{
  "best_metric": 1.0687636137008667,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.032416224320272295,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016208112160136148,
      "grad_norm": 1.4745482206344604,
      "learning_rate": 1e-05,
      "loss": 4.1044,
      "step": 1
    },
    {
      "epoch": 0.00016208112160136148,
      "eval_loss": 1.1832860708236694,
      "eval_runtime": 620.5828,
      "eval_samples_per_second": 16.746,
      "eval_steps_per_second": 4.186,
      "step": 1
    },
    {
      "epoch": 0.00032416224320272295,
      "grad_norm": 1.285522222518921,
      "learning_rate": 2e-05,
      "loss": 4.3271,
      "step": 2
    },
    {
      "epoch": 0.00048624336480408443,
      "grad_norm": 1.335143804550171,
      "learning_rate": 3e-05,
      "loss": 4.8634,
      "step": 3
    },
    {
      "epoch": 0.0006483244864054459,
      "grad_norm": 1.3842264413833618,
      "learning_rate": 4e-05,
      "loss": 4.7529,
      "step": 4
    },
    {
      "epoch": 0.0008104056080068074,
      "grad_norm": 0.994800865650177,
      "learning_rate": 5e-05,
      "loss": 4.0747,
      "step": 5
    },
    {
      "epoch": 0.0009724867296081689,
      "grad_norm": 0.7915685772895813,
      "learning_rate": 6e-05,
      "loss": 3.8156,
      "step": 6
    },
    {
      "epoch": 0.0011345678512095303,
      "grad_norm": 0.760496199131012,
      "learning_rate": 7e-05,
      "loss": 4.0043,
      "step": 7
    },
    {
      "epoch": 0.0012966489728108918,
      "grad_norm": 0.6685930490493774,
      "learning_rate": 8e-05,
      "loss": 4.5498,
      "step": 8
    },
    {
      "epoch": 0.0014587300944122533,
      "grad_norm": 0.6834664940834045,
      "learning_rate": 9e-05,
      "loss": 4.3309,
      "step": 9
    },
    {
      "epoch": 0.0016208112160136148,
      "grad_norm": 0.8207894563674927,
      "learning_rate": 0.0001,
      "loss": 4.3685,
      "step": 10
    },
    {
      "epoch": 0.0017828923376149762,
      "grad_norm": 0.8365195393562317,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.3908,
      "step": 11
    },
    {
      "epoch": 0.0019449734592163377,
      "grad_norm": 0.7589403986930847,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.0645,
      "step": 12
    },
    {
      "epoch": 0.002107054580817699,
      "grad_norm": 0.686841607093811,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.2938,
      "step": 13
    },
    {
      "epoch": 0.0022691357024190607,
      "grad_norm": 0.6511795520782471,
      "learning_rate": 9.989068136093873e-05,
      "loss": 4.178,
      "step": 14
    },
    {
      "epoch": 0.002431216824020422,
      "grad_norm": 0.6714349389076233,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.1767,
      "step": 15
    },
    {
      "epoch": 0.0025932979456217836,
      "grad_norm": 0.6749226450920105,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.2671,
      "step": 16
    },
    {
      "epoch": 0.002755379067223145,
      "grad_norm": 0.6431313753128052,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.8208,
      "step": 17
    },
    {
      "epoch": 0.0029174601888245066,
      "grad_norm": 0.8135528564453125,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.3844,
      "step": 18
    },
    {
      "epoch": 0.003079541310425868,
      "grad_norm": 0.6886083483695984,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.2619,
      "step": 19
    },
    {
      "epoch": 0.0032416224320272295,
      "grad_norm": 0.6730997562408447,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.196,
      "step": 20
    },
    {
      "epoch": 0.003403703553628591,
      "grad_norm": 0.6361275911331177,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.4178,
      "step": 21
    },
    {
      "epoch": 0.0035657846752299525,
      "grad_norm": 0.6108586192131042,
      "learning_rate": 9.901899829374047e-05,
      "loss": 4.153,
      "step": 22
    },
    {
      "epoch": 0.003727865796831314,
      "grad_norm": 0.6017228960990906,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.9051,
      "step": 23
    },
    {
      "epoch": 0.0038899469184326754,
      "grad_norm": 0.6435880661010742,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.1171,
      "step": 24
    },
    {
      "epoch": 0.004052028040034037,
      "grad_norm": 0.6439114212989807,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.1763,
      "step": 25
    },
    {
      "epoch": 0.004214109161635398,
      "grad_norm": 0.698366641998291,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.9537,
