{
  "best_metric": 1.792533040046692,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.6993006993006993,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004662004662004662,
      "grad_norm": 0.4375835657119751,
      "learning_rate": 1e-05,
      "loss": 1.5209,
      "step": 1
    },
    {
      "epoch": 0.004662004662004662,
      "eval_loss": 3.115844488143921,
      "eval_runtime": 10.7207,
      "eval_samples_per_second": 33.673,
      "eval_steps_per_second": 8.488,
      "step": 1
    },
    {
      "epoch": 0.009324009324009324,
      "grad_norm": 0.49615123867988586,
      "learning_rate": 2e-05,
      "loss": 1.5175,
      "step": 2
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 0.5683251619338989,
      "learning_rate": 3e-05,
      "loss": 1.6754,
      "step": 3
    },
    {
      "epoch": 0.018648018648018648,
      "grad_norm": 0.5945281982421875,
      "learning_rate": 4e-05,
      "loss": 1.9437,
      "step": 4
    },
    {
      "epoch": 0.023310023310023312,
      "grad_norm": 0.6417495012283325,
      "learning_rate": 5e-05,
      "loss": 1.7501,
      "step": 5
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.6976508498191833,
      "learning_rate": 6e-05,
      "loss": 1.9262,
      "step": 6
    },
    {
      "epoch": 0.03263403263403263,
      "grad_norm": 0.6939217448234558,
      "learning_rate": 7e-05,
      "loss": 2.0375,
      "step": 7
    },
    {
      "epoch": 0.037296037296037296,
      "grad_norm": 0.7348048090934753,
      "learning_rate": 8e-05,
      "loss": 2.089,
      "step": 8
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 0.7200487852096558,
      "learning_rate": 9e-05,
      "loss": 2.229,
      "step": 9
    },
    {
      "epoch": 0.046620046620046623,
      "grad_norm": 0.744043231010437,
      "learning_rate": 0.0001,
      "loss": 2.2799,
      "step": 10
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.7743932604789734,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.4532,
      "step": 11
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.7929210662841797,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.1635,
      "step": 12
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.6702142953872681,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.2964,
      "step": 13
    },
    {
      "epoch": 0.06526806526806526,
      "grad_norm": 0.6804782152175903,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.2449,
      "step": 14
    },
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 0.6070465445518494,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.9579,
      "step": 15
    },
    {
      "epoch": 0.07459207459207459,
      "grad_norm": 0.6283896565437317,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.9218,
      "step": 16
    },
    {
      "epoch": 0.07925407925407925,
      "grad_norm": 0.6561678647994995,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.1807,
      "step": 17
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 0.7340338826179504,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.113,
      "step": 18
    },
    {
      "epoch": 0.08857808857808858,
      "grad_norm": 0.6012392640113831,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.962,
      "step": 19
    },
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 0.6492958068847656,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.2825,
      "step": 20
    },
    {
      "epoch": 0.0979020979020979,
      "grad_norm": 0.8319525718688965,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.3008,
      "step": 21
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.6819949150085449,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.2583,
      "step": 22
    },
    {
      "epoch": 0.10722610722610723,
      "grad_norm": 0.7541967630386353,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.3178,
      "step": 23
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 0.7257853746414185,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.2379,
      "step": 24
    },
    {
      "epoch": 0.11655011655011654,
      "grad_norm": 0.6871631741523743,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.238,
      "step": 25
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.7202929258346558,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.2557,
      "step": 26
    },
    {
      "epoch": 0.1258741258741259,
      "grad_norm": 0.7082440257072449,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.357,
      "step": 27
    },
    {
      "epoch": 0.13053613053613053,
      "grad_norm": 0.8260137438774109,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.2676,
      "step": 28
    },
    {
      "epoch": 0.1351981351981352,
      "grad_norm": 0.8222116827964783,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3511,
      "step": 29
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 0.8005507588386536,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.101,
      "step": 30
    },
    {
      "epoch": 0.1445221445221445,
      "grad_norm": 0.7329530119895935,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.1017,
      "step": 31
    },
    {
      "epoch": 0.14918414918414918,
      "grad_norm": 0.8081792593002319,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.2719,
      "step": 32
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.770129382610321,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.064,
      "step": 33
    },
    {
      "epoch": 0.1585081585081585,
      "grad_norm": 0.73978590965271,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.3378,
      "step": 34
    },
    {
      "epoch": 0.16317016317016317,
      "grad_norm": 0.8344706892967224,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.2809,
      "step": 35
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 0.8207667469978333,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.5136,
      "step": 36
    },
    {
      "epoch": 0.17249417249417248,
      "grad_norm": 0.8725455403327942,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.4247,
      "step": 37
    },
    {
      "epoch": 0.17715617715617715,
