{
  "best_metric": 0.23564165830612183,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.017063754452573427,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.531877226286714e-05,
      "grad_norm": 1.2464861869812012,
      "learning_rate": 1e-05,
      "loss": 0.4214,
      "step": 1
    },
    {
      "epoch": 8.531877226286714e-05,
      "eval_loss": 0.7482507228851318,
      "eval_runtime": 1483.5317,
      "eval_samples_per_second": 13.306,
      "eval_steps_per_second": 3.327,
      "step": 1
    },
    {
      "epoch": 0.00017063754452573428,
      "grad_norm": 1.5281243324279785,
      "learning_rate": 2e-05,
      "loss": 0.532,
      "step": 2
    },
    {
      "epoch": 0.00025595631678860143,
      "grad_norm": 1.6495031118392944,
      "learning_rate": 3e-05,
      "loss": 0.5322,
      "step": 3
    },
    {
      "epoch": 0.00034127508905146855,
      "grad_norm": 1.5111128091812134,
      "learning_rate": 4e-05,
      "loss": 0.4668,
      "step": 4
    },
    {
      "epoch": 0.0004265938613143357,
      "grad_norm": 1.3864272832870483,
      "learning_rate": 5e-05,
      "loss": 0.3644,
      "step": 5
    },
    {
      "epoch": 0.0005119126335772029,
      "grad_norm": 1.4793012142181396,
      "learning_rate": 6e-05,
      "loss": 0.3305,
      "step": 6
    },
    {
      "epoch": 0.0005972314058400699,
      "grad_norm": 1.3043208122253418,
      "learning_rate": 7e-05,
      "loss": 0.325,
      "step": 7
    },
    {
      "epoch": 0.0006825501781029371,
      "grad_norm": 1.21058988571167,
      "learning_rate": 8e-05,
      "loss": 0.3634,
      "step": 8
    },
    {
      "epoch": 0.0007678689503658043,
      "grad_norm": 1.0812054872512817,
      "learning_rate": 9e-05,
      "loss": 0.3319,
      "step": 9
    },
    {
      "epoch": 0.0008531877226286714,
      "grad_norm": 1.0187865495681763,
      "learning_rate": 0.0001,
      "loss": 0.3057,
      "step": 10
    },
    {
      "epoch": 0.0009385064948915385,
      "grad_norm": 1.0747543573379517,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.2975,
      "step": 11
    },
    {
      "epoch": 0.0010238252671544057,
      "grad_norm": 0.8817413449287415,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2442,
      "step": 12
    },
    {
      "epoch": 0.0011091440394172729,
      "grad_norm": 0.9227721095085144,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2863,
      "step": 13
    },
    {
      "epoch": 0.0011944628116801399,
      "grad_norm": 0.9496636986732483,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2912,
      "step": 14
    },
    {
      "epoch": 0.001279781583943007,
      "grad_norm": 0.9581251740455627,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.3178,
      "step": 15
    },
    {
      "epoch": 0.0013651003562058742,
      "grad_norm": 0.9072206020355225,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2662,
      "step": 16
    },
    {
      "epoch": 0.0014504191284687414,
      "grad_norm": 0.9696200489997864,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.2656,
      "step": 17
    },
    {
      "epoch": 0.0015357379007316086,
      "grad_norm": 0.9928320050239563,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.3002,
      "step": 18
    },
    {
      "epoch": 0.0016210566729944755,
      "grad_norm": 1.0626753568649292,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.3232,
      "step": 19
    },
    {
      "epoch": 0.0017063754452573427,
      "grad_norm": 0.9923722147941589,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3036,
      "step": 20
    },
    {
      "epoch": 0.0017916942175202099,
      "grad_norm": 1.0356357097625732,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3039,
      "step": 21
    },
    {
      "epoch": 0.001877012989783077,
      "grad_norm": 0.9788214564323425,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2962,
      "step": 22
    },
    {
      "epoch": 0.001962331762045944,
      "grad_norm": 0.9420165419578552,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2941,
      "step": 23
    },
    {
      "epoch": 0.0020476505343088114,
      "grad_norm": 1.023369312286377,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3314,
      "step": 24
    },
    {
      "epoch": 0.0021329693065716784,
      "grad_norm": 0.9040637016296387,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.2702,
      "step": 25
    },
    {
      "epoch": 0.0022182880788345458,
      "grad_norm": 0.9994131922721863,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3051,
      "step": 26
    },
    {
      "epoch": 0.0023036068510974127,
      "grad_norm": 0.8970037698745728,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2412,
      "step": 27
    },
    {
      "epoch": 0.0023889256233602797,
      "grad_norm": 0.9744396805763245,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2832,
