{
  "best_metric": 10.32762336730957,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02463888632233823,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012319443161169116,
      "grad_norm": 0.37034285068511963,
      "learning_rate": 1e-05,
      "loss": 41.5079,
      "step": 1
    },
    {
      "epoch": 0.00012319443161169116,
      "eval_loss": 10.379491806030273,
      "eval_runtime": 28.7674,
      "eval_samples_per_second": 475.225,
      "eval_steps_per_second": 118.815,
      "step": 1
    },
    {
      "epoch": 0.0002463888632233823,
      "grad_norm": 0.41543495655059814,
      "learning_rate": 2e-05,
      "loss": 41.5068,
      "step": 2
    },
    {
      "epoch": 0.00036958329483507344,
      "grad_norm": 0.3897373080253601,
      "learning_rate": 3e-05,
      "loss": 41.5251,
      "step": 3
    },
    {
      "epoch": 0.0004927777264467646,
      "grad_norm": 0.4008975923061371,
      "learning_rate": 4e-05,
      "loss": 41.5305,
      "step": 4
    },
    {
      "epoch": 0.0006159721580584558,
      "grad_norm": 0.39021116495132446,
      "learning_rate": 5e-05,
      "loss": 41.4983,
      "step": 5
    },
    {
      "epoch": 0.0007391665896701469,
      "grad_norm": 0.4045765995979309,
      "learning_rate": 6e-05,
      "loss": 41.5147,
      "step": 6
    },
    {
      "epoch": 0.000862361021281838,
      "grad_norm": 0.36582186818122864,
      "learning_rate": 7e-05,
      "loss": 41.538,
      "step": 7
    },
    {
      "epoch": 0.0009855554528935293,
      "grad_norm": 0.38223153352737427,
      "learning_rate": 8e-05,
      "loss": 41.4999,
      "step": 8
    },
    {
      "epoch": 0.0011087498845052204,
      "grad_norm": 0.3638783395290375,
      "learning_rate": 9e-05,
      "loss": 41.5122,
      "step": 9
    },
    {
      "epoch": 0.0012319443161169115,
      "grad_norm": 0.3758089542388916,
      "learning_rate": 0.0001,
      "loss": 41.5182,
      "step": 10
    },
    {
      "epoch": 0.0013551387477286026,
      "grad_norm": 0.4046088755130768,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.5346,
      "step": 11
    },
    {
      "epoch": 0.0014783331793402938,
      "grad_norm": 0.4480150640010834,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4884,
      "step": 12
    },
    {
      "epoch": 0.001601527610951985,
      "grad_norm": 0.38534626364707947,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.4963,
      "step": 13
    },
    {
      "epoch": 0.001724722042563676,
      "grad_norm": 0.46365806460380554,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.5039,
      "step": 14
    },
    {
      "epoch": 0.0018479164741753672,
      "grad_norm": 0.49963846802711487,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.5156,
      "step": 15
    },
    {
      "epoch": 0.0019711109057870585,
      "grad_norm": 0.49704065918922424,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.5083,
      "step": 16
    },
    {
      "epoch": 0.0020943053373987494,
      "grad_norm": 0.4433138370513916,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.4786,
      "step": 17
    },
    {
      "epoch": 0.0022174997690104408,
      "grad_norm": 0.5082147717475891,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.4805,
      "step": 18
    },
    {
      "epoch": 0.0023406942006221317,
      "grad_norm": 0.5090774297714233,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.5024,
      "step": 19
    },
    {
      "epoch": 0.002463888632233823,
      "grad_norm": 0.5320281386375427,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.4618,
      "step": 20
    },
    {
      "epoch": 0.0025870830638455144,
      "grad_norm": 0.6355424523353577,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.4794,
      "step": 21
    },
    {
      "epoch": 0.0027102774954572053,
      "grad_norm": 0.6119551062583923,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.4549,
      "step": 22
    },
    {
      "epoch": 0.0028334719270688966,
      "grad_norm": 0.6141555309295654,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.4591,
      "step": 23
    },
    {
      "epoch": 0.0029566663586805876,
      "grad_norm": 0.7022342085838318,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.4826,
      "step": 24
    },
    {
      "epoch": 0.003079860790292279,
      "grad_norm": 0.7128514647483826,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.486,
      "step": 25
    },
    {
