{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.5079365079365079,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025396825396825397,
      "grad_norm": 2.636047975101974e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0025396825396825397,
      "eval_loss": 11.5,
      "eval_runtime": 3.0878,
      "eval_samples_per_second": 214.715,
      "eval_steps_per_second": 53.76,
      "step": 1
    },
    {
      "epoch": 0.005079365079365079,
      "grad_norm": 1.585873542353511e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 1.521205012977589e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.010158730158730159,
      "grad_norm": 7.912056753411889e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 7.582987745990977e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 5.410366793512367e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 3.776412268052809e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.020317460317460317,
      "grad_norm": 4.8580666771158576e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.00010020422632806003,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 4.565776907838881e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.027936507936507936,
      "grad_norm": 5.4764972446719185e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.030476190476190476,
      "grad_norm": 3.321702388348058e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.03301587301587302,
      "grad_norm": 6.865579052828252e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 4.169821477262303e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 4.352764881332405e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.040634920634920635,
      "grad_norm": 4.6682140236953273e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.04317460317460318,
      "grad_norm": 8.784668170846999e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 7.045775419101119e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.04825396825396826,
      "grad_norm": 6.30182767054066e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 5.3640713304048404e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 6.437586125684902e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.05587301587301587,
      "grad_norm": 5.5837543186498806e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.058412698412698416,
      "grad_norm": 4.846237789024599e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.06095238095238095,
      "grad_norm": 8.162963786162436e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 9.017662523547187e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.06603174603174604,
      "grad_norm": 8.8534812675789e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 9.559650061419234e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 9.565611253492534e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.07365079365079365,
      "grad_norm": 0.0001084337491192855,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 8.251346298493445e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.07873015873015873,
      "grad_norm": 0.0002288178657181561,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.08126984126984127,
      "grad_norm": 9.787649469217286e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.0838095238095238,
      "grad_norm": 0.00011837005877168849,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.08634920634920636,
      "grad_norm": 0.0001275823451578617,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.00015519934822805226,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.00011317635653540492,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.09396825396825396,
      "grad_norm": 0.00014402306987904012,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.09650793650793651,
      "grad_norm": 0.0002321524516446516,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.09904761904761905,
      "grad_norm": 0.00019878199964296073,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 0.00019834170234389603,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.10412698412698412,
      "grad_norm": 0.00010827643563970923,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.00022535884636454284,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.10920634920634921,
      "grad_norm": 0.00023150436754804105,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.11174603174603175,
      "grad_norm": 0.00021806175936944783,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.0002765064418781549,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.11682539682539683,
      "grad_norm": 0.00023308668460231274,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.11936507936507937,
      "grad_norm": 0.0002145510952686891,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.1219047619047619,
      "grad_norm": 0.000395020266296342,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 0.0004656356468331069,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.0003186403482686728,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.12698412698412698,
      "eval_loss": 11.5,
      "eval_runtime": 3.0411,
      "eval_samples_per_second": 218.014,
      "eval_steps_per_second": 54.586,
      "step": 50
    },
    {
      "epoch": 0.1295238095238095,
      "grad_norm": 7.056217873468995e-05,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.13206349206349208,
      "grad_norm": 6.737103831255808e-05,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.1346031746031746,
      "grad_norm": 7.846256630728021e-05,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.00016675135702826083,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 0.0001710946235107258,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.00011573624942684546,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.14476190476190476,
      "grad_norm": 0.0001440720952814445,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.1473015873015873,
      "grad_norm": 0.00011513965000631288,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.14984126984126983,
      "grad_norm": 0.00011899576929863542,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.0002316621976206079,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.15492063492063493,
      "grad_norm": 0.0001637023378862068,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.15746031746031747,
      "grad_norm": 0.00030930814682506025,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.00012213404988870025,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.16253968253968254,
      "grad_norm": 9.744994895299897e-05,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 0.00016659994435030967,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.1676190476190476,
      "grad_norm": 0.00038930814480409026,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.17015873015873015,
      "grad_norm": 0.00020493389456532896,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.1726984126984127,
