{
  "best_metric": 0.5550929307937622,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.4184397163120568,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 8.05357837677002,
      "learning_rate": 1e-05,
      "loss": 2.5463,
      "step": 1
    },
    {
      "epoch": 0.0070921985815602835,
      "eval_loss": 3.0699386596679688,
      "eval_runtime": 4.7582,
      "eval_samples_per_second": 50.019,
      "eval_steps_per_second": 12.61,
      "step": 1
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 10.838326454162598,
      "learning_rate": 2e-05,
      "loss": 2.79,
      "step": 2
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 8.85204792022705,
      "learning_rate": 3e-05,
      "loss": 2.7062,
      "step": 3
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 4.852919578552246,
      "learning_rate": 4e-05,
      "loss": 2.6851,
      "step": 4
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 4.499677658081055,
      "learning_rate": 5e-05,
      "loss": 2.4067,
      "step": 5
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 4.731116771697998,
      "learning_rate": 6e-05,
      "loss": 2.4972,
      "step": 6
    },
    {
      "epoch": 0.04964539007092199,
      "grad_norm": 3.367246150970459,
      "learning_rate": 7e-05,
      "loss": 2.176,
      "step": 7
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 2.1521012783050537,
      "learning_rate": 8e-05,
      "loss": 1.8984,
      "step": 8
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 2.3264524936676025,
      "learning_rate": 9e-05,
      "loss": 1.8045,
      "step": 9
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 2.074296236038208,
      "learning_rate": 0.0001,
      "loss": 1.5394,
      "step": 10
    },
    {
      "epoch": 0.07801418439716312,
      "grad_norm": 2.067852735519409,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4358,
      "step": 11
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 1.765109896659851,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2752,
      "step": 12
    },
    {
      "epoch": 0.09219858156028368,
      "grad_norm": 1.8644369840621948,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1874,
      "step": 13
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 1.5777784585952759,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1035,
      "step": 14
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 1.6741243600845337,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.04,
      "step": 15
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 1.3801331520080566,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0535,
      "step": 16
    },
    {
      "epoch": 0.12056737588652482,
      "grad_norm": 1.2960208654403687,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9674,
      "step": 17
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 1.146315097808838,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9224,
      "step": 18
    },
    {
      "epoch": 0.1347517730496454,
      "grad_norm": 1.3943123817443848,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8943,
      "step": 19
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 1.0280953645706177,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.779,
      "step": 20
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 1.1355559825897217,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8361,
      "step": 21
    },
    {
      "epoch": 0.15602836879432624,
      "grad_norm": 1.0945531129837036,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7334,
      "step": 22
    },
    {
      "epoch": 0.16312056737588654,
      "grad_norm": 1.1994026899337769,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6122,
      "step": 23
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.8883627653121948,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5611,
      "step": 24
    },
    {
      "epoch": 0.1773049645390071,
      "grad_norm": 0.9672736525535583,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5966,
      "step": 25
    },
    {
      "epoch": 0.18439716312056736,
      "grad_norm": 1.0175507068634033,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5375,
      "step": 26
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 0.8878077864646912,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4385,
      "step": 27
    },
    {
      "epoch": 0.19858156028368795,
      "grad_norm": 1.0303905010223389,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4613,
      "step": 28
    },
    {
      "epoch": 0.20567375886524822,
      "grad_norm": 0.9411659836769104,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4759,
      "step": 29
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.9171887636184692,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4398,
      "step": 30
    },
    {
      "epoch": 0.2198581560283688,
      "grad_norm": 0.8607805967330933,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4089,
      "step": 31
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.9131023287773132,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4104,
      "step": 32
    },
    {
      "epoch": 0.23404255319148937,
      "grad_norm": 1.23581063747406,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4628,
      "step": 33
    },
    {
      "epoch": 0.24113475177304963,
      "grad_norm": 1.4086484909057617,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3627,
      "step": 34
    },
    {
      "epoch": 0.24822695035460993,
      "grad_norm": 6.753032207489014,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.771,
      "step": 35
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 2.011505365371704,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.4407,
      "step": 36
    },
    {
      "epoch": 0.2624113475177305,
      "grad_norm": 1.8137774467468262,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.315,
      "step": 37
    },
    {
      "epoch": 0.2695035460992908,
      "grad_norm": 1.5304665565490723,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.1503,
      "step": 38
    },
    {
      "epoch": 0.2765957446808511,
      "grad_norm": 1.1797360181808472,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1155,
      "step": 39
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 1.039712905883789,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0547,
      "step": 40
    },
    {
      "epoch": 0.2907801418439716,