      "epoch": 0.00320305522190397,
      "grad_norm": 0.7015478610992432,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.4673,
      "step": 26
    },
    {
      "epoch": 0.003326249653515661,
      "grad_norm": 0.8382724523544312,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.4349,
      "step": 27
    },
    {
      "epoch": 0.003449444085127352,
      "grad_norm": 0.8730006814002991,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.4475,
      "step": 28
    },
    {
      "epoch": 0.0035726385167390434,
      "grad_norm": 0.9358540177345276,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.4493,
      "step": 29
    },
    {
      "epoch": 0.0036958329483507343,
      "grad_norm": 0.892292320728302,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.4491,
      "step": 30
    },
    {
      "epoch": 0.0038190273799624257,
      "grad_norm": 0.9767299890518188,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.4422,
      "step": 31
    },
    {
      "epoch": 0.003942221811574117,
      "grad_norm": 0.9271118640899658,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.406,
      "step": 32
    },
    {
      "epoch": 0.004065416243185808,
      "grad_norm": 1.1558642387390137,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.424,
      "step": 33
    },
    {
      "epoch": 0.004188610674797499,
      "grad_norm": 1.2022905349731445,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.4216,
      "step": 34
    },
    {
      "epoch": 0.004311805106409191,
      "grad_norm": 0.9297153949737549,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.4242,
      "step": 35
    },
    {
      "epoch": 0.0044349995380208816,
      "grad_norm": 1.0654194355010986,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.4281,
      "step": 36
    },
    {
      "epoch": 0.0045581939696325725,
      "grad_norm": 1.1089550256729126,
      "learning_rate": 9.509956150664796e-05,
      "loss": 41.3838,
      "step": 37
    },
    {
      "epoch": 0.004681388401244263,
      "grad_norm": 1.1491121053695679,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.3703,
      "step": 38
    },
    {
      "epoch": 0.004804582832855955,
      "grad_norm": 0.9658917784690857,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.3815,
      "step": 39
    },
    {
      "epoch": 0.004927777264467646,
      "grad_norm": 0.9329264760017395,
      "learning_rate": 9.397368756032445e-05,
      "loss": 41.3701,
      "step": 40
    },
    {
      "epoch": 0.005050971696079337,
      "grad_norm": 0.955482542514801,
      "learning_rate": 9.357421218136386e-05,
      "loss": 41.3742,
      "step": 41
    },
    {
      "epoch": 0.005174166127691029,
      "grad_norm": 0.886280357837677,
      "learning_rate": 9.316282404787871e-05,
      "loss": 41.3932,
      "step": 42
    },
    {
      "epoch": 0.00529736055930272,
      "grad_norm": 0.7329453825950623,
      "learning_rate": 9.273963562927695e-05,
      "loss": 41.3587,
      "step": 43
    },
    {
      "epoch": 0.005420554990914411,
      "grad_norm": 0.776685893535614,
      "learning_rate": 9.230476262104677e-05,
      "loss": 41.3672,
      "step": 44
    },
    {
      "epoch": 0.0055437494225261015,
      "grad_norm": 0.7093920707702637,
      "learning_rate": 9.185832391312644e-05,
      "loss": 41.3434,
      "step": 45
    },
    {
      "epoch": 0.005666943854137793,
      "grad_norm": 0.6888406276702881,
      "learning_rate": 9.140044155740101e-05,
      "loss": 41.3421,
      "step": 46
    },
    {
      "epoch": 0.005790138285749484,
      "grad_norm": 0.6905254125595093,
      "learning_rate": 9.093124073433463e-05,
      "loss": 41.3444,
      "step": 47
    },
    {
      "epoch": 0.005913332717361175,
      "grad_norm": 0.6538366675376892,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.3437,
      "step": 48
    },
    {
      "epoch": 0.006036527148972866,
      "grad_norm": 0.6010540723800659,
      "learning_rate": 8.995939984474624e-05,
      "loss": 41.3592,
      "step": 49
    },
    {
      "epoch": 0.006159721580584558,
      "grad_norm": 0.7231239080429077,
      "learning_rate": 8.945702546981969e-05,
      "loss": 41.3236,
      "step": 50
    },
    {
      "epoch": 0.006159721580584558,
      "eval_loss": 10.336989402770996,
      "eval_runtime": 28.4939,
      "eval_samples_per_second": 479.787,
      "eval_steps_per_second": 119.956,
      "step": 50
    },
    {
