351092338562,
      "learning_rate": 3.144013755408895e-05,
      "loss": 3.0664,
      "step": 128
    },
    {
      "epoch": 0.1178082191780822,
      "grad_norm": 1.1182414293289185,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.8267,
      "step": 129
    },
    {
      "epoch": 0.1187214611872146,
      "grad_norm": 1.194542646408081,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.0075,
      "step": 130
    },
    {
      "epoch": 0.11963470319634703,
      "grad_norm": 1.1700336933135986,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.9288,
      "step": 131
    },
    {
      "epoch": 0.12054794520547946,
      "grad_norm": 1.2209653854370117,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.0185,
      "step": 132
    },
    {
      "epoch": 0.12146118721461187,
      "grad_norm": 1.2434297800064087,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.9685,
      "step": 133
    },
    {
      "epoch": 0.1223744292237443,
      "grad_norm": 1.2368055582046509,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.973,
      "step": 134
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 1.2635014057159424,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.0592,
      "step": 135
    },
    {
      "epoch": 0.12420091324200913,
      "grad_norm": 1.2338664531707764,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.9675,
      "step": 136
    },
    {
      "epoch": 0.12511415525114156,
      "grad_norm": 1.3074524402618408,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.8732,
      "step": 137
    },
    {
      "epoch": 0.12602739726027398,
      "grad_norm": 1.3928890228271484,
      "learning_rate": 2.405152131093926e-05,
      "loss": 3.1138,
      "step": 138
    },
    {
      "epoch": 0.12694063926940638,
      "grad_norm": 1.44473397731781,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.9951,
      "step": 139
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 1.4934630393981934,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.8359,
      "step": 140
    },
    {
      "epoch": 0.12876712328767123,
      "grad_norm": 1.4810824394226074,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.9315,
      "step": 141
    },
    {
      "epoch": 0.12968036529680366,
      "grad_norm": 1.5166199207305908,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.8097,
      "step": 142
    },
    {
      "epoch": 0.13059360730593608,
      "grad_norm": 1.63760244846344,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.0578,
      "step": 143
    },
    {
      "epoch": 0.13150684931506848,
      "grad_norm": 1.7715166807174683,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.254,
      "step": 144
    },
    {
      "epoch": 0.1324200913242009,
      "grad_norm": 1.7834426164627075,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.7702,
      "step": 145
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.9994410276412964,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.1353,
      "step": 146
    },
    {
      "epoch": 0.13424657534246576,
      "grad_norm": 2.126396417617798,
      "learning_rate": 1.800157297483417e-05,
      "loss": 3.1682,
      "step": 147
    },
    {
      "epoch": 0.13515981735159818,
      "grad_norm": 2.8418822288513184,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 3.4917,
      "step": 148
    },
    {
      "epoch": 0.13607305936073058,
      "grad_norm": 3.5221149921417236,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 3.3658,
      "step": 149
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 6.702593803405762,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.631,
      "step": 150
    },
    {
      "epoch": 0.136986301369863,
      "eval_loss": 3.0353729724884033,
      "eval_runtime": 32.5217,
      "eval_samples_per_second": 56.731,
      "eval_steps_per_second": 14.206,
      "step": 150
    },
    {
      "epoch": 0.13789954337899543,
      "grad_norm": 0.801619827747345,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.1243,
      "step": 151
    },
    {
      "epoch": 0.13881278538812786,
      "grad_norm": 0.9424443244934082,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.2188,
      "step": 152
    },
    {
      "epoch": 0.13972602739726028,
      "grad_norm": 1.0036393404006958,
      "learning_rate": 1.435357758543015e-05,
      "loss": 3.1708,
      "step": 153
    },
    {
      "epoch": 0.14063926940639268,
      "grad_norm": 1.020045280456543,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 3.003,
      "step": 154
    },
    {
      "epoch": 0.1415525114155251,
      "grad_norm": 1.0738372802734375,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.9596,
      "step": 155
    },
    {
      "epoch": 0.14246575342465753,
      "grad_norm": 1.0767014026641846,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.9769,
      "step": 156
    },
    {
      "epoch": 0.14337899543378996,
      "grad_norm": 1.0650362968444824,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 3.0826,
      "step": 157
    },
    {
      "epoch": 0.14429223744292238,
      "grad_norm": 1.0221047401428223,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.9668,
      "step": 158
    },
    {
      "epoch": 0.14520547945205478,
      "grad_norm": 1.0178636312484741,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.9944,
      "step": 159
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.9979190826416016,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.118,
      "step": 160
    },
    {
      "epoch": 0.14703196347031963,
      "grad_norm": 1.0110697746276855,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 3.2159,
      "step": 161
    },
    {
      "epoch": 0.14794520547945206,
      "grad_norm": 0.9642910361289978,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.0488,
      "step": 162
    },
    {
      "epoch": 0.14885844748858448,
      "grad_norm": 0.9357563257217407,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.9615,
      "step": 163
    },
    {
      "epoch": 0.14977168949771688,
      "grad_norm": 0.9772146344184875,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.1948,
      "step": 164
