{
  "best_metric": 2.159189224243164,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.4024024024024024,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 0.9779966473579407,
      "learning_rate": 1e-05,
      "loss": 2.5128,
      "step": 1
    },
    {
      "epoch": 0.012012012012012012,
      "eval_loss": 2.620347499847412,
      "eval_runtime": 5.5331,
      "eval_samples_per_second": 25.302,
      "eval_steps_per_second": 6.326,
      "step": 1
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 1.0254873037338257,
      "learning_rate": 2e-05,
      "loss": 2.502,
      "step": 2
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 1.00424063205719,
      "learning_rate": 3e-05,
      "loss": 2.5308,
      "step": 3
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 0.8424004912376404,
      "learning_rate": 4e-05,
      "loss": 2.4553,
      "step": 4
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 0.7853732109069824,
      "learning_rate": 5e-05,
      "loss": 2.4893,
      "step": 5
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.6891431212425232,
      "learning_rate": 6e-05,
      "loss": 2.4391,
      "step": 6
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 0.7737429141998291,
      "learning_rate": 7e-05,
      "loss": 2.6113,
      "step": 7
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 0.6969437003135681,
      "learning_rate": 8e-05,
      "loss": 2.3737,
      "step": 8
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.7930096387863159,
      "learning_rate": 9e-05,
      "loss": 2.5104,
      "step": 9
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.7012117505073547,
      "learning_rate": 0.0001,
      "loss": 2.5152,
      "step": 10
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 0.65236896276474,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.4692,
      "step": 11
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.6483259201049805,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.5443,
      "step": 12
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 0.5994179248809814,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.5418,
      "step": 13
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 0.5770494937896729,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.4485,
      "step": 14
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 0.538013219833374,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.5063,
      "step": 15
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 0.49851569533348083,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.4049,
      "step": 16
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 0.49778127670288086,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.5072,
      "step": 17
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.48549842834472656,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.5148,
      "step": 18
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 0.4956447184085846,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.5717,
      "step": 19
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.5286897420883179,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.6826,
      "step": 20
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 0.4844571053981781,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.2198,
      "step": 21
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 0.47686830163002014,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.2501,
      "step": 22
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 0.44916439056396484,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.2848,
      "step": 23
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.4688701033592224,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.2434,
      "step": 24
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 0.49085330963134766,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.3217,
      "step": 25
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 0.49016809463500977,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.2963,
      "step": 26
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.46133869886398315,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.2833,
      "step": 27
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 0.4724460244178772,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.3373,
      "step": 28
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 0.4763452410697937,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.2562,
      "step": 29
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.4774019122123718,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.3369,
      "step": 30
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 0.4706208407878876,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.3542,
      "step": 31
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 0.4632410705089569,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.3312,
      "step": 32
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 0.5100334882736206,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.2899,
      "step": 33
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 0.463093101978302,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.3384,
      "step": 34
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 0.47128352522850037,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.2834,
      "step": 35
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.47490766644477844,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.3157,
      "step": 36
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.48920348286628723,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.4561,
      "step": 37
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 0.4785793721675873,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.3855,
      "step": 38
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 0.4861472249031067,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5434,
      "step": 39
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.49264657497406006,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.5534,
      "step": 40
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 0.46673184633255005,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.1588,
      "step": 41
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.4770936965942383,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.1512,