      "epoch": 0.006282916012196249,
      "grad_norm": 0.5357275605201721,
      "learning_rate": 8.894386393810563e-05,
      "loss": 41.3429,
      "step": 51
    },
    {
      "epoch": 0.00640611044380794,
      "grad_norm": 0.45036154985427856,
      "learning_rate": 8.842005554284296e-05,
      "loss": 41.3454,
      "step": 52
    },
    {
      "epoch": 0.006529304875419631,
      "grad_norm": 0.4848557710647583,
      "learning_rate": 8.788574348801675e-05,
      "loss": 41.3536,
      "step": 53
    },
    {
      "epoch": 0.006652499307031322,
      "grad_norm": 0.5253639221191406,
      "learning_rate": 8.73410738492077e-05,
      "loss": 41.3685,
      "step": 54
    },
    {
      "epoch": 0.006775693738643013,
      "grad_norm": 0.4596695899963379,
      "learning_rate": 8.678619553365659e-05,
      "loss": 41.357,
      "step": 55
    },
    {
      "epoch": 0.006898888170254704,
      "grad_norm": 0.5238817930221558,
      "learning_rate": 8.622126023955446e-05,
      "loss": 41.3657,
      "step": 56
    },
    {
      "epoch": 0.007022082601866396,
      "grad_norm": 0.4427866041660309,
      "learning_rate": 8.564642241456986e-05,
      "loss": 41.3481,
      "step": 57
    },
    {
      "epoch": 0.007145277033478087,
      "grad_norm": 0.3829557001590729,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.3555,
      "step": 58
    },
    {
      "epoch": 0.007268471465089778,
      "grad_norm": 0.3675144910812378,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.3587,
      "step": 59
    },
    {
      "epoch": 0.007391665896701469,
      "grad_norm": 0.4128322899341583,
      "learning_rate": 8.386407858128706e-05,
      "loss": 41.3466,
      "step": 60
    },
    {
      "epoch": 0.0075148603283131605,
      "grad_norm": 0.47052329778671265,
      "learning_rate": 8.32512286056924e-05,
      "loss": 41.3435,
      "step": 61
    },
    {
      "epoch": 0.007638054759924851,
      "grad_norm": 0.4124845862388611,
      "learning_rate": 8.262928807620843e-05,
      "loss": 41.3465,
      "step": 62
    },
    {
      "epoch": 0.007761249191536542,
      "grad_norm": 0.3967921733856201,
      "learning_rate": 8.199842702516583e-05,
      "loss": 41.3349,
      "step": 63
    },
    {
      "epoch": 0.007884443623148234,
      "grad_norm": 0.44313010573387146,
      "learning_rate": 8.135881792367686e-05,
      "loss": 41.324,
      "step": 64
    },
    {
      "epoch": 0.008007638054759925,
      "grad_norm": 0.32965555787086487,
      "learning_rate": 8.07106356344834e-05,
      "loss": 41.3273,
      "step": 65
    },
    {
      "epoch": 0.008130832486371616,
      "grad_norm": 0.3851642310619354,
      "learning_rate": 8.005405736415126e-05,
      "loss": 41.3315,
      "step": 66
    },
    {
      "epoch": 0.008254026917983307,
      "grad_norm": 0.43205058574676514,
      "learning_rate": 7.938926261462366e-05,
      "loss": 41.3255,
      "step": 67
    },
    {
      "epoch": 0.008377221349594998,
      "grad_norm": 0.39321786165237427,
      "learning_rate": 7.871643313414718e-05,
      "loss": 41.3477,
      "step": 68
    },
    {
      "epoch": 0.008500415781206689,
      "grad_norm": 0.441262423992157,
      "learning_rate": 7.803575286758364e-05,
      "loss": 41.3206,
      "step": 69
    },
    {
      "epoch": 0.008623610212818381,
      "grad_norm": 0.34648528695106506,
      "learning_rate": 7.734740790612136e-05,
      "loss": 41.3267,
      "step": 70
    },
    {
      "epoch": 0.008746804644430072,
      "grad_norm": 0.3708791732788086,
      "learning_rate": 7.66515864363997e-05,
      "loss": 41.3234,
      "step": 71
    },
    {
      "epoch": 0.008869999076041763,
      "grad_norm": 0.3931605815887451,
      "learning_rate": 7.594847868906076e-05,
      "loss": 41.3447,
      "step": 72
    },
    {
      "epoch": 0.008993193507653454,
      "grad_norm": 0.3708871901035309,
      "learning_rate": 7.52382768867422e-05,
      "loss": 41.3465,
      "step": 73
    },
    {
      "epoch": 0.009116387939265145,
      "grad_norm": 0.34970754384994507,
      "learning_rate": 7.452117519152542e-05,
      "loss": 41.3311,
      "step": 74
    },
    {
      "epoch": 0.009239582370876836,
      "grad_norm": 0.4211370050907135,
      "learning_rate": 7.379736965185368e-05,
      "loss": 41.3399,
      "step": 75
    },
    {
      "epoch": 0.009362776802488527,
      "grad_norm": 0.36415454745292664,