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.9693437218666077,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.0235,
      "step": 165
    },
    {
      "epoch": 0.15159817351598173,
      "grad_norm": 0.9571791887283325,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.1533,
      "step": 166
    },
    {
      "epoch": 0.15251141552511416,
      "grad_norm": 0.9739653468132019,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.2319,
      "step": 167
    },
    {
      "epoch": 0.15342465753424658,
      "grad_norm": 0.9877220392227173,
      "learning_rate": 6.837175952121306e-06,
      "loss": 3.2334,
      "step": 168
    },
    {
      "epoch": 0.154337899543379,
      "grad_norm": 1.0074142217636108,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.076,
      "step": 169
    },
    {
      "epoch": 0.1552511415525114,
      "grad_norm": 0.9896501302719116,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.2152,
      "step": 170
    },
    {
      "epoch": 0.15616438356164383,
      "grad_norm": 0.9626983404159546,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.037,
      "step": 171
    },
    {
      "epoch": 0.15707762557077626,
      "grad_norm": 0.983116090297699,
      "learning_rate": 5.263533508961827e-06,
      "loss": 3.027,
      "step": 172
    },
    {
      "epoch": 0.15799086757990868,
      "grad_norm": 1.0183579921722412,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.027,
      "step": 173
    },
    {
      "epoch": 0.1589041095890411,
      "grad_norm": 1.0004000663757324,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.8328,
      "step": 174
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 1.033658504486084,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.964,
      "step": 175
    },
    {
      "epoch": 0.16073059360730593,
      "grad_norm": 1.045946717262268,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.9764,
      "step": 176
    },
    {
      "epoch": 0.16164383561643836,
      "grad_norm": 1.0732818841934204,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.0671,
      "step": 177
    },
    {
      "epoch": 0.16255707762557078,
      "grad_norm": 1.1134257316589355,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.0076,
      "step": 178
    },
    {
      "epoch": 0.1634703196347032,
      "grad_norm": 1.1153031587600708,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.9405,
      "step": 179
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 1.1565691232681274,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.9939,
      "step": 180
    },
    {
      "epoch": 0.16529680365296803,
      "grad_norm": 1.1723369359970093,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.9056,
      "step": 181
    },
    {
      "epoch": 0.16621004566210046,
      "grad_norm": 1.1096471548080444,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.9163,
      "step": 182
    },
    {
      "epoch": 0.16712328767123288,
      "grad_norm": 1.1584538221359253,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.8178,
      "step": 183
    },
    {
      "epoch": 0.1680365296803653,
      "grad_norm": 1.1778326034545898,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 3.0308,
      "step": 184
    },
    {
      "epoch": 0.1689497716894977,
      "grad_norm": 1.1874874830245972,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.9698,
      "step": 185
    },
    {
      "epoch": 0.16986301369863013,
      "grad_norm": 1.2491706609725952,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.7782,
      "step": 186
    },
    {
      "epoch": 0.17077625570776256,
      "grad_norm": 1.2878979444503784,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 3.0038,
      "step": 187
    },
    {
      "epoch": 0.17168949771689498,
      "grad_norm": 1.3031625747680664,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.8438,
      "step": 188
    },
    {
      "epoch": 0.1726027397260274,
      "grad_norm": 1.4007648229599,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.8835,
      "step": 189
    },
    {
      "epoch": 0.1735159817351598,
      "grad_norm": 1.4737303256988525,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.0548,
      "step": 190
    },
    {
      "epoch": 0.17442922374429223,
      "grad_norm": 1.5961741209030151,
      "learning_rate": 5.526064699265753e-07,
      "loss": 3.1415,
      "step": 191
    },
    {
      "epoch": 0.17534246575342466,
      "grad_norm": 1.5274404287338257,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.8456,
      "step": 192
    },
    {
      "epoch": 0.17625570776255708,
      "grad_norm": 1.5790578126907349,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.857,
      "step": 193
    },
    {
      "epoch": 0.1771689497716895,
      "grad_norm": 1.716803789138794,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.9838,
      "step": 194
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 1.75033700466156,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.0708,
      "step": 195
    },
    {
      "epoch": 0.17899543378995433,
      "grad_norm": 1.9834656715393066,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 3.055,
      "step": 196
    },
    {
      "epoch": 0.17990867579908676,
      "grad_norm": 2.300001382827759,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.3217,
      "step": 197
    },
    {
      "epoch": 0.18082191780821918,
      "grad_norm": 2.847092390060425,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.4746,
      "step": 198
    },
    {
      "epoch": 0.1817351598173516,
      "grad_norm": 3.9122302532196045,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.4704,
      "step": 199
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 9.093494415283203,
      "learning_rate": 0.0,
      "loss": 3.715,
      "step": 200
    },
    {
      "epoch": 0.182648401826484,
      "eval_loss": 3.023913860321045,
      "eval_runtime": 32.4977,
      "eval_samples_per_second": 56.773,
      "eval_steps_per_second": 14.216,
      "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": 1.555357089398784e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}