      "grad_norm": 0.8840526342391968,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.3504,
      "step": 38
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.9244182109832764,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.2945,
      "step": 39
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": 0.7929784655570984,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.2753,
      "step": 40
    },
    {
      "epoch": 0.19114219114219114,
      "grad_norm": 0.819206953048706,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.4541,
      "step": 41
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 0.8387634754180908,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.273,
      "step": 42
    },
    {
      "epoch": 0.20046620046620048,
      "grad_norm": 0.9408571124076843,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.3629,
      "step": 43
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.8774721622467041,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.4433,
      "step": 44
    },
    {
      "epoch": 0.2097902097902098,
      "grad_norm": 0.9822505712509155,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.5175,
      "step": 45
    },
    {
      "epoch": 0.21445221445221446,
      "grad_norm": 0.9141904711723328,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.3018,
      "step": 46
    },
    {
      "epoch": 0.2191142191142191,
      "grad_norm": 0.9038905501365662,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.4702,
      "step": 47
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 0.9073315262794495,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.5694,
      "step": 48
    },
    {
      "epoch": 0.22843822843822845,
      "grad_norm": 1.1187613010406494,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.3622,
      "step": 49
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 1.0683103799819946,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.6338,
      "step": 50
    },
    {
      "epoch": 0.2331002331002331,
      "eval_loss": 2.035034418106079,
      "eval_runtime": 10.7297,
      "eval_samples_per_second": 33.645,
      "eval_steps_per_second": 8.481,
      "step": 50
    },
    {
      "epoch": 0.23776223776223776,
      "grad_norm": 0.8205508589744568,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.4091,
      "step": 51
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.7514739632606506,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.3873,
      "step": 52
    },
    {
      "epoch": 0.24708624708624707,
      "grad_norm": 0.7235717177391052,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5742,
      "step": 53
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 0.6290205121040344,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4079,
      "step": 54
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.5443893074989319,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4103,
      "step": 55
    },
    {
      "epoch": 0.26107226107226106,
      "grad_norm": 0.5583277940750122,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.3308,
      "step": 56
    },
    {
      "epoch": 0.26573426573426573,
      "grad_norm": 0.4870063364505768,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.3329,
      "step": 57
    },
    {
      "epoch": 0.2703962703962704,
      "grad_norm": 0.5397898554801941,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5708,
      "step": 58
    },
    {
      "epoch": 0.27505827505827507,
      "grad_norm": 0.509706437587738,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5297,
      "step": 59
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.5184931755065918,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.7365,
      "step": 60
    },
    {
      "epoch": 0.28438228438228436,
      "grad_norm": 0.5428276658058167,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.5407,
      "step": 61
    },
    {
      "epoch": 0.289044289044289,
      "grad_norm": 0.5609496235847473,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.6237,
      "step": 62
    },
    {
      "epoch": 0.2937062937062937,
      "grad_norm": 0.6210252642631531,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6283,
      "step": 63
    },
    {
      "epoch": 0.29836829836829837,
      "grad_norm": 0.5531906485557556,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.6081,
      "step": 64
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.5712310671806335,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.8558,
      "step": 65
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.6507643461227417,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.7259,
      "step": 66
    },
    {
      "epoch": 0.3123543123543124,
      "grad_norm": 0.6221694350242615,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7598,
      "step": 67
    },
    {
      "epoch": 0.317016317016317,
      "grad_norm": 0.6468785405158997,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.8502,
      "step": 68
    },
    {
      "epoch": 0.32167832167832167,
      "grad_norm": 0.6227116584777832,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.798,
      "step": 69
    },
    {
      "epoch": 0.32634032634032634,
      "grad_norm": 0.5716899037361145,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.7745,
      "step": 70
    },
    {
      "epoch": 0.331002331002331,
      "grad_norm": 0.6229769587516785,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.7605,
      "step": 71
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 0.6259751319885254,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.9215,
      "step": 72
    },
    {
      "epoch": 0.34032634032634035,
      "grad_norm": 0.6568538546562195,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.7482,
      "step": 73
    },
    {
      "epoch": 0.34498834498834496,
      "grad_norm": 0.6698790192604065,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.7304,
      "step": 74
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 0.6729266047477722,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.8363,
      "step": 75
    },
    {
      "epoch": 0.3543123543123543,