      "learning_rate": 7.30670581489344e-05,
      "loss": 41.3429,
      "step": 76
    },
    {
      "epoch": 0.00948597123410022,
      "grad_norm": 0.36701810359954834,
      "learning_rate": 7.233044034264034e-05,
      "loss": 41.3501,
      "step": 77
    },
    {
      "epoch": 0.00960916566571191,
      "grad_norm": 0.45310914516448975,
      "learning_rate": 7.158771761692464e-05,
      "loss": 41.3187,
      "step": 78
    },
    {
      "epoch": 0.009732360097323601,
      "grad_norm": 0.3968198597431183,
      "learning_rate": 7.083909302476453e-05,
      "loss": 41.3347,
      "step": 79
    },
    {
      "epoch": 0.009855554528935292,
      "grad_norm": 0.34118831157684326,
      "learning_rate": 7.008477123264848e-05,
      "loss": 41.3228,
      "step": 80
    },
    {
      "epoch": 0.009978748960546983,
      "grad_norm": 0.32499533891677856,
      "learning_rate": 6.932495846462261e-05,
      "loss": 41.3377,
      "step": 81
    },
    {
      "epoch": 0.010101943392158674,
      "grad_norm": 0.39074838161468506,
      "learning_rate": 6.855986244591104e-05,
      "loss": 41.3265,
      "step": 82
    },
    {
      "epoch": 0.010225137823770365,
      "grad_norm": 0.37348777055740356,
      "learning_rate": 6.778969234612584e-05,
      "loss": 41.3244,
      "step": 83
    },
    {
      "epoch": 0.010348332255382058,
      "grad_norm": 0.3705248534679413,
      "learning_rate": 6.701465872208216e-05,
      "loss": 41.3355,
      "step": 84
    },
    {
      "epoch": 0.010471526686993748,
      "grad_norm": 0.32013359665870667,
      "learning_rate": 6.623497346023418e-05,
      "loss": 41.3354,
      "step": 85
    },
    {
      "epoch": 0.01059472111860544,
      "grad_norm": 0.3610351085662842,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.3316,
      "step": 86
    },
    {
      "epoch": 0.01071791555021713,
      "grad_norm": 0.3613660931587219,
      "learning_rate": 6.466250186922325e-05,
      "loss": 41.3088,
      "step": 87
    },
    {
      "epoch": 0.010841109981828821,
      "grad_norm": 0.48871198296546936,
      "learning_rate": 6.387014543809223e-05,
      "loss": 41.3168,
      "step": 88
    },
    {
      "epoch": 0.010964304413440512,
      "grad_norm": 0.3728695213794708,
      "learning_rate": 6.307399704769099e-05,
      "loss": 41.2947,
      "step": 89
    },
    {
      "epoch": 0.011087498845052203,
      "grad_norm": 0.4032233953475952,
      "learning_rate": 6.227427435703997e-05,
      "loss": 41.3213,
      "step": 90
    },
    {
      "epoch": 0.011210693276663894,
      "grad_norm": 0.374328076839447,
      "learning_rate": 6.147119600233758e-05,
      "loss": 41.3285,
      "step": 91
    },
    {
      "epoch": 0.011333887708275587,
      "grad_norm": 0.3907609283924103,
      "learning_rate": 6.066498153718735e-05,
      "loss": 41.2982,
      "step": 92
    },
    {
      "epoch": 0.011457082139887277,
      "grad_norm": 0.4053857922554016,
      "learning_rate": 5.985585137257401e-05,
      "loss": 41.3239,
      "step": 93
    },
    {
      "epoch": 0.011580276571498968,
      "grad_norm": 0.4666404724121094,
      "learning_rate": 5.90440267166055e-05,
      "loss": 41.3147,
      "step": 94
    },
    {
      "epoch": 0.01170347100311066,
      "grad_norm": 0.4556801915168762,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 41.288,
      "step": 95
    },
    {
      "epoch": 0.01182666543472235,
      "grad_norm": 0.40397128462791443,
      "learning_rate": 5.74131823855921e-05,
      "loss": 41.3193,
      "step": 96
    },
    {
      "epoch": 0.011949859866334041,
      "grad_norm": 0.4455827474594116,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 41.2847,
      "step": 97
    },
    {
      "epoch": 0.012073054297945732,
      "grad_norm": 0.4562518298625946,
      "learning_rate": 5.577423184847932e-05,
      "loss": 41.3214,
      "step": 98
    },
    {
      "epoch": 0.012196248729557425,
      "grad_norm": 0.4034453332424164,
      "learning_rate": 5.495227651252315e-05,
      "loss": 41.2924,
      "step": 99
    },
    {
      "epoch": 0.012319443161169116,
      "grad_norm": 0.5995578765869141,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 41.2806,
      "step": 100
    },
    {
      "epoch": 0.012319443161169116,
      "eval_loss": 10.330382347106934,
      "eval_runtime": 28.739,
      "eval_samples_per_second": 475.695,
      "eval_steps_per_second": 118.932,
      "step": 100