      "grad_norm": 0.0001555823109811172,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.17523809523809525,
      "grad_norm": 0.00029480442753992975,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.00029169078334234655,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.18031746031746032,
      "grad_norm": 0.00030570433591492474,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.0002601992164272815,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.1853968253968254,
      "grad_norm": 0.0003022164455614984,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.18793650793650793,
      "grad_norm": 0.0003140048938803375,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.00033752265153452754,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.19301587301587303,
      "grad_norm": 0.00042699818732216954,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 0.0004237899265717715,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.1980952380952381,
      "grad_norm": 0.0003525879583321512,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.20063492063492064,
      "grad_norm": 0.0004997409996576607,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 0.0004200693510938436,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.0002597474376671016,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.20825396825396825,
      "grad_norm": 0.00044633387005887926,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.21079365079365078,
      "grad_norm": 0.00043739756802096963,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.00046963366912677884,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 0.00048542593140155077,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.21841269841269842,
      "grad_norm": 0.00034454616252332926,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.22095238095238096,
      "grad_norm": 0.00043540395563468337,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.2234920634920635,
      "grad_norm": 0.0003677148779388517,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.22603174603174603,
      "grad_norm": 0.00033803097903728485,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.00048143233289010823,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 0.0005051847547292709,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.23365079365079366,
      "grad_norm": 0.0003523195628076792,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.2361904761904762,
      "grad_norm": 0.0006515139248222113,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.23873015873015874,
      "grad_norm": 0.0006587188690900803,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 0.0004790454695466906,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.2438095238095238,
      "grad_norm": 0.0006076972931623459,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.24634920634920635,
      "grad_norm": 0.0009590393165126443,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 0.000612728763371706,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.0009764377027750015,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.0011880138190463185,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.25396825396825395,
      "eval_loss": 11.5,
      "eval_runtime": 3.0517,
      "eval_samples_per_second": 217.255,
      "eval_steps_per_second": 54.396,
      "step": 100
    },
    {
      "epoch": 0.2565079365079365,
      "grad_norm": 0.00015683531819377095,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.259047619047619,
      "grad_norm": 0.00012049138604197651,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.2615873015873016,
      "grad_norm": 0.00017800556088332087,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.26412698412698415,
      "grad_norm": 0.00026861418155021966,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.0003716795181389898,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.2692063492063492,
      "grad_norm": 0.0002833975595422089,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.27174603174603174,
      "grad_norm": 0.0003513269766699523,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.00023855481413193047,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.2768253968253968,
      "grad_norm": 0.00023193252854980528,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 0.00029786513186991215,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.2819047619047619,
      "grad_norm": 0.00025254423962906003,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.000365566520486027,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.286984126984127,
      "grad_norm": 0.00027666729874908924,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.2895238095238095,
      "grad_norm": 0.00039132856181822717,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 0.00044664432061836123,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.2946031746031746,
      "grad_norm": 0.00042760182986967266,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.0003109555982518941,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.29968253968253966,
      "grad_norm": 0.0005549000925384462,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 0.00037709763273596764,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.0005275582661852241,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.3073015873015873,
      "grad_norm": 0.0006868797354400158,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.30984126984126986,
      "grad_norm": 0.0003916198038496077,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.31238095238095237,
      "grad_norm": 0.00041374217835254967,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.31492063492063493,
      "grad_norm": 0.00048302829964086413,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.000454338121926412,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.000542081892490387,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.3225396825396825,
      "grad_norm": 0.000495821819640696,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.3250793650793651,
      "grad_norm": 0.0005824922118335962,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.32761904761904764,
      "grad_norm": 0.0007732115336693823,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 0.0003601844946388155,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.3326984126984127,
      "grad_norm": 0.0007275976240634918,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.3352380952380952,
      "grad_norm": 0.0007252413779497147,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 0.0006040868465788662,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.3403174603174603,
      "grad_norm": 0.0007312872330658138,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.0006050340598449111,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.3453968253968254,