      "grad_norm": 0.6422204375267029,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.8836,
      "step": 76
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.7767156362533569,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.0069,
      "step": 77
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.6429267525672913,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.9034,
      "step": 78
    },
    {
      "epoch": 0.3682983682983683,
      "grad_norm": 0.7345889806747437,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.0848,
      "step": 79
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 0.7321730256080627,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.0755,
      "step": 80
    },
    {
      "epoch": 0.3776223776223776,
      "grad_norm": 0.7333937883377075,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.2402,
      "step": 81
    },
    {
      "epoch": 0.3822843822843823,
      "grad_norm": 0.7137296795845032,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.992,
      "step": 82
    },
    {
      "epoch": 0.38694638694638694,
      "grad_norm": 0.755987286567688,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.0282,
      "step": 83
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 0.7867782115936279,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.9715,
      "step": 84
    },
    {
      "epoch": 0.3962703962703963,
      "grad_norm": 0.7993813157081604,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.9678,
      "step": 85
    },
    {
      "epoch": 0.40093240093240096,
      "grad_norm": 0.740828812122345,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9705,
      "step": 86
    },
    {
      "epoch": 0.40559440559440557,
      "grad_norm": 0.8410376906394958,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.0066,
      "step": 87
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.7595714330673218,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9163,
      "step": 88
    },
    {
      "epoch": 0.4149184149184149,
      "grad_norm": 0.8600166440010071,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.2047,
      "step": 89
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 0.9230474829673767,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.2662,
      "step": 90
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.8501133322715759,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.2002,
      "step": 91
    },
    {
      "epoch": 0.4289044289044289,
      "grad_norm": 0.8710208535194397,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.2121,
      "step": 92
    },
    {
      "epoch": 0.43356643356643354,
      "grad_norm": 0.8752327561378479,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.3393,
      "step": 93
    },
    {
      "epoch": 0.4382284382284382,
      "grad_norm": 0.8154497146606445,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.1175,
      "step": 94
    },
    {
      "epoch": 0.4428904428904429,
      "grad_norm": 0.8364301919937134,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.2119,
      "step": 95
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 0.9071353077888489,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.3722,
      "step": 96
    },
    {
      "epoch": 0.4522144522144522,
      "grad_norm": 0.8232983946800232,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.174,
      "step": 97
    },
    {
      "epoch": 0.4568764568764569,
      "grad_norm": 1.0158485174179077,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.2335,
      "step": 98
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.9511692523956299,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.3042,
      "step": 99
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 1.0589745044708252,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.3682,
      "step": 100
    },
    {
      "epoch": 0.4662004662004662,
      "eval_loss": 1.8713520765304565,
      "eval_runtime": 10.7623,
      "eval_samples_per_second": 33.543,
      "eval_steps_per_second": 8.455,
      "step": 100
    },
    {
      "epoch": 0.47086247086247085,
      "grad_norm": 0.6302658319473267,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.2328,
      "step": 101
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 0.5877934098243713,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2642,
      "step": 102
    },
    {
      "epoch": 0.4801864801864802,
      "grad_norm": 0.6043432354927063,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.3779,
      "step": 103
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.5296673774719238,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.3788,
      "step": 104
    },
    {
      "epoch": 0.48951048951048953,
      "grad_norm": 0.5024903416633606,
      "learning_rate": 5e-05,
      "loss": 1.3012,
      "step": 105
    },
    {
      "epoch": 0.49417249417249415,
      "grad_norm": 0.5119273066520691,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.3185,
      "step": 106
    },
    {
      "epoch": 0.4988344988344988,
      "grad_norm": 0.4788738191127777,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.3679,
      "step": 107
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 0.5437080264091492,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4681,
      "step": 108
    },
    {
      "epoch": 0.5081585081585082,
      "grad_norm": 0.5525368452072144,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.4913,
      "step": 109
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.5370126366615295,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6615,
      "step": 110
    },
    {
      "epoch": 0.5174825174825175,
      "grad_norm": 0.5269562005996704,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.5188,
      "step": 111
    },
    {
      "epoch": 0.5221445221445221,
      "grad_norm": 0.5016019344329834,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4567,
      "step": 112
    },
    {
      "epoch": 0.5268065268065268,
      "grad_norm": 0.5243374109268188,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.4363,
      "step": 113