    },
    {
      "epoch": 0.012442637592780807,
      "grad_norm": 0.45945844054222107,
      "learning_rate": 5.330452921628497e-05,
      "loss": 41.3285,
      "step": 101
    },
    {
      "epoch": 0.012565832024392497,
      "grad_norm": 0.3176629841327667,
      "learning_rate": 5.247918773366112e-05,
      "loss": 41.3579,
      "step": 102
    },
    {
      "epoch": 0.012689026456004188,
      "grad_norm": 0.3888489305973053,
      "learning_rate": 5.165316846586541e-05,
      "loss": 41.3267,
      "step": 103
    },
    {
      "epoch": 0.01281222088761588,
      "grad_norm": 0.3837381601333618,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 41.3467,
      "step": 104
    },
    {
      "epoch": 0.01293541531922757,
      "grad_norm": 0.3548348546028137,
      "learning_rate": 5e-05,
      "loss": 41.3039,
      "step": 105
    },
    {
      "epoch": 0.013058609750839263,
      "grad_norm": 0.37431982159614563,
      "learning_rate": 4.917330276168208e-05,
      "loss": 41.3269,
      "step": 106
    },
    {
      "epoch": 0.013181804182450954,
      "grad_norm": 0.4022105932235718,
      "learning_rate": 4.834683153413459e-05,
      "loss": 41.3233,
      "step": 107
    },
    {
      "epoch": 0.013304998614062645,
      "grad_norm": 0.3207654654979706,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 41.3501,
      "step": 108
    },
    {
      "epoch": 0.013428193045674336,
      "grad_norm": 0.3817063868045807,
      "learning_rate": 4.669547078371504e-05,
      "loss": 41.3347,
      "step": 109
    },
    {
      "epoch": 0.013551387477286026,
      "grad_norm": 0.3260782063007355,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 41.3431,
      "step": 110
    },
    {
      "epoch": 0.013674581908897717,
      "grad_norm": 0.39310598373413086,
      "learning_rate": 4.504772348747687e-05,
      "loss": 41.314,
      "step": 111
    },
    {
      "epoch": 0.013797776340509408,
      "grad_norm": 0.3685118556022644,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 41.3077,
      "step": 112
    },
    {
      "epoch": 0.013920970772121101,
      "grad_norm": 0.3489997386932373,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 41.3431,
      "step": 113
    },
    {
      "epoch": 0.014044165203732792,
      "grad_norm": 0.3275761008262634,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 41.3338,
      "step": 114
    },
    {
      "epoch": 0.014167359635344483,
      "grad_norm": 0.37457457184791565,
      "learning_rate": 4.17702704859633e-05,
      "loss": 41.3491,
      "step": 115
    },
    {
      "epoch": 0.014290554066956174,
      "grad_norm": 0.35564523935317993,
      "learning_rate": 4.095597328339452e-05,
      "loss": 41.3282,
      "step": 116
    },
    {
      "epoch": 0.014413748498567865,
      "grad_norm": 0.2800564169883728,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 41.323,
      "step": 117
    },
    {
      "epoch": 0.014536942930179556,
      "grad_norm": 0.37886232137680054,
      "learning_rate": 3.933501846281267e-05,
      "loss": 41.3263,
      "step": 118
    },
    {
      "epoch": 0.014660137361791246,
      "grad_norm": 0.34558311104774475,
      "learning_rate": 3.852880399766243e-05,
      "loss": 41.3342,
      "step": 119
    },
    {
      "epoch": 0.014783331793402937,
      "grad_norm": 0.3198447525501251,
      "learning_rate": 3.772572564296005e-05,
      "loss": 41.3284,
      "step": 120
    },
    {
      "epoch": 0.01490652622501463,
      "grad_norm": 0.29619088768959045,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 41.303,
      "step": 121
    },
    {
      "epoch": 0.015029720656626321,
      "grad_norm": 0.37361475825309753,
      "learning_rate": 3.612985456190778e-05,
      "loss": 41.314,
      "step": 122
    },
    {
      "epoch": 0.015152915088238012,
      "grad_norm": 0.44932469725608826,
      "learning_rate": 3.533749813077677e-05,
      "loss": 41.3175,
      "step": 123
    },
    {
      "epoch": 0.015276109519849703,
      "grad_norm": 0.37011954188346863,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.3393,
      "step": 124
    },
    {
      "epoch": 0.015399303951461394,
      "grad_norm": 0.3884902894496918,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 41.3252,
      "step": 125
    },
    {
      "epoch": 0.015522498383073085,
      "grad_norm": 0.3051610291004181,
      "learning_rate": 3.298534127791785e-05,