      "grad_norm": 0.9909119606018066,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9739,
      "step": 41
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 0.9350584745407104,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9576,
      "step": 42
    },
    {
      "epoch": 0.3049645390070922,
      "grad_norm": 0.9247877597808838,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8348,
      "step": 43
    },
    {
      "epoch": 0.3120567375886525,
      "grad_norm": 0.8802565932273865,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8251,
      "step": 44
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.8769276142120361,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8402,
      "step": 45
    },
    {
      "epoch": 0.3262411347517731,
      "grad_norm": 0.8504616618156433,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7801,
      "step": 46
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.8093395829200745,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.799,
      "step": 47
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.8495473265647888,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8004,
      "step": 48
    },
    {
      "epoch": 0.3475177304964539,
      "grad_norm": 0.8172727227210999,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.747,
      "step": 49
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 0.8406370282173157,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7108,
      "step": 50
    },
    {
      "epoch": 0.3546099290780142,
      "eval_loss": 0.6801980137825012,
      "eval_runtime": 4.7673,
      "eval_samples_per_second": 49.923,
      "eval_steps_per_second": 12.586,
      "step": 50
    },
    {
      "epoch": 0.3617021276595745,
      "grad_norm": 0.764500617980957,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5958,
      "step": 51
    },
    {
      "epoch": 0.36879432624113473,
      "grad_norm": 0.8594017624855042,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6416,
      "step": 52
    },
    {
      "epoch": 0.375886524822695,
      "grad_norm": 0.8616093397140503,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6171,
      "step": 53
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 0.8169087767601013,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6634,
      "step": 54
    },
    {
      "epoch": 0.3900709219858156,
      "grad_norm": 0.8082086443901062,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5689,
      "step": 55
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.7250106930732727,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5487,
      "step": 56
    },
    {
      "epoch": 0.40425531914893614,
      "grad_norm": 0.8334801197052002,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5422,
      "step": 57
    },
    {
      "epoch": 0.41134751773049644,
      "grad_norm": 0.8466203808784485,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5634,
      "step": 58
    },
    {
      "epoch": 0.41843971631205673,
      "grad_norm": 0.6738994121551514,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.416,
      "step": 59
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.685225784778595,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4565,
      "step": 60
    },
    {
      "epoch": 0.4326241134751773,
      "grad_norm": 0.7276149988174438,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4568,
      "step": 61
    },
    {
      "epoch": 0.4397163120567376,
      "grad_norm": 0.7686889171600342,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4216,
      "step": 62
    },
    {
      "epoch": 0.44680851063829785,
      "grad_norm": 0.7390680909156799,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3804,
      "step": 63
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 0.6119396686553955,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3465,
      "step": 64
    },
    {
      "epoch": 0.46099290780141844,
      "grad_norm": 0.7658885717391968,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4185,
      "step": 65
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 0.6248570680618286,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3154,
      "step": 66
    },
    {
      "epoch": 0.475177304964539,
      "grad_norm": 0.7547570466995239,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3711,
      "step": 67
    },
    {
      "epoch": 0.48226950354609927,
      "grad_norm": 0.8419597148895264,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.331,
      "step": 68
    },
    {
      "epoch": 0.48936170212765956,
      "grad_norm": 1.0954856872558594,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3504,
      "step": 69
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 4.436848163604736,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5475,
      "step": 70
    },
    {
      "epoch": 0.5035460992907801,
      "grad_norm": 1.220984935760498,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2138,
      "step": 71
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 1.1256914138793945,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.031,
      "step": 72
    },
    {
      "epoch": 0.5177304964539007,
      "grad_norm": 1.0466660261154175,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0315,
      "step": 73
    },
    {
      "epoch": 0.524822695035461,
      "grad_norm": 0.9186965227127075,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9771,
      "step": 74
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 0.78371661901474,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8715,
      "step": 75
    },
    {
      "epoch": 0.5390070921985816,
      "grad_norm": 0.7783875465393066,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9333,
      "step": 76
    },
    {
      "epoch": 0.5460992907801419,
      "grad_norm": 0.7499712109565735,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8841,
      "step": 77
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 0.7532545328140259,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8294,
      "step": 78
    },
    {
      "epoch": 0.5602836879432624,
      "grad_norm": 0.6495918035507202,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7184,
      "step": 79
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.7577716112136841,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7317,
      "step": 80
    },
    {
      "epoch": 0.574468085106383,
      "grad_norm": 0.7226397395133972,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7158,