      "step": 42
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 0.47114598751068115,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.2237,
      "step": 43
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 0.46100324392318726,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.1884,
      "step": 44
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.4606519043445587,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.2079,
      "step": 45
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 0.4770957827568054,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.2235,
      "step": 46
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 0.4682772755622864,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.241,
      "step": 47
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.48025694489479065,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2365,
      "step": 48
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 0.460593044757843,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.241,
      "step": 49
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.48151668906211853,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.2679,
      "step": 50
    },
    {
      "epoch": 0.6006006006006006,
      "eval_loss": 2.256049871444702,
      "eval_runtime": 5.6339,
      "eval_samples_per_second": 24.85,
      "eval_steps_per_second": 6.212,
      "step": 50
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 0.4661988317966461,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.1841,
      "step": 51
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 0.45055660605430603,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.2628,
      "step": 52
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 0.47169768810272217,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.305,
      "step": 53
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.47180622816085815,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.2606,
      "step": 54
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 0.47041988372802734,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.2409,
      "step": 55
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 0.454802006483078,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.2503,
      "step": 56
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 0.4808672070503235,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3921,
      "step": 57
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 0.4827421307563782,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.262,
      "step": 58
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 0.49734070897102356,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.4196,
      "step": 59
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.5037516951560974,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.4554,
      "step": 60
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 0.4393552541732788,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.1092,
      "step": 61
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 0.4560452103614807,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.0799,
      "step": 62
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.4581015706062317,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.1583,
      "step": 63
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 0.4785716235637665,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.2039,
      "step": 64
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 0.46477729082107544,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.1403,
      "step": 65
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.46302974224090576,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.1734,
      "step": 66
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 0.469603955745697,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2121,
      "step": 67
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 0.48566359281539917,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.216,
      "step": 68
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 0.4689801037311554,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.1911,
      "step": 69
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.4652516543865204,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.2589,
      "step": 70
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 0.46898356080055237,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.1985,
      "step": 71
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.4824417531490326,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.2688,
      "step": 72
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 0.46958738565444946,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.2605,
      "step": 73
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.4817938208580017,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.2527,
      "step": 74
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.4745516777038574,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.2814,
      "step": 75
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 0.49045321345329285,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.3105,
      "step": 76
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 0.5104289054870605,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.2616,
      "step": 77
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.5061110854148865,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.3641,
      "step": 78
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 0.49394217133522034,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.4144,
      "step": 79
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.5313133597373962,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.5564,
      "step": 80
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.4830684959888458,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.1418,
      "step": 81
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 0.47343122959136963,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.1518,
      "step": 82
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 0.4916979670524597,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.2134,
      "step": 83
    },
    {
      "epoch": 1.009009009009009,
      "grad_norm": 1.7826623916625977,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.0989,
      "step": 84