      "loss": 41.2991,
      "step": 126
    },
    {
      "epoch": 0.015645692814684777,
      "grad_norm": 0.3233656585216522,
      "learning_rate": 3.221030765387417e-05,
      "loss": 41.3326,
      "step": 127
    },
    {
      "epoch": 0.015768887246296468,
      "grad_norm": 0.4488888680934906,
      "learning_rate": 3.144013755408895e-05,
      "loss": 41.2823,
      "step": 128
    },
    {
      "epoch": 0.01589208167790816,
      "grad_norm": 0.3062331974506378,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 41.3405,
      "step": 129
    },
    {
      "epoch": 0.01601527610951985,
      "grad_norm": 0.3733638525009155,
      "learning_rate": 2.991522876735154e-05,
      "loss": 41.3219,
      "step": 130
    },
    {
      "epoch": 0.01613847054113154,
      "grad_norm": 0.3980589807033539,
      "learning_rate": 2.916090697523549e-05,
      "loss": 41.3033,
      "step": 131
    },
    {
      "epoch": 0.016261664972743232,
      "grad_norm": 0.41536206007003784,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 41.3283,
      "step": 132
    },
    {
      "epoch": 0.016384859404354923,
      "grad_norm": 0.38303500413894653,
      "learning_rate": 2.766955965735968e-05,
      "loss": 41.3185,
      "step": 133
    },
    {
      "epoch": 0.016508053835966614,
      "grad_norm": 0.3494269847869873,
      "learning_rate": 2.693294185106562e-05,
      "loss": 41.302,
      "step": 134
    },
    {
      "epoch": 0.016631248267578305,
      "grad_norm": 0.30082157254219055,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 41.3081,
      "step": 135
    },
    {
      "epoch": 0.016754442699189995,
      "grad_norm": 0.3740646541118622,
      "learning_rate": 2.547882480847461e-05,
      "loss": 41.3094,
      "step": 136
    },
    {
      "epoch": 0.016877637130801686,
      "grad_norm": 0.36229270696640015,
      "learning_rate": 2.476172311325783e-05,
      "loss": 41.3087,
      "step": 137
    },
    {
      "epoch": 0.017000831562413377,
      "grad_norm": 0.36643633246421814,
      "learning_rate": 2.405152131093926e-05,
      "loss": 41.2834,
      "step": 138
    },
    {
      "epoch": 0.01712402599402507,
      "grad_norm": 0.356387197971344,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 41.3077,
      "step": 139
    },
    {
      "epoch": 0.017247220425636763,
      "grad_norm": 0.36646512150764465,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 41.2882,
      "step": 140
    },
    {
      "epoch": 0.017370414857248453,
      "grad_norm": 0.2967137098312378,
      "learning_rate": 2.196424713241637e-05,
      "loss": 41.3225,
      "step": 141
    },
    {
      "epoch": 0.017493609288860144,
      "grad_norm": 0.3648103177547455,
      "learning_rate": 2.128356686585282e-05,
      "loss": 41.3174,
      "step": 142
    },
    {
      "epoch": 0.017616803720471835,
      "grad_norm": 0.37364527583122253,
      "learning_rate": 2.061073738537635e-05,
      "loss": 41.2795,
      "step": 143
    },
    {
      "epoch": 0.017739998152083526,
      "grad_norm": 0.31925126910209656,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 41.2903,
      "step": 144
    },
    {
      "epoch": 0.017863192583695217,
      "grad_norm": 0.40006139874458313,
      "learning_rate": 1.928936436551661e-05,
      "loss": 41.2956,
      "step": 145
    },
    {
      "epoch": 0.017986387015306908,
      "grad_norm": 0.4049123227596283,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 41.2931,
      "step": 146
    },
    {
      "epoch": 0.0181095814469186,
      "grad_norm": 0.38992005586624146,
      "learning_rate": 1.800157297483417e-05,
      "loss": 41.3238,
      "step": 147
    },
    {
      "epoch": 0.01823277587853029,
      "grad_norm": 0.3740057945251465,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 41.2797,
      "step": 148
    },
    {
      "epoch": 0.01835597031014198,
      "grad_norm": 0.40869832038879395,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 41.3091,
      "step": 149
    },
    {
      "epoch": 0.01847916474175367,
      "grad_norm": 0.38570329546928406,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 41.295,
      "step": 150
    },
    {
      "epoch": 0.01847916474175367,
      "eval_loss": 10.32783031463623,
      "eval_runtime": 28.686,
      "eval_samples_per_second": 476.574,
      "eval_steps_per_second": 119.152,
      "step": 150
    },
    {