      "step": 28
    },
    {
      "epoch": 0.002474244395623147,
      "grad_norm": 0.997397780418396,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2371,
      "step": 29
    },
    {
      "epoch": 0.002559563167886014,
      "grad_norm": 1.0509902238845825,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3107,
      "step": 30
    },
    {
      "epoch": 0.0026448819401488815,
      "grad_norm": 1.0135645866394043,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.306,
      "step": 31
    },
    {
      "epoch": 0.0027302007124117484,
      "grad_norm": 1.0272971391677856,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2744,
      "step": 32
    },
    {
      "epoch": 0.0028155194846746154,
      "grad_norm": 0.9856159090995789,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2923,
      "step": 33
    },
    {
      "epoch": 0.0029008382569374828,
      "grad_norm": 0.9450370073318481,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2643,
      "step": 34
    },
    {
      "epoch": 0.0029861570292003497,
      "grad_norm": 1.0237394571304321,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.314,
      "step": 35
    },
    {
      "epoch": 0.003071475801463217,
      "grad_norm": 1.0201995372772217,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2792,
      "step": 36
    },
    {
      "epoch": 0.003156794573726084,
      "grad_norm": 1.0572022199630737,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2912,
      "step": 37
    },
    {
      "epoch": 0.003242113345988951,
      "grad_norm": 1.1516457796096802,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3039,
      "step": 38
    },
    {
      "epoch": 0.0033274321182518185,
      "grad_norm": 1.0593175888061523,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2966,
      "step": 39
    },
    {
      "epoch": 0.0034127508905146854,
      "grad_norm": 1.0439590215682983,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2674,
      "step": 40
    },
    {
      "epoch": 0.003498069662777553,
      "grad_norm": 1.1773626804351807,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.298,
      "step": 41
    },
    {
      "epoch": 0.0035833884350404198,
      "grad_norm": 1.09316086769104,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.2878,
      "step": 42
    },
    {
      "epoch": 0.0036687072073032867,
      "grad_norm": 1.0136131048202515,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2619,
      "step": 43
    },
    {
      "epoch": 0.003754025979566154,
      "grad_norm": 1.061280608177185,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3142,
      "step": 44
    },
    {
      "epoch": 0.003839344751829021,
      "grad_norm": 1.0769422054290771,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2805,
      "step": 45
    },
    {
      "epoch": 0.003924663524091888,
      "grad_norm": 1.2159357070922852,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2998,
      "step": 46
    },
    {
      "epoch": 0.0040099822963547554,
      "grad_norm": 1.0424118041992188,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2641,
      "step": 47
    },
    {
      "epoch": 0.004095301068617623,
      "grad_norm": 1.5114845037460327,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3071,
      "step": 48
    },
    {
      "epoch": 0.004180619840880489,
      "grad_norm": 1.5022063255310059,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3376,
      "step": 49
    },
    {
      "epoch": 0.004265938613143357,
      "grad_norm": 1.8348913192749023,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3647,
      "step": 50
    },
    {
      "epoch": 0.004265938613143357,
      "eval_loss": 0.3193605840206146,
      "eval_runtime": 1490.9395,
      "eval_samples_per_second": 13.24,
      "eval_steps_per_second": 3.31,
      "step": 50
    },
    {
      "epoch": 0.004351257385406224,
      "grad_norm": 1.4306588172912598,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4202,
      "step": 51
    },
    {
      "epoch": 0.0044365761576690916,
      "grad_norm": 1.0270633697509766,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3468,
      "step": 52
    },
    {
      "epoch": 0.004521894929931958,
      "grad_norm": 0.686927080154419,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3232,
      "step": 53
    },
    {
      "epoch": 0.0046072137021948255,
      "grad_norm": 0.6519087553024292,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2586,
      "step": 54
    },
    {
      "epoch": 0.004692532474457693,
      "grad_norm": 0.7089278697967529,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.2663,
      "step": 55
    },
    {
      "epoch": 0.004777851246720559,
      "grad_norm": 0.7305288910865784,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.2777,
      "step": 56
    },
    {
      "epoch": 0.004863170018983427,