      "step": 26
    },
    {
      "epoch": 0.00437619028323676,
      "grad_norm": 0.7522488832473755,
      "learning_rate": 9.803768380684242e-05,
      "loss": 4.3705,
      "step": 27
    },
    {
      "epoch": 0.004538271404838121,
      "grad_norm": 0.6683444976806641,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.3137,
      "step": 28
    },
    {
      "epoch": 0.004700352526439483,
      "grad_norm": 0.6507847905158997,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.0125,
      "step": 29
    },
    {
      "epoch": 0.004862433648040844,
      "grad_norm": 0.7175493836402893,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.0479,
      "step": 30
    },
    {
      "epoch": 0.005024514769642206,
      "grad_norm": 0.8238893151283264,
      "learning_rate": 9.701596950580806e-05,
      "loss": 4.392,
      "step": 31
    },
    {
      "epoch": 0.005186595891243567,
      "grad_norm": 0.7261873483657837,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.092,
      "step": 32
    },
    {
      "epoch": 0.005348677012844929,
      "grad_norm": 0.7629175782203674,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.4373,
      "step": 33
    },
    {
      "epoch": 0.00551075813444629,
      "grad_norm": 0.7119680047035217,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.195,
      "step": 34
    },
    {
      "epoch": 0.005672839256047652,
      "grad_norm": 0.8018630743026733,
      "learning_rate": 9.578866633275288e-05,
      "loss": 4.6156,
      "step": 35
    },
    {
      "epoch": 0.005834920377649013,
      "grad_norm": 0.7650766968727112,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.4107,
      "step": 36
    },
    {
      "epoch": 0.005997001499250375,
      "grad_norm": 1.3296184539794922,
      "learning_rate": 9.509956150664796e-05,
      "loss": 4.5631,
      "step": 37
    },
    {
      "epoch": 0.006159082620851736,
      "grad_norm": 0.9296122193336487,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.7538,
      "step": 38
    },
    {
      "epoch": 0.006321163742453098,
      "grad_norm": 0.9114640355110168,
      "learning_rate": 9.43611409721806e-05,
      "loss": 4.8723,
      "step": 39
    },
    {
      "epoch": 0.006483244864054459,
      "grad_norm": 0.9263441562652588,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.2283,
      "step": 40
    },
    {
      "epoch": 0.0066453259856558205,
      "grad_norm": 0.937839686870575,
      "learning_rate": 9.357421218136386e-05,
      "loss": 4.8501,
      "step": 41
    },
    {
      "epoch": 0.006807407107257182,
      "grad_norm": 1.2569628953933716,
      "learning_rate": 9.316282404787871e-05,
      "loss": 5.3442,
      "step": 42
    },
    {
      "epoch": 0.0069694882288585435,
      "grad_norm": 0.9827930927276611,
      "learning_rate": 9.273963562927695e-05,
      "loss": 4.7776,
      "step": 43
    },
    {
      "epoch": 0.007131569350459905,
      "grad_norm": 1.2934597730636597,
      "learning_rate": 9.230476262104677e-05,
      "loss": 4.9483,
      "step": 44
    },
    {
      "epoch": 0.007293650472061266,
      "grad_norm": 1.0828169584274292,
      "learning_rate": 9.185832391312644e-05,
      "loss": 5.2057,
      "step": 45
    },
    {
      "epoch": 0.007455731593662628,
      "grad_norm": 1.2613872289657593,
      "learning_rate": 9.140044155740101e-05,
      "loss": 5.4434,
      "step": 46
    },
    {
      "epoch": 0.007617812715263989,
      "grad_norm": 1.3614377975463867,
      "learning_rate": 9.093124073433463e-05,
      "loss": 5.0157,
      "step": 47
    },
    {
      "epoch": 0.007779893836865351,
      "grad_norm": 1.6211588382720947,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.4575,
      "step": 48
    },
    {
      "epoch": 0.007941974958466713,
      "grad_norm": 2.0259907245635986,
      "learning_rate": 8.995939984474624e-05,
      "loss": 5.6708,
      "step": 49
    },
    {
      "epoch": 0.008104056080068074,
      "grad_norm": 2.6310853958129883,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.858,
      "step": 50
    },
    {
      "epoch": 0.008104056080068074,
      "eval_loss": 1.1202869415283203,
      "eval_runtime": 624.0,
      "eval_samples_per_second": 16.654,
      "eval_steps_per_second": 4.163,
      "step": 50
    },
    {
      "epoch": 0.008266137201669436,
      "grad_norm": 1.0332852602005005,
      "learning_rate": 8.894386393810563e-05,
      "loss": 4.6871,
      "step": 51
    },
    {
      "epoch": 0.008428218323270797,
      "grad_norm": 0.747059166431427,