      "epoch": 0.018602359173365363,
      "grad_norm": 0.29322147369384766,
      "learning_rate": 1.553232954407171e-05,
      "loss": 41.3261,
      "step": 151
    },
    {
      "epoch": 0.018725553604977054,
      "grad_norm": 0.3674944043159485,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 41.326,
      "step": 152
    },
    {
      "epoch": 0.018848748036588748,
      "grad_norm": 0.34021836519241333,
      "learning_rate": 1.435357758543015e-05,
      "loss": 41.3166,
      "step": 153
    },
    {
      "epoch": 0.01897194246820044,
      "grad_norm": 0.4250488579273224,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 41.324,
      "step": 154
    },
    {
      "epoch": 0.01909513689981213,
      "grad_norm": 0.28842154145240784,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 41.309,
      "step": 155
    },
    {
      "epoch": 0.01921833133142382,
      "grad_norm": 0.37146052718162537,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 41.3095,
      "step": 156
    },
    {
      "epoch": 0.01934152576303551,
      "grad_norm": 0.3950320780277252,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 41.3228,
      "step": 157
    },
    {
      "epoch": 0.019464720194647202,
      "grad_norm": 0.3732362389564514,
      "learning_rate": 1.157994445715706e-05,
      "loss": 41.3206,
      "step": 158
    },
    {
      "epoch": 0.019587914626258893,
      "grad_norm": 0.32746651768684387,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.3418,
      "step": 159
    },
    {
      "epoch": 0.019711109057870584,
      "grad_norm": 0.40929681062698364,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 41.3331,
      "step": 160
    },
    {
      "epoch": 0.019834303489482275,
      "grad_norm": 0.3719869554042816,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 41.3383,
      "step": 161
    },
    {
      "epoch": 0.019957497921093966,
      "grad_norm": 0.373146116733551,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.3259,
      "step": 162
    },
    {
      "epoch": 0.020080692352705657,
      "grad_norm": 0.4307291805744171,
      "learning_rate": 9.068759265665384e-06,
      "loss": 41.34,
      "step": 163
    },
    {
      "epoch": 0.020203886784317348,
      "grad_norm": 0.3563025891780853,
      "learning_rate": 8.599558442598998e-06,
      "loss": 41.3077,
      "step": 164
    },
    {
      "epoch": 0.02032708121592904,
      "grad_norm": 0.2874586880207062,
      "learning_rate": 8.141676086873572e-06,
      "loss": 41.3375,
      "step": 165
    },
    {
      "epoch": 0.02045027564754073,
      "grad_norm": 0.4188411235809326,
      "learning_rate": 7.695237378953223e-06,
      "loss": 41.3221,
      "step": 166
    },
    {
      "epoch": 0.02057347007915242,
      "grad_norm": 0.3838663697242737,
      "learning_rate": 7.260364370723044e-06,
      "loss": 41.3361,
      "step": 167
    },
    {
      "epoch": 0.020696664510764115,
      "grad_norm": 0.31003084778785706,
      "learning_rate": 6.837175952121306e-06,
      "loss": 41.3145,
      "step": 168
    },
    {
      "epoch": 0.020819858942375806,
      "grad_norm": 0.35382720828056335,
      "learning_rate": 6.425787818636131e-06,
      "loss": 41.3053,
      "step": 169
    },
    {
      "epoch": 0.020943053373987497,
      "grad_norm": 0.3113577663898468,
      "learning_rate": 6.026312439675552e-06,
      "loss": 41.34,
      "step": 170
    },
    {
      "epoch": 0.021066247805599188,
      "grad_norm": 0.32111984491348267,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 41.331,
      "step": 171
    },
    {
      "epoch": 0.02118944223721088,
      "grad_norm": 0.3550707995891571,
      "learning_rate": 5.263533508961827e-06,
      "loss": 41.3191,
      "step": 172
    },
    {
      "epoch": 0.02131263666882257,
      "grad_norm": 0.3614715337753296,
      "learning_rate": 4.900438493352055e-06,
      "loss": 41.2958,
      "step": 173
    },
    {
      "epoch": 0.02143583110043426,
      "grad_norm": 0.4031304121017456,
      "learning_rate": 4.549673247541875e-06,
      "loss": 41.3089,
      "step": 174
    },
    {
      "epoch": 0.02155902553204595,
      "grad_norm": 0.4373549818992615,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 41.2899,
      "step": 175
    },
    {
      "epoch": 0.021682219963657642,
      "grad_norm": 0.3327663838863373,
      "learning_rate": 3.885512251130763e-06,
      "loss": 41.3155,
      "step": 176