      "grad_norm": 0.6100066304206848,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2407,
      "step": 57
    },
    {
      "epoch": 0.004948488791246294,
      "grad_norm": 0.6845047473907471,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2532,
      "step": 58
    },
    {
      "epoch": 0.005033807563509161,
      "grad_norm": 0.7084606885910034,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2842,
      "step": 59
    },
    {
      "epoch": 0.005119126335772028,
      "grad_norm": 0.682884693145752,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2672,
      "step": 60
    },
    {
      "epoch": 0.0052044451080348955,
      "grad_norm": 0.5755671262741089,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1856,
      "step": 61
    },
    {
      "epoch": 0.005289763880297763,
      "grad_norm": 0.7196089029312134,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.2408,
      "step": 62
    },
    {
      "epoch": 0.0053750826525606294,
      "grad_norm": 0.7290205359458923,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2473,
      "step": 63
    },
    {
      "epoch": 0.005460401424823497,
      "grad_norm": 0.7057019472122192,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2628,
      "step": 64
    },
    {
      "epoch": 0.005545720197086364,
      "grad_norm": 0.698653519153595,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2402,
      "step": 65
    },
    {
      "epoch": 0.005631038969349231,
      "grad_norm": 0.797401487827301,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2975,
      "step": 66
    },
    {
      "epoch": 0.005716357741612098,
      "grad_norm": 0.7598553895950317,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2662,
      "step": 67
    },
    {
      "epoch": 0.0058016765138749656,
      "grad_norm": 0.8131743669509888,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.2826,
      "step": 68
    },
    {
      "epoch": 0.005886995286137832,
      "grad_norm": 0.7249765992164612,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.266,
      "step": 69
    },
    {
      "epoch": 0.0059723140584006995,
      "grad_norm": 0.758956789970398,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.275,
      "step": 70
    },
    {
      "epoch": 0.006057632830663567,
      "grad_norm": 0.804485023021698,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2477,
      "step": 71
    },
    {
      "epoch": 0.006142951602926434,
      "grad_norm": 0.8069186210632324,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3032,
      "step": 72
    },
    {
      "epoch": 0.006228270375189301,
      "grad_norm": 0.8778233528137207,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3149,
      "step": 73
    },
    {
      "epoch": 0.006313589147452168,
      "grad_norm": 0.7881379127502441,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2377,
      "step": 74
    },
    {
      "epoch": 0.006398907919715036,
      "grad_norm": 1.2000892162322998,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2647,
      "step": 75
    },
    {
      "epoch": 0.006484226691977902,
      "grad_norm": 0.7718772888183594,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2428,
      "step": 76
    },
    {
      "epoch": 0.0065695454642407695,
      "grad_norm": 0.7269161343574524,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.2374,
      "step": 77
    },
    {
      "epoch": 0.006654864236503637,
      "grad_norm": 0.8207325339317322,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2384,
      "step": 78
    },
    {
      "epoch": 0.006740183008766503,
      "grad_norm": 0.8615207672119141,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.2582,
      "step": 79
    },
    {
      "epoch": 0.006825501781029371,
      "grad_norm": 0.8644890189170837,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.2697,
      "step": 80
    },
    {
      "epoch": 0.006910820553292238,
      "grad_norm": 0.8401942253112793,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2651,
      "step": 81
    },
    {
      "epoch": 0.006996139325555106,
      "grad_norm": 0.8869915008544922,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3013,
      "step": 82
    },
    {
      "epoch": 0.007081458097817972,
      "grad_norm": 0.8247209191322327,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2566,
      "step": 83
    },
    {
      "epoch": 0.0071667768700808395,
      "grad_norm": 0.8518325686454773,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2569,
      "step": 84
    },
    {
      "epoch": 0.007252095642343707,
      "grad_norm": 0.8171535730361938,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2545,
      "step": 85
    },
    {
      "epoch": 0.0073374144146065735,
      "grad_norm": 1.149787425994873,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2415,
      "step": 86
    },