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 0.5685271620750427,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.5868,
      "step": 114
    },
    {
      "epoch": 0.5361305361305362,
      "grad_norm": 0.5902321934700012,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.589,
      "step": 115
    },
    {
      "epoch": 0.5407925407925408,
      "grad_norm": 0.5882418155670166,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.7838,
      "step": 116
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.6185193657875061,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.812,
      "step": 117
    },
    {
      "epoch": 0.5501165501165501,
      "grad_norm": 0.6451072692871094,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.8217,
      "step": 118
    },
    {
      "epoch": 0.5547785547785548,
      "grad_norm": 0.632240355014801,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.7533,
      "step": 119
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.6013713479042053,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.6603,
      "step": 120
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.5924433469772339,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.6549,
      "step": 121
    },
    {
      "epoch": 0.5687645687645687,
      "grad_norm": 0.7028740644454956,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.6005,
      "step": 122
    },
    {
      "epoch": 0.5734265734265734,
      "grad_norm": 0.7034977674484253,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.9802,
      "step": 123
    },
    {
      "epoch": 0.578088578088578,
      "grad_norm": 0.7669457197189331,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.8327,
      "step": 124
    },
    {
      "epoch": 0.5827505827505828,
      "grad_norm": 0.6575400233268738,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.8541,
      "step": 125
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 0.7511604428291321,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.7712,
      "step": 126
    },
    {
      "epoch": 0.5920745920745921,
      "grad_norm": 0.8430941104888916,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.1503,
      "step": 127
    },
    {
      "epoch": 0.5967365967365967,
      "grad_norm": 0.6790040135383606,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.9044,
      "step": 128
    },
    {
      "epoch": 0.6013986013986014,
      "grad_norm": 0.6855138540267944,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.8459,
      "step": 129
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.8203029036521912,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.1096,
      "step": 130
    },
    {
      "epoch": 0.6107226107226107,
      "grad_norm": 0.7765827775001526,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.0067,
      "step": 131
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.8429322838783264,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.1071,
      "step": 132
    },
    {
      "epoch": 0.62004662004662,
      "grad_norm": 0.8036541938781738,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.0064,
      "step": 133
    },
    {
      "epoch": 0.6247086247086248,
      "grad_norm": 0.884415328502655,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.2085,
      "step": 134
    },
    {
      "epoch": 0.6293706293706294,
      "grad_norm": 0.7145037055015564,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.9588,
      "step": 135
    },
    {
      "epoch": 0.634032634032634,
      "grad_norm": 0.7449626326560974,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.8609,
      "step": 136
    },
    {
      "epoch": 0.6386946386946387,
      "grad_norm": 0.7585590481758118,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.8423,
      "step": 137
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 0.9376791715621948,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.1774,
      "step": 138
    },
    {
      "epoch": 0.6480186480186481,
      "grad_norm": 0.864797830581665,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.9965,
      "step": 139
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 0.830837607383728,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.9375,
      "step": 140
    },
    {
      "epoch": 0.6573426573426573,
      "grad_norm": 0.8673924803733826,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.1165,
      "step": 141
    },
    {
      "epoch": 0.662004662004662,
      "grad_norm": 0.9556111693382263,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.0692,
      "step": 142
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.939336895942688,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.2542,
      "step": 143
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 0.9361501336097717,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.1401,
      "step": 144
    },
    {
      "epoch": 0.675990675990676,
      "grad_norm": 1.0414737462997437,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.1523,
      "step": 145
    },
    {
      "epoch": 0.6806526806526807,
      "grad_norm": 0.9971078038215637,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.0692,
      "step": 146
    },
    {
      "epoch": 0.6853146853146853,
      "grad_norm": 1.0580642223358154,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.1947,
      "step": 147
    },
    {
      "epoch": 0.6899766899766899,
      "grad_norm": 1.0020278692245483,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.0696,
      "step": 148
    },
    {
      "epoch": 0.6946386946386947,
      "grad_norm": 0.9605817198753357,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.3733,
      "step": 149
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 1.195831298828125,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.2114,
      "step": 150
    },
    {
      "epoch": 0.6993006993006993,
      "eval_loss": 1.792533040046692,
      "eval_runtime": 10.7405,
      "eval_samples_per_second": 33.611,
      "eval_steps_per_second": 8.473,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.96356015734784e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}