    },
    {
      "epoch": 0.021805414395269333,
      "grad_norm": 0.31886810064315796,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 41.2987,
      "step": 177
    },
    {
      "epoch": 0.021928608826881024,
      "grad_norm": 0.36802637577056885,
      "learning_rate": 3.271776770026963e-06,
      "loss": 41.3308,
      "step": 178
    },
    {
      "epoch": 0.022051803258492715,
      "grad_norm": 0.3171312212944031,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 41.3021,
      "step": 179
    },
    {
      "epoch": 0.022174997690104406,
      "grad_norm": 0.32209452986717224,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 41.3092,
      "step": 180
    },
    {
      "epoch": 0.022298192121716097,
      "grad_norm": 0.35692593455314636,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.3095,
      "step": 181
    },
    {
      "epoch": 0.022421386553327788,
      "grad_norm": 0.34302806854248047,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 41.3083,
      "step": 182
    },
    {
      "epoch": 0.022544580984939482,
      "grad_norm": 0.3289535939693451,
      "learning_rate": 1.962316193157593e-06,
      "loss": 41.334,
      "step": 183
    },
    {
      "epoch": 0.022667775416551173,
      "grad_norm": 0.4378049671649933,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 41.3029,
      "step": 184
    },
    {
      "epoch": 0.022790969848162864,
      "grad_norm": 0.3344568610191345,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 41.3138,
      "step": 185
    },
    {
      "epoch": 0.022914164279774555,
      "grad_norm": 0.34980833530426025,
      "learning_rate": 1.333670137599713e-06,
      "loss": 41.3044,
      "step": 186
    },
    {
      "epoch": 0.023037358711386246,
      "grad_norm": 0.3678795397281647,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 41.2976,
      "step": 187
    },
    {
      "epoch": 0.023160553142997937,
      "grad_norm": 0.4266866147518158,
      "learning_rate": 9.810017062595322e-07,
      "loss": 41.3177,
      "step": 188
    },
    {
      "epoch": 0.023283747574609628,
      "grad_norm": 0.35492751002311707,
      "learning_rate": 8.247462563808817e-07,
      "loss": 41.3067,
      "step": 189
    },
    {
      "epoch": 0.02340694200622132,
      "grad_norm": 0.4533149003982544,
      "learning_rate": 6.819348298638839e-07,
      "loss": 41.2824,
      "step": 190
    },
    {
      "epoch": 0.02353013643783301,
      "grad_norm": 0.3437725305557251,
      "learning_rate": 5.526064699265753e-07,
      "loss": 41.2956,
      "step": 191
    },
    {
      "epoch": 0.0236533308694447,
      "grad_norm": 0.43365609645843506,
      "learning_rate": 4.367965336512403e-07,
      "loss": 41.3099,
      "step": 192
    },
    {
      "epoch": 0.02377652530105639,
      "grad_norm": 0.3725466728210449,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 41.2875,
      "step": 193
    },
    {
      "epoch": 0.023899719732668082,
      "grad_norm": 0.3781149685382843,
      "learning_rate": 2.458548727494292e-07,
      "loss": 41.308,
      "step": 194
    },
    {
      "epoch": 0.024022914164279773,
      "grad_norm": 0.3700525164604187,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 41.3202,
      "step": 195
    },
    {
      "epoch": 0.024146108595891464,
      "grad_norm": 0.315239280462265,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 41.287,
      "step": 196
    },
    {
      "epoch": 0.02426930302750316,
      "grad_norm": 0.3573191463947296,
      "learning_rate": 6.150154258476315e-08,
      "loss": 41.2788,
      "step": 197
    },
    {
      "epoch": 0.02439249745911485,
      "grad_norm": 0.32416683435440063,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 41.3028,
      "step": 198
    },
    {
      "epoch": 0.02451569189072654,
      "grad_norm": 0.4037030041217804,
      "learning_rate": 6.834750376549792e-09,
      "loss": 41.285,
      "step": 199
    },
    {
      "epoch": 0.02463888632233823,
      "grad_norm": 0.4670313894748688,
      "learning_rate": 0.0,
      "loss": 41.2808,
      "step": 200
    },
    {
      "epoch": 0.02463888632233823,
      "eval_loss": 10.32762336730957,
      "eval_runtime": 28.6514,
      "eval_samples_per_second": 477.15,
      "eval_steps_per_second": 119.296,
      "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": 43176645623808.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}