    {
      "epoch": 0.007422733186869441,
      "grad_norm": 0.8294546604156494,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2572,
      "step": 87
    },
    {
      "epoch": 0.007508051959132308,
      "grad_norm": 0.8672974109649658,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2332,
      "step": 88
    },
    {
      "epoch": 0.007593370731395176,
      "grad_norm": 1.1290428638458252,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3217,
      "step": 89
    },
    {
      "epoch": 0.007678689503658042,
      "grad_norm": 1.0930269956588745,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2989,
      "step": 90
    },
    {
      "epoch": 0.00776400827592091,
      "grad_norm": 1.3688007593154907,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2511,
      "step": 91
    },
    {
      "epoch": 0.007849327048183776,
      "grad_norm": 0.9447515606880188,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2585,
      "step": 92
    },
    {
      "epoch": 0.007934645820446644,
      "grad_norm": 1.0924570560455322,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.2975,
      "step": 93
    },
    {
      "epoch": 0.008019964592709511,
      "grad_norm": 0.9857505559921265,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2445,
      "step": 94
    },
    {
      "epoch": 0.008105283364972378,
      "grad_norm": 0.9534607529640198,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2287,
      "step": 95
    },
    {
      "epoch": 0.008190602137235246,
      "grad_norm": 1.0266928672790527,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.2782,
      "step": 96
    },
    {
      "epoch": 0.008275920909498113,
      "grad_norm": 0.9990158677101135,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2623,
      "step": 97
    },
    {
      "epoch": 0.008361239681760979,
      "grad_norm": 1.167478322982788,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2732,
      "step": 98
    },
    {
      "epoch": 0.008446558454023846,
      "grad_norm": 1.2563468217849731,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2993,
      "step": 99
    },
    {
      "epoch": 0.008531877226286714,
      "grad_norm": 1.479835867881775,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3311,
      "step": 100
    },
    {
      "epoch": 0.008531877226286714,
      "eval_loss": 0.289458304643631,
      "eval_runtime": 1491.6906,
      "eval_samples_per_second": 13.233,
      "eval_steps_per_second": 3.308,
      "step": 100
    },
    {
      "epoch": 0.008617195998549581,
      "grad_norm": 0.9032772183418274,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3579,
      "step": 101
    },
    {
      "epoch": 0.008702514770812448,
      "grad_norm": 0.8081871271133423,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3355,
      "step": 102
    },
    {
      "epoch": 0.008787833543075316,
      "grad_norm": 0.6597061157226562,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2763,
      "step": 103
    },
    {
      "epoch": 0.008873152315338183,
      "grad_norm": 0.604412853717804,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2498,
      "step": 104
    },
    {
      "epoch": 0.008958471087601049,
      "grad_norm": 0.6138935089111328,
      "learning_rate": 5e-05,
      "loss": 0.2511,
      "step": 105
    },
    {
      "epoch": 0.009043789859863916,
      "grad_norm": 0.5212016105651855,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2301,
      "step": 106
    },
    {
      "epoch": 0.009129108632126784,
      "grad_norm": 0.5596919655799866,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2405,
      "step": 107
    },
    {
      "epoch": 0.009214427404389651,
      "grad_norm": 0.5765125751495361,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2322,
      "step": 108
    },
    {
      "epoch": 0.009299746176652518,
      "grad_norm": 0.6592385172843933,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.2766,
      "step": 109
    },
    {
      "epoch": 0.009385064948915386,
      "grad_norm": 0.5780729651451111,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.2318,
      "step": 110
    },
    {
      "epoch": 0.009470383721178251,
      "grad_norm": 0.5643982291221619,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.211,
      "step": 111
    },
    {
      "epoch": 0.009555702493441119,
      "grad_norm": 0.620904803276062,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2637,
      "step": 112
    },
    {
      "epoch": 0.009641021265703986,
      "grad_norm": 0.6117725372314453,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2407,
      "step": 113
    },
    {
      "epoch": 0.009726340037966854,
      "grad_norm": 0.6310005187988281,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2699,
      "step": 114
    },
    {
      "epoch": 0.009811658810229721,