      "step": 81
    },
    {
      "epoch": 0.5815602836879432,
      "grad_norm": 0.7062472701072693,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7555,
      "step": 82
    },
    {
      "epoch": 0.5886524822695035,
      "grad_norm": 0.7153007984161377,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6622,
      "step": 83
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.7236975431442261,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6507,
      "step": 84
    },
    {
      "epoch": 0.6028368794326241,
      "grad_norm": 0.6651884913444519,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6209,
      "step": 85
    },
    {
      "epoch": 0.6099290780141844,
      "grad_norm": 0.6654047966003418,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5769,
      "step": 86
    },
    {
      "epoch": 0.6170212765957447,
      "grad_norm": 0.6003665924072266,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5082,
      "step": 87
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 0.7228586673736572,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6009,
      "step": 88
    },
    {
      "epoch": 0.6312056737588653,
      "grad_norm": 0.6803051233291626,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5428,
      "step": 89
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.714916467666626,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4958,
      "step": 90
    },
    {
      "epoch": 0.6453900709219859,
      "grad_norm": 0.6927108764648438,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5062,
      "step": 91
    },
    {
      "epoch": 0.6524822695035462,
      "grad_norm": 0.7170802354812622,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4642,
      "step": 92
    },
    {
      "epoch": 0.6595744680851063,
      "grad_norm": 0.6946068406105042,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4154,
      "step": 93
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.7123287916183472,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.4838,
      "step": 94
    },
    {
      "epoch": 0.6737588652482269,
      "grad_norm": 0.6604336500167847,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4114,
      "step": 95
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.7255561351776123,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3689,
      "step": 96
    },
    {
      "epoch": 0.6879432624113475,
      "grad_norm": 0.7515962719917297,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4193,
      "step": 97
    },
    {
      "epoch": 0.6950354609929078,
      "grad_norm": 0.5581212639808655,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3111,
      "step": 98
    },
    {
      "epoch": 0.7021276595744681,
      "grad_norm": 0.6331417560577393,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3859,
      "step": 99
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.6088494062423706,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3138,
      "step": 100
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 0.6135360598564148,
      "eval_runtime": 4.7671,
      "eval_samples_per_second": 49.926,
      "eval_steps_per_second": 12.586,
      "step": 100
    },
    {
      "epoch": 0.7163120567375887,
      "grad_norm": 0.72311931848526,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3679,
      "step": 101
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 0.774229884147644,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3399,
      "step": 102
    },
    {
      "epoch": 0.7304964539007093,
      "grad_norm": 0.7326410412788391,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2171,
      "step": 103
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 1.004658579826355,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2633,
      "step": 104
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 3.270434617996216,
      "learning_rate": 5e-05,
      "loss": 0.4722,
      "step": 105
    },
    {
      "epoch": 0.75177304964539,
      "grad_norm": 1.1170271635055542,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.1038,
      "step": 106
    },
    {
      "epoch": 0.7588652482269503,
      "grad_norm": 1.0157475471496582,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0103,
      "step": 107
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.9804872870445251,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.0137,
      "step": 108
    },
    {
      "epoch": 0.7730496453900709,
      "grad_norm": 0.8220306634902954,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8287,
      "step": 109
    },
    {
      "epoch": 0.7801418439716312,
      "grad_norm": 0.829501748085022,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8722,
      "step": 110
    },
    {
      "epoch": 0.7872340425531915,
      "grad_norm": 0.7647123336791992,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8407,
      "step": 111
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 0.7503801584243774,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7584,
      "step": 112
    },
    {
      "epoch": 0.8014184397163121,
      "grad_norm": 0.6786141991615295,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7253,
      "step": 113
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 0.6269477605819702,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6798,
      "step": 114
    },
    {
      "epoch": 0.8156028368794326,
      "grad_norm": 0.6445633769035339,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7028,
      "step": 115
    },
    {
      "epoch": 0.8226950354609929,
      "grad_norm": 0.6332740187644958,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7253,
      "step": 116
    },
    {
      "epoch": 0.8297872340425532,
      "grad_norm": 0.6345296502113342,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6284,
      "step": 117
    },
    {
      "epoch": 0.8368794326241135,
      "grad_norm": 0.6838743090629578,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6435,
      "step": 118
    },
    {
      "epoch": 0.8439716312056738,
      "grad_norm": 0.6241557598114014,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6254,
      "step": 119
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.6874054074287415,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6226,
      "step": 120
    },
    {
      "epoch": 0.8581560283687943,
      "grad_norm": 0.650952160358429,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5349,
      "step": 121
    },