    },
    {
      "epoch": 1.021021021021021,
      "grad_norm": 0.48136138916015625,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.0882,
      "step": 85
    },
    {
      "epoch": 1.033033033033033,
      "grad_norm": 0.48217904567718506,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0661,
      "step": 86
    },
    {
      "epoch": 1.045045045045045,
      "grad_norm": 0.4503604769706726,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.0021,
      "step": 87
    },
    {
      "epoch": 1.057057057057057,
      "grad_norm": 0.482292115688324,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.0701,
      "step": 88
    },
    {
      "epoch": 1.069069069069069,
      "grad_norm": 0.47316575050354004,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.0497,
      "step": 89
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.48678597807884216,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.1136,
      "step": 90
    },
    {
      "epoch": 1.093093093093093,
      "grad_norm": 0.511247992515564,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.1374,
      "step": 91
    },
    {
      "epoch": 1.105105105105105,
      "grad_norm": 0.48688921332359314,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.1204,
      "step": 92
    },
    {
      "epoch": 1.117117117117117,
      "grad_norm": 0.48262637853622437,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.095,
      "step": 93
    },
    {
      "epoch": 1.1291291291291292,
      "grad_norm": 0.4971187114715576,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.0891,
      "step": 94
    },
    {
      "epoch": 1.1411411411411412,
      "grad_norm": 0.4802643656730652,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.1336,
      "step": 95
    },
    {
      "epoch": 1.1531531531531531,
      "grad_norm": 0.5007813572883606,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.1243,
      "step": 96
    },
    {
      "epoch": 1.165165165165165,
      "grad_norm": 0.48893651366233826,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.0958,
      "step": 97
    },
    {
      "epoch": 1.1771771771771773,
      "grad_norm": 0.4917381703853607,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.2016,
      "step": 98
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 0.5127087235450745,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.1832,
      "step": 99
    },
    {
      "epoch": 1.2012012012012012,
      "grad_norm": 0.5067014098167419,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.2025,
      "step": 100
    },
    {
      "epoch": 1.2012012012012012,
      "eval_loss": 2.191638946533203,
      "eval_runtime": 5.6281,
      "eval_samples_per_second": 24.875,
      "eval_steps_per_second": 6.219,
      "step": 100
    },
    {
      "epoch": 1.2132132132132132,
      "grad_norm": 0.4863550662994385,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.1902,
      "step": 101
    },
    {
      "epoch": 1.2252252252252251,
      "grad_norm": 0.5129148960113525,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.2576,
      "step": 102
    },
    {
      "epoch": 1.2372372372372373,
      "grad_norm": 0.5114224553108215,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.3244,
      "step": 103
    },
    {
      "epoch": 1.2492492492492493,
      "grad_norm": 0.493896484375,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.1238,
      "step": 104
    },
    {
      "epoch": 1.2612612612612613,
      "grad_norm": 0.4961284399032593,
      "learning_rate": 5e-05,
      "loss": 2.0501,
      "step": 105
    },
    {
      "epoch": 1.2732732732732732,
      "grad_norm": 0.5010257363319397,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.0496,
      "step": 106
    },
    {
      "epoch": 1.2852852852852852,
      "grad_norm": 0.487203985452652,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.0778,
      "step": 107
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.5181256532669067,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.1125,
      "step": 108
    },
    {
      "epoch": 1.3093093093093093,
      "grad_norm": 0.5039774775505066,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.0538,
      "step": 109
    },
    {
      "epoch": 1.3213213213213213,
      "grad_norm": 0.4977467358112335,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.0539,
      "step": 110
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.48416605591773987,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.0533,
      "step": 111
    },
    {
      "epoch": 1.3453453453453452,
      "grad_norm": 0.5055656433105469,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.1372,
      "step": 112
    },
    {
      "epoch": 1.3573573573573574,
      "grad_norm": 0.5132829546928406,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.1402,
      "step": 113
    },
    {
      "epoch": 1.3693693693693694,
      "grad_norm": 0.49982255697250366,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.0683,
      "step": 114
    },
    {
      "epoch": 1.3813813813813813,
      "grad_norm": 0.5092611908912659,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.1226,
      "step": 115
    },
    {
      "epoch": 1.3933933933933935,
      "grad_norm": 0.5046988129615784,
      "learning_rate": 4.095597328339452e-05,
      "loss": 2.1228,
      "step": 116
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.5184442400932312,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.115,
      "step": 117
    },
    {
      "epoch": 1.4174174174174174,
      "grad_norm": 0.5079309940338135,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.1694,
      "step": 118
    },
    {
      "epoch": 1.4294294294294294,
      "grad_norm": 0.5087984204292297,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.1278,
      "step": 119
    },
    {
      "epoch": 1.4414414414414414,
      "grad_norm": 0.5254697203636169,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.1064,
      "step": 120
    },
    {
      "epoch": 1.4534534534534536,
      "grad_norm": 0.5005338788032532,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.1765,
      "step": 121
    },
    {
      "epoch": 1.4654654654654655,
      "grad_norm": 0.5177510976791382,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.2555,
      "step": 122
    },
    {
      "epoch": 1.4774774774774775,
      "grad_norm": 0.5199260711669922,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.348,
      "step": 123