      "grad_norm": 0.6059605479240417,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2172,
      "step": 115
    },
    {
      "epoch": 0.009896977582492588,
      "grad_norm": 0.7402892112731934,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.2434,
      "step": 116
    },
    {
      "epoch": 0.009982296354755456,
      "grad_norm": 0.7294708490371704,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.235,
      "step": 117
    },
    {
      "epoch": 0.010067615127018321,
      "grad_norm": 0.644306480884552,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.2424,
      "step": 118
    },
    {
      "epoch": 0.010152933899281189,
      "grad_norm": 0.6743088960647583,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2314,
      "step": 119
    },
    {
      "epoch": 0.010238252671544056,
      "grad_norm": 0.7130791544914246,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2807,
      "step": 120
    },
    {
      "epoch": 0.010323571443806924,
      "grad_norm": 0.7781491875648499,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2441,
      "step": 121
    },
    {
      "epoch": 0.010408890216069791,
      "grad_norm": 0.7216753363609314,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.2729,
      "step": 122
    },
    {
      "epoch": 0.010494208988332658,
      "grad_norm": 0.7023508548736572,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2646,
      "step": 123
    },
    {
      "epoch": 0.010579527760595526,
      "grad_norm": 0.72576904296875,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2596,
      "step": 124
    },
    {
      "epoch": 0.010664846532858391,
      "grad_norm": 0.7103844285011292,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.233,
      "step": 125
    },
    {
      "epoch": 0.010750165305121259,
      "grad_norm": 0.6678680777549744,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2312,
      "step": 126
    },
    {
      "epoch": 0.010835484077384126,
      "grad_norm": 0.7078672051429749,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2339,
      "step": 127
    },
    {
      "epoch": 0.010920802849646994,
      "grad_norm": 0.8453111052513123,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2782,
      "step": 128
    },
    {
      "epoch": 0.011006121621909861,
      "grad_norm": 0.8020609021186829,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2809,
      "step": 129
    },
    {
      "epoch": 0.011091440394172728,
      "grad_norm": 0.6998770236968994,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.233,
      "step": 130
    },
    {
      "epoch": 0.011176759166435594,
      "grad_norm": 0.758491039276123,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2558,
      "step": 131
    },
    {
      "epoch": 0.011262077938698462,
      "grad_norm": 0.8167868852615356,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.268,
      "step": 132
    },
    {
      "epoch": 0.011347396710961329,
      "grad_norm": 0.7342557311058044,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2178,
      "step": 133
    },
    {
      "epoch": 0.011432715483224196,
      "grad_norm": 0.7934457659721375,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2338,
      "step": 134
    },
    {
      "epoch": 0.011518034255487064,
      "grad_norm": 0.8661943078041077,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2701,
      "step": 135
    },
    {
      "epoch": 0.011603353027749931,
      "grad_norm": 0.8646010160446167,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2557,
      "step": 136
    },
    {
      "epoch": 0.011688671800012798,
      "grad_norm": 0.8198699951171875,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2446,
      "step": 137
    },
    {
      "epoch": 0.011773990572275664,
      "grad_norm": 0.7358266115188599,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2028,
      "step": 138
    },
    {
      "epoch": 0.011859309344538532,
      "grad_norm": 0.7880418300628662,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.222,
      "step": 139
    },
    {
      "epoch": 0.011944628116801399,
      "grad_norm": 0.7976980805397034,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2108,
      "step": 140
    },
    {
      "epoch": 0.012029946889064266,
      "grad_norm": 0.8414627313613892,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.2495,
      "step": 141
    },
    {
      "epoch": 0.012115265661327134,
      "grad_norm": 0.7766191363334656,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.1911,
      "step": 142
    },
    {
      "epoch": 0.012200584433590001,
      "grad_norm": 0.8738869428634644,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2331,
      "step": 143
    },
    {
      "epoch": 0.012285903205852869,
      "grad_norm": 0.9872680306434631,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2705,
      "step": 144
    },