    {
      "epoch": 0.8652482269503546,
      "grad_norm": 0.6546323895454407,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5715,
      "step": 122
    },
    {
      "epoch": 0.8723404255319149,
      "grad_norm": 0.6813673377037048,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5908,
      "step": 123
    },
    {
      "epoch": 0.8794326241134752,
      "grad_norm": 0.6731253266334534,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5554,
      "step": 124
    },
    {
      "epoch": 0.8865248226950354,
      "grad_norm": 0.6880707144737244,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5198,
      "step": 125
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 0.6165528297424316,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5125,
      "step": 126
    },
    {
      "epoch": 0.900709219858156,
      "grad_norm": 0.624283492565155,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4478,
      "step": 127
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 0.6110616326332092,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4553,
      "step": 128
    },
    {
      "epoch": 0.9148936170212766,
      "grad_norm": 0.6599687337875366,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4373,
      "step": 129
    },
    {
      "epoch": 0.9219858156028369,
      "grad_norm": 0.6878976821899414,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4953,
      "step": 130
    },
    {
      "epoch": 0.9290780141843972,
      "grad_norm": 0.5550860166549683,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.351,
      "step": 131
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.6531512141227722,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4004,
      "step": 132
    },
    {
      "epoch": 0.9432624113475178,
      "grad_norm": 0.6485903859138489,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3665,
      "step": 133
    },
    {
      "epoch": 0.950354609929078,
      "grad_norm": 0.6129137873649597,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3848,
      "step": 134
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 0.6872605681419373,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.408,
      "step": 135
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 0.7254231572151184,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3731,
      "step": 136
    },
    {
      "epoch": 0.9716312056737588,
      "grad_norm": 0.7933410406112671,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3907,
      "step": 137
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 0.6715631484985352,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2521,
      "step": 138
    },
    {
      "epoch": 0.9858156028368794,
      "grad_norm": 1.3465372323989868,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3178,
      "step": 139
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 3.0612990856170654,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4534,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7969256043434143,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6872,
      "step": 141
    },
    {
      "epoch": 1.0070921985815602,
      "grad_norm": 0.7533031105995178,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9698,
      "step": 142
    },
    {
      "epoch": 1.0141843971631206,
      "grad_norm": 0.7495368719100952,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8849,
      "step": 143
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.7248710989952087,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.83,
      "step": 144
    },
    {
      "epoch": 1.0283687943262412,
      "grad_norm": 0.6989593505859375,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.8468,
      "step": 145
    },
    {
      "epoch": 1.0354609929078014,
      "grad_norm": 0.7099794745445251,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7607,
      "step": 146
    },
    {
      "epoch": 1.0425531914893618,
      "grad_norm": 0.6711968183517456,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7214,
      "step": 147
    },
    {
      "epoch": 1.049645390070922,
      "grad_norm": 0.6636238694190979,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.682,
      "step": 148
    },
    {
      "epoch": 1.0567375886524824,
      "grad_norm": 0.6560536026954651,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6319,
      "step": 149
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.6504359245300293,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5816,
      "step": 150
    },
    {
      "epoch": 1.0638297872340425,
      "eval_loss": 0.572798490524292,
      "eval_runtime": 4.77,
      "eval_samples_per_second": 49.896,
      "eval_steps_per_second": 12.579,
      "step": 150
    },
    {
      "epoch": 1.070921985815603,
      "grad_norm": 0.660551905632019,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6234,
      "step": 151
    },
    {
      "epoch": 1.0780141843971631,
      "grad_norm": 0.617889940738678,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6388,
      "step": 152
    },
    {
      "epoch": 1.0851063829787233,
      "grad_norm": 0.6906648278236389,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6463,
      "step": 153
    },
    {
      "epoch": 1.0921985815602837,
      "grad_norm": 0.6109856963157654,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5092,
      "step": 154
    },
    {
      "epoch": 1.099290780141844,
      "grad_norm": 0.6247379779815674,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5623,
      "step": 155
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.6057058572769165,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5638,
      "step": 156
    },
    {
      "epoch": 1.1134751773049645,
      "grad_norm": 0.6146364808082581,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.453,
      "step": 157
    },
    {
      "epoch": 1.1205673758865249,
      "grad_norm": 0.6693795323371887,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5068,
      "step": 158
    },
    {
      "epoch": 1.127659574468085,
      "grad_norm": 0.6862658858299255,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5096,
      "step": 159
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.7163901329040527,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5284,
      "step": 160
    },
    {
      "epoch": 1.1418439716312057,
      "grad_norm": 0.6084697842597961,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5107,
      "step": 161
    },