    },
    {
      "epoch": 1.4894894894894894,
      "grad_norm": 0.4976234436035156,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0259,
      "step": 124
    },
    {
      "epoch": 1.5015015015015014,
      "grad_norm": 0.5113729238510132,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.9603,
      "step": 125
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.498358815908432,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.0127,
      "step": 126
    },
    {
      "epoch": 1.5255255255255256,
      "grad_norm": 0.5064008235931396,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.0124,
      "step": 127
    },
    {
      "epoch": 1.5375375375375375,
      "grad_norm": 0.509179413318634,
      "learning_rate": 3.144013755408895e-05,
      "loss": 2.0722,
      "step": 128
    },
    {
      "epoch": 1.5495495495495497,
      "grad_norm": 0.48622190952301025,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.9935,
      "step": 129
    },
    {
      "epoch": 1.5615615615615615,
      "grad_norm": 0.4933459758758545,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.0576,
      "step": 130
    },
    {
      "epoch": 1.5735735735735736,
      "grad_norm": 0.4934154450893402,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.0638,
      "step": 131
    },
    {
      "epoch": 1.5855855855855856,
      "grad_norm": 0.4895775020122528,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.0604,
      "step": 132
    },
    {
      "epoch": 1.5975975975975976,
      "grad_norm": 0.49020150303840637,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.0882,
      "step": 133
    },
    {
      "epoch": 1.6096096096096097,
      "grad_norm": 0.5107933878898621,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.1417,
      "step": 134
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.49079135060310364,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.1179,
      "step": 135
    },
    {
      "epoch": 1.6336336336336337,
      "grad_norm": 0.5079110264778137,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.1177,
      "step": 136
    },
    {
      "epoch": 1.6456456456456456,
      "grad_norm": 0.5160492658615112,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.1703,
      "step": 137
    },
    {
      "epoch": 1.6576576576576576,
      "grad_norm": 0.5230135917663574,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.1859,
      "step": 138
    },
    {
      "epoch": 1.6696696696696698,
      "grad_norm": 0.5043229460716248,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.1092,
      "step": 139
    },
    {
      "epoch": 1.6816816816816815,
      "grad_norm": 0.5143576264381409,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.1918,
      "step": 140
    },
    {
      "epoch": 1.6936936936936937,
      "grad_norm": 0.5266605615615845,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.268,
      "step": 141
    },
    {
      "epoch": 1.7057057057057057,
      "grad_norm": 0.5235373377799988,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.2505,
      "step": 142
    },
    {
      "epoch": 1.7177177177177176,
      "grad_norm": 0.5367483496665955,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4294,
      "step": 143
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.49311956763267517,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0812,
      "step": 144
    },
    {
      "epoch": 1.7417417417417418,
      "grad_norm": 0.5057884454727173,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.9529,
      "step": 145
    },
    {
      "epoch": 1.7537537537537538,
      "grad_norm": 0.4936122000217438,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.932,
      "step": 146
    },
    {
      "epoch": 1.7657657657657657,
      "grad_norm": 0.5071538090705872,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.0011,
      "step": 147
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.505588173866272,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.9714,
      "step": 148
    },
    {
      "epoch": 1.7897897897897899,
      "grad_norm": 0.5011753439903259,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.0795,
      "step": 149
    },
    {
      "epoch": 1.8018018018018018,
      "grad_norm": 0.5014941692352295,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.0601,
      "step": 150
    },
    {
      "epoch": 1.8018018018018018,
      "eval_loss": 2.163229465484619,
      "eval_runtime": 5.6409,
      "eval_samples_per_second": 24.819,
      "eval_steps_per_second": 6.205,
      "step": 150
    },
    {
      "epoch": 1.8138138138138138,
      "grad_norm": 0.5076649188995361,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.021,
      "step": 151
    },
    {
      "epoch": 1.825825825825826,
      "grad_norm": 0.495312362909317,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.0526,
      "step": 152
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.5158017873764038,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.1428,
      "step": 153
    },
    {
      "epoch": 1.84984984984985,
      "grad_norm": 0.5068858861923218,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.0552,
      "step": 154
    },
    {
      "epoch": 1.8618618618618619,
      "grad_norm": 0.5228625535964966,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.0949,
      "step": 155
    },
    {
      "epoch": 1.8738738738738738,
      "grad_norm": 0.5136927366256714,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.1073,
      "step": 156
    },
    {
      "epoch": 1.885885885885886,
      "grad_norm": 0.5210297107696533,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 2.0973,
      "step": 157
    },
    {
      "epoch": 1.8978978978978978,
      "grad_norm": 0.4969292879104614,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.0457,
      "step": 158
    },
    {
      "epoch": 1.90990990990991,
      "grad_norm": 0.5109185576438904,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.0995,
      "step": 159
    },
    {
      "epoch": 1.921921921921922,
      "grad_norm": 0.5158543586730957,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.2339,
      "step": 160
    },
    {
      "epoch": 1.9339339339339339,
      "grad_norm": 0.504898726940155,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 2.1546,
      "step": 161
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.5134164690971375,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.3228,
      "step": 162