    {
      "epoch": 0.012371221978115734,
      "grad_norm": 0.8350234627723694,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2319,
      "step": 145
    },
    {
      "epoch": 0.012456540750378602,
      "grad_norm": 1.025537133216858,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2773,
      "step": 146
    },
    {
      "epoch": 0.012541859522641469,
      "grad_norm": 0.9157933592796326,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2232,
      "step": 147
    },
    {
      "epoch": 0.012627178294904336,
      "grad_norm": 1.1109967231750488,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2734,
      "step": 148
    },
    {
      "epoch": 0.012712497067167204,
      "grad_norm": 1.05686616897583,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.2682,
      "step": 149
    },
    {
      "epoch": 0.012797815839430071,
      "grad_norm": 1.449411392211914,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3932,
      "step": 150
    },
    {
      "epoch": 0.012797815839430071,
      "eval_loss": 0.24746929109096527,
      "eval_runtime": 1491.868,
      "eval_samples_per_second": 13.232,
      "eval_steps_per_second": 3.308,
      "step": 150
    },
    {
      "epoch": 0.012883134611692939,
      "grad_norm": 0.5403258204460144,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3059,
      "step": 151
    },
    {
      "epoch": 0.012968453383955804,
      "grad_norm": 0.6402106285095215,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.267,
      "step": 152
    },
    {
      "epoch": 0.013053772156218672,
      "grad_norm": 0.6450059413909912,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.3025,
      "step": 153
    },
    {
      "epoch": 0.013139090928481539,
      "grad_norm": 0.6216607093811035,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2539,
      "step": 154
    },
    {
      "epoch": 0.013224409700744406,
      "grad_norm": 0.5774719715118408,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.229,
      "step": 155
    },
    {
      "epoch": 0.013309728473007274,
      "grad_norm": 0.5633203387260437,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.222,
      "step": 156
    },
    {
      "epoch": 0.013395047245270141,
      "grad_norm": 0.5804242491722107,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.2079,
      "step": 157
    },
    {
      "epoch": 0.013480366017533007,
      "grad_norm": 0.5956029891967773,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2118,
      "step": 158
    },
    {
      "epoch": 0.013565684789795874,
      "grad_norm": 0.5941432118415833,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2451,
      "step": 159
    },
    {
      "epoch": 0.013651003562058742,
      "grad_norm": 0.5543824434280396,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.2152,
      "step": 160
    },
    {
      "epoch": 0.013736322334321609,
      "grad_norm": 0.5527306795120239,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.2048,
      "step": 161
    },
    {
      "epoch": 0.013821641106584476,
      "grad_norm": 0.5387033820152283,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2088,
      "step": 162
    },
    {
      "epoch": 0.013906959878847344,
      "grad_norm": 0.6048414707183838,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.2069,
      "step": 163
    },
    {
      "epoch": 0.013992278651110211,
      "grad_norm": 0.5967785120010376,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.2325,
      "step": 164
    },
    {
      "epoch": 0.014077597423373077,
      "grad_norm": 0.6019954681396484,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2269,
      "step": 165
    },
    {
      "epoch": 0.014162916195635944,
      "grad_norm": 0.6287665367126465,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.2394,
      "step": 166
    },
    {
      "epoch": 0.014248234967898812,
      "grad_norm": 0.5563615560531616,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2056,
      "step": 167
    },
    {
      "epoch": 0.014333553740161679,
      "grad_norm": 0.6922852993011475,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2392,
      "step": 168
    },
    {
      "epoch": 0.014418872512424546,
      "grad_norm": 0.5828565955162048,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2187,
      "step": 169
    },
    {
      "epoch": 0.014504191284687414,
      "grad_norm": 0.5800209045410156,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1853,
      "step": 170
    },
    {
      "epoch": 0.014589510056950281,
      "grad_norm": 0.616269052028656,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2233,
      "step": 171
    },
    {
      "epoch": 0.014674828829213147,
      "grad_norm": 0.6804556846618652,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2605,
      "step": 172