      "grad_norm": 0.0005079463589936495,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.34793650793650793,
      "grad_norm": 0.0007020235061645508,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.3504761904761905,
      "grad_norm": 0.00045382286771200597,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.353015873015873,
      "grad_norm": 0.000577699625864625,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.0006426837062463164,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.3580952380952381,
      "grad_norm": 0.0007479987107217312,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.36063492063492064,
      "grad_norm": 0.0011289599351584911,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.36317460317460315,
      "grad_norm": 0.0007505420944653451,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.0009757123771123588,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 0.0010634862119331956,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.3707936507936508,
      "grad_norm": 0.0010427199304103851,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.0013985201949253678,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.37587301587301586,
      "grad_norm": 0.0008832611492834985,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.3784126984126984,
      "grad_norm": 0.001664287643507123,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.0016788316424936056,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.38095238095238093,
      "eval_loss": 11.5,
      "eval_runtime": 3.0583,
      "eval_samples_per_second": 216.79,
      "eval_steps_per_second": 54.279,
      "step": 150
    },
    {
      "epoch": 0.3834920634920635,
      "grad_norm": 0.0001507675915490836,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.38603174603174606,
      "grad_norm": 0.00015799202083144337,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.38857142857142857,
      "grad_norm": 0.0002981535217259079,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 0.0005736402818001807,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 0.00046769826440140605,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.3961904761904762,
      "grad_norm": 0.0005333162262104452,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.3987301587301587,
      "grad_norm": 0.0004069180286023766,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.4012698412698413,
      "grad_norm": 0.00045734853483736515,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.4038095238095238,
      "grad_norm": 0.00038881177897565067,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 0.0006046105409041047,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 0.0008934616926126182,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 0.0006283086840994656,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.413968253968254,
      "grad_norm": 0.0002501502458471805,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.4165079365079365,
      "grad_norm": 0.000643797277007252,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 0.00046031048987060785,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.42158730158730157,
      "grad_norm": 0.00045485360897146165,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.42412698412698413,
      "grad_norm": 0.00041288204374723136,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.0003486561181489378,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.4292063492063492,
      "grad_norm": 0.00033542406163178384,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 0.00043678382644429803,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.4342857142857143,
      "grad_norm": 0.0004820231406483799,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.43682539682539684,
      "grad_norm": 0.0006722785765305161,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.43936507936507935,
      "grad_norm": 0.0005217442521825433,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.4419047619047619,
      "grad_norm": 0.0005299354088492692,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.0006642525549978018,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.446984126984127,
      "grad_norm": 0.0006187099497765303,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.44952380952380955,
      "grad_norm": 0.0008217595750465989,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.45206349206349206,
      "grad_norm": 0.0006930683157406747,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.4546031746031746,
      "grad_norm": 0.0007860871846787632,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.0006492060492746532,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.4596825396825397,
      "grad_norm": 0.0005901999538764358,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.0006238595233298838,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.46476190476190476,
      "grad_norm": 0.0008841100498102605,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.46730158730158733,
      "grad_norm": 0.0005608927458524704,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 0.0006603376241400838,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.4723809523809524,
      "grad_norm": 0.0008104827720671892,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.4749206349206349,
      "grad_norm": 0.0008827261626720428,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.4774603174603175,
      "grad_norm": 0.000377334508812055,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0011284862412139773,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 0.0005800533108413219,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.48507936507936505,
      "grad_norm": 0.0010874561266973615,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.4876190476190476,
      "grad_norm": 0.0008321768254972994,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.4901587301587302,
      "grad_norm": 0.0008640267769806087,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.4926984126984127,
      "grad_norm": 0.001046935678459704,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 0.0009591786074452102,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.00164878461509943,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.5003174603174603,
      "grad_norm": 0.001384081901051104,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.5028571428571429,
      "grad_norm": 0.001185267698019743,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.5053968253968254,
      "grad_norm": 0.0015531462850049138,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.0017203431343659759,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.5079365079365079,
      "eval_loss": 11.5,
      "eval_runtime": 3.0566,
      "eval_samples_per_second": 216.91,
      "eval_steps_per_second": 54.309,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32158462771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}