    },
    {
      "epoch": 1.9579579579579578,
      "grad_norm": 0.5394213795661926,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.3563,
      "step": 163
    },
    {
      "epoch": 1.96996996996997,
      "grad_norm": 0.5164071321487427,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.0496,
      "step": 164
    },
    {
      "epoch": 1.981981981981982,
      "grad_norm": 0.48599231243133545,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.0247,
      "step": 165
    },
    {
      "epoch": 1.993993993993994,
      "grad_norm": 0.5050970315933228,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.1064,
      "step": 166
    },
    {
      "epoch": 2.006006006006006,
      "grad_norm": 1.8524956703186035,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.9696,
      "step": 167
    },
    {
      "epoch": 2.018018018018018,
      "grad_norm": 0.47299107909202576,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.9459,
      "step": 168
    },
    {
      "epoch": 2.03003003003003,
      "grad_norm": 0.47611644864082336,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.9219,
      "step": 169
    },
    {
      "epoch": 2.042042042042042,
      "grad_norm": 0.48737451434135437,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.9682,
      "step": 170
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 0.486991286277771,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.9597,
      "step": 171
    },
    {
      "epoch": 2.066066066066066,
      "grad_norm": 0.49181637167930603,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.9385,
      "step": 172
    },
    {
      "epoch": 2.078078078078078,
      "grad_norm": 0.4990840256214142,
      "learning_rate": 4.900438493352055e-06,
      "loss": 2.0694,
      "step": 173
    },
    {
      "epoch": 2.09009009009009,
      "grad_norm": 0.49461281299591064,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.0174,
      "step": 174
    },
    {
      "epoch": 2.1021021021021022,
      "grad_norm": 0.47608286142349243,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.011,
      "step": 175
    },
    {
      "epoch": 2.114114114114114,
      "grad_norm": 0.494524747133255,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.1101,
      "step": 176
    },
    {
      "epoch": 2.126126126126126,
      "grad_norm": 0.4931861460208893,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.0956,
      "step": 177
    },
    {
      "epoch": 2.138138138138138,
      "grad_norm": 0.47971487045288086,
      "learning_rate": 3.271776770026963e-06,
      "loss": 2.0612,
      "step": 178
    },
    {
      "epoch": 2.15015015015015,
      "grad_norm": 0.49637532234191895,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.1168,
      "step": 179
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.48739728331565857,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.1211,
      "step": 180
    },
    {
      "epoch": 2.174174174174174,
      "grad_norm": 0.48743805289268494,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0713,
      "step": 181
    },
    {
      "epoch": 2.186186186186186,
      "grad_norm": 0.5085588693618774,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.0678,
      "step": 182
    },
    {
      "epoch": 2.1981981981981984,
      "grad_norm": 0.5004733800888062,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.1098,
      "step": 183
    },
    {
      "epoch": 2.21021021021021,
      "grad_norm": 0.5064164996147156,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.1741,
      "step": 184
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.4986509084701538,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.1568,
      "step": 185
    },
    {
      "epoch": 2.234234234234234,
      "grad_norm": 0.5039064288139343,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.2443,
      "step": 186
    },
    {
      "epoch": 2.2462462462462462,
      "grad_norm": 0.5045194029808044,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.1629,
      "step": 187
    },
    {
      "epoch": 2.2582582582582584,
      "grad_norm": 0.48815736174583435,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.93,
      "step": 188
    },
    {
      "epoch": 2.27027027027027,
      "grad_norm": 0.5025401711463928,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.956,
      "step": 189
    },
    {
      "epoch": 2.2822822822822824,
      "grad_norm": 0.4753499925136566,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9593,
      "step": 190
    },
    {
      "epoch": 2.294294294294294,
      "grad_norm": 0.49134448170661926,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.9995,
      "step": 191
    },
    {
      "epoch": 2.3063063063063063,
      "grad_norm": 0.4763307571411133,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.9588,
      "step": 192
    },
    {
      "epoch": 2.3183183183183185,
      "grad_norm": 0.48177674412727356,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.0006,
      "step": 193
    },
    {
      "epoch": 2.33033033033033,
      "grad_norm": 0.48630112409591675,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.0097,
      "step": 194
    },
    {
      "epoch": 2.3423423423423424,
      "grad_norm": 0.4901660680770874,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.9813,
      "step": 195
    },
    {
      "epoch": 2.3543543543543546,
      "grad_norm": 0.4822320342063904,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.9636,
      "step": 196
    },
    {
      "epoch": 2.3663663663663663,
      "grad_norm": 0.5069350004196167,
      "learning_rate": 6.150154258476315e-08,
      "loss": 2.069,
      "step": 197
    },
    {
      "epoch": 2.3783783783783785,
      "grad_norm": 0.48865294456481934,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.0203,
      "step": 198
    },
    {
      "epoch": 2.3903903903903903,
      "grad_norm": 0.5015993118286133,
      "learning_rate": 6.834750376549792e-09,
      "loss": 2.1148,
      "step": 199
    },
    {
      "epoch": 2.4024024024024024,
      "grad_norm": 0.4962920844554901,
      "learning_rate": 0.0,
      "loss": 2.0704,
      "step": 200
    },
    {
      "epoch": 2.4024024024024024,
      "eval_loss": 2.159189224243164,
      "eval_runtime": 5.6455,
      "eval_samples_per_second": 24.798,
      "eval_steps_per_second": 6.2,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7.99521286127616e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}