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.6499509811401367,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2317,
      "step": 173
    },
    {
      "epoch": 0.014845466373738882,
      "grad_norm": 0.7500078678131104,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2708,
      "step": 174
    },
    {
      "epoch": 0.014930785146001749,
      "grad_norm": 0.7017810344696045,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2393,
      "step": 175
    },
    {
      "epoch": 0.015016103918264617,
      "grad_norm": 0.7403309941291809,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.2349,
      "step": 176
    },
    {
      "epoch": 0.015101422690527484,
      "grad_norm": 0.7385720610618591,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2363,
      "step": 177
    },
    {
      "epoch": 0.015186741462790351,
      "grad_norm": 0.7304592728614807,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2542,
      "step": 178
    },
    {
      "epoch": 0.015272060235053217,
      "grad_norm": 0.6861647963523865,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.241,
      "step": 179
    },
    {
      "epoch": 0.015357379007316084,
      "grad_norm": 0.7816575169563293,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2829,
      "step": 180
    },
    {
      "epoch": 0.015442697779578952,
      "grad_norm": 0.7072176933288574,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2145,
      "step": 181
    },
    {
      "epoch": 0.01552801655184182,
      "grad_norm": 0.7830233573913574,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2672,
      "step": 182
    },
    {
      "epoch": 0.015613335324104687,
      "grad_norm": 0.7226740717887878,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2444,
      "step": 183
    },
    {
      "epoch": 0.015698654096367552,
      "grad_norm": 0.797498881816864,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2648,
      "step": 184
    },
    {
      "epoch": 0.01578397286863042,
      "grad_norm": 0.7293609380722046,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2195,
      "step": 185
    },
    {
      "epoch": 0.015869291640893287,
      "grad_norm": 0.7652772068977356,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2377,
      "step": 186
    },
    {
      "epoch": 0.015954610413156156,
      "grad_norm": 0.8103626370429993,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.2513,
      "step": 187
    },
    {
      "epoch": 0.016039929185419022,
      "grad_norm": 0.7453922033309937,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2236,
      "step": 188
    },
    {
      "epoch": 0.016125247957681887,
      "grad_norm": 0.7586413025856018,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2109,
      "step": 189
    },
    {
      "epoch": 0.016210566729944757,
      "grad_norm": 0.8357709050178528,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.2276,
      "step": 190
    },
    {
      "epoch": 0.016295885502207622,
      "grad_norm": 0.8202524185180664,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2402,
      "step": 191
    },
    {
      "epoch": 0.01638120427447049,
      "grad_norm": 0.8759474158287048,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2615,
      "step": 192
    },
    {
      "epoch": 0.016466523046733357,
      "grad_norm": 0.9401312470436096,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.2839,
      "step": 193
    },
    {
      "epoch": 0.016551841818996226,
      "grad_norm": 0.9110872745513916,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2532,
      "step": 194
    },
    {
      "epoch": 0.016637160591259092,
      "grad_norm": 1.0322833061218262,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2967,
      "step": 195
    },
    {
      "epoch": 0.016722479363521957,
      "grad_norm": 0.8920602202415466,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.2502,
      "step": 196
    },
    {
      "epoch": 0.016807798135784827,
      "grad_norm": 0.9985930919647217,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.2706,
      "step": 197
    },
    {
      "epoch": 0.016893116908047692,
      "grad_norm": 1.1254011392593384,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2851,
      "step": 198
    },
    {
      "epoch": 0.01697843568031056,
      "grad_norm": 1.5885820388793945,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3014,
      "step": 199
    },
    {
      "epoch": 0.017063754452573427,
      "grad_norm": 1.5242902040481567,
      "learning_rate": 0.0,
      "loss": 0.3512,
      "step": 200
    },
    {
      "epoch": 0.017063754452573427,
      "eval_loss": 0.23564165830612183,
      "eval_runtime": 1490.6497,
      "eval_samples_per_second": 13.243,
      "eval_steps_per_second": 3.311,
      "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": 2.876307616730972e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}