    {
      "epoch": 1.148936170212766,
      "grad_norm": 0.6437754034996033,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4771,
      "step": 162
    },
    {
      "epoch": 1.1560283687943262,
      "grad_norm": 0.6459302306175232,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4638,
      "step": 163
    },
    {
      "epoch": 1.1631205673758864,
      "grad_norm": 0.5849676728248596,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3398,
      "step": 164
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 0.5909267663955688,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3214,
      "step": 165
    },
    {
      "epoch": 1.177304964539007,
      "grad_norm": 0.6215970516204834,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3948,
      "step": 166
    },
    {
      "epoch": 1.1843971631205674,
      "grad_norm": 0.6223005056381226,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3943,
      "step": 167
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.591517448425293,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3294,
      "step": 168
    },
    {
      "epoch": 1.198581560283688,
      "grad_norm": 0.5986785888671875,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3227,
      "step": 169
    },
    {
      "epoch": 1.2056737588652482,
      "grad_norm": 0.6252090334892273,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2887,
      "step": 170
    },
    {
      "epoch": 1.2127659574468086,
      "grad_norm": 0.6571121215820312,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3528,
      "step": 171
    },
    {
      "epoch": 1.2198581560283688,
      "grad_norm": 0.6483495235443115,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2749,
      "step": 172
    },
    {
      "epoch": 1.226950354609929,
      "grad_norm": 0.6415087580680847,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2799,
      "step": 173
    },
    {
      "epoch": 1.2340425531914894,
      "grad_norm": 0.8774486184120178,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.288,
      "step": 174
    },
    {
      "epoch": 1.2411347517730495,
      "grad_norm": 0.9746853113174438,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2354,
      "step": 175
    },
    {
      "epoch": 1.24822695035461,
      "grad_norm": 2.3162097930908203,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3473,
      "step": 176
    },
    {
      "epoch": 1.2553191489361701,
      "grad_norm": 0.6907155513763428,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9727,
      "step": 177
    },
    {
      "epoch": 1.2624113475177305,
      "grad_norm": 0.6453986167907715,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8441,
      "step": 178
    },
    {
      "epoch": 1.2695035460992907,
      "grad_norm": 0.6262970566749573,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8015,
      "step": 179
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.6407637000083923,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7144,
      "step": 180
    },
    {
      "epoch": 1.2836879432624113,
      "grad_norm": 0.6383804678916931,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7124,
      "step": 181
    },
    {
      "epoch": 1.2907801418439715,
      "grad_norm": 0.6513094902038574,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7273,
      "step": 182
    },
    {
      "epoch": 1.297872340425532,
      "grad_norm": 0.6380339860916138,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6975,
      "step": 183
    },
    {
      "epoch": 1.3049645390070923,
      "grad_norm": 0.6610780954360962,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6906,
      "step": 184
    },
    {
      "epoch": 1.3120567375886525,
      "grad_norm": 0.6918430328369141,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.677,
      "step": 185
    },
    {
      "epoch": 1.3191489361702127,
      "grad_norm": 0.6196809411048889,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6158,
      "step": 186
    },
    {
      "epoch": 1.326241134751773,
      "grad_norm": 0.6588773131370544,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6134,
      "step": 187
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.6725887060165405,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6,
      "step": 188
    },
    {
      "epoch": 1.3404255319148937,
      "grad_norm": 0.6330568790435791,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6241,
      "step": 189
    },
    {
      "epoch": 1.3475177304964538,
      "grad_norm": 0.6477409601211548,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5487,
      "step": 190
    },
    {
      "epoch": 1.3546099290780143,
      "grad_norm": 0.5947543382644653,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5163,
      "step": 191
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.5868836641311646,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4797,
      "step": 192
    },
    {
      "epoch": 1.3687943262411348,
      "grad_norm": 0.6020753979682922,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.489,
      "step": 193
    },
    {
      "epoch": 1.375886524822695,
      "grad_norm": 0.6148223280906677,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5058,
      "step": 194
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.6265669465065002,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4756,
      "step": 195
    },
    {
      "epoch": 1.3900709219858156,
      "grad_norm": 0.5820423364639282,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4349,
      "step": 196
    },
    {
      "epoch": 1.397163120567376,
      "grad_norm": 0.6171536445617676,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3995,
      "step": 197
    },
    {
      "epoch": 1.4042553191489362,
      "grad_norm": 0.5911435484886169,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3988,
      "step": 198
    },
    {
      "epoch": 1.4113475177304964,
      "grad_norm": 0.6192638874053955,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4081,
      "step": 199
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.5591219663619995,
      "learning_rate": 0.0,
      "loss": 0.3524,
      "step": 200
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 0.5550929307937622,
      "eval_runtime": 4.7697,
      "eval_samples_per_second": 49.898,
      "eval_steps_per_second": 12.579,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.264962487536845e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}