      "learning_rate": 8.842005554284296e-05,
      "loss": 4.6101,
      "step": 52
    },
    {
      "epoch": 0.008590299444872159,
      "grad_norm": 0.7617971897125244,
      "learning_rate": 8.788574348801675e-05,
      "loss": 4.3059,
      "step": 53
    },
    {
      "epoch": 0.00875238056647352,
      "grad_norm": 0.6986435055732727,
      "learning_rate": 8.73410738492077e-05,
      "loss": 4.1676,
      "step": 54
    },
    {
      "epoch": 0.008914461688074882,
      "grad_norm": 0.6283707618713379,
      "learning_rate": 8.678619553365659e-05,
      "loss": 4.0447,
      "step": 55
    },
    {
      "epoch": 0.009076542809676243,
      "grad_norm": 0.5435439944267273,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.9407,
      "step": 56
    },
    {
      "epoch": 0.009238623931277605,
      "grad_norm": 0.6282440423965454,
      "learning_rate": 8.564642241456986e-05,
      "loss": 4.2496,
      "step": 57
    },
    {
      "epoch": 0.009400705052878966,
      "grad_norm": 0.5533632636070251,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.908,
      "step": 58
    },
    {
      "epoch": 0.009562786174480328,
      "grad_norm": 0.5285382270812988,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.8597,
      "step": 59
    },
    {
      "epoch": 0.009724867296081689,
      "grad_norm": 0.5500264763832092,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.9084,
      "step": 60
    },
    {
      "epoch": 0.009886948417683051,
      "grad_norm": 0.5860369801521301,
      "learning_rate": 8.32512286056924e-05,
      "loss": 4.3225,
      "step": 61
    },
    {
      "epoch": 0.010049029539284412,
      "grad_norm": 0.549226701259613,
      "learning_rate": 8.262928807620843e-05,
      "loss": 4.1944,
      "step": 62
    },
    {
      "epoch": 0.010211110660885774,
      "grad_norm": 0.5468707084655762,
      "learning_rate": 8.199842702516583e-05,
      "loss": 4.1808,
      "step": 63
    },
    {
      "epoch": 0.010373191782487134,
      "grad_norm": 0.5705710649490356,
      "learning_rate": 8.135881792367686e-05,
      "loss": 4.3865,
      "step": 64
    },
    {
      "epoch": 0.010535272904088497,
      "grad_norm": 0.5604478120803833,
      "learning_rate": 8.07106356344834e-05,
      "loss": 4.0285,
      "step": 65
    },
    {
      "epoch": 0.010697354025689857,
      "grad_norm": 0.5283072590827942,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.7654,
      "step": 66
    },
    {
      "epoch": 0.01085943514729122,
      "grad_norm": 0.6135756373405457,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.9427,
      "step": 67
    },
    {
      "epoch": 0.01102151626889258,
      "grad_norm": 0.5224963426589966,
      "learning_rate": 7.871643313414718e-05,
      "loss": 4.1028,
      "step": 68
    },
    {
      "epoch": 0.011183597390493943,
      "grad_norm": 0.5102367997169495,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.752,
      "step": 69
    },
    {
      "epoch": 0.011345678512095303,
      "grad_norm": 0.6364815831184387,
      "learning_rate": 7.734740790612136e-05,
      "loss": 4.2697,
      "step": 70
    },
    {
      "epoch": 0.011507759633696666,
      "grad_norm": 0.5517566800117493,
      "learning_rate": 7.66515864363997e-05,
      "loss": 4.3871,
      "step": 71
    },
    {
      "epoch": 0.011669840755298026,
      "grad_norm": 0.5636042952537537,
      "learning_rate": 7.594847868906076e-05,
      "loss": 4.1798,
      "step": 72
    },
    {
      "epoch": 0.011831921876899389,
      "grad_norm": 0.5331016778945923,
      "learning_rate": 7.52382768867422e-05,
      "loss": 4.1414,
      "step": 73
    },
    {
      "epoch": 0.01199400299850075,
      "grad_norm": 0.5853242874145508,
      "learning_rate": 7.452117519152542e-05,
      "loss": 4.2212,
      "step": 74
    },
    {
      "epoch": 0.012156084120102112,
      "grad_norm": 0.5571672320365906,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.9346,
      "step": 75
    },
    {
      "epoch": 0.012318165241703472,
      "grad_norm": 0.5618833303451538,
      "learning_rate": 7.30670581489344e-05,
      "loss": 4.046,
      "step": 76
    },
    {
      "epoch": 0.012480246363304835,
      "grad_norm": 0.590742290019989,
      "learning_rate": 7.233044034264034e-05,
      "loss": 4.191,
      "step": 77
    },
    {
      "epoch": 0.012642327484906195,
      "grad_norm": 0.6346542835235596,
      "learning_rate": 7.158771761692464e-05,
      "loss": 4.1737,
      "step": 78
    },
    {
      "epoch": 0.012804408606507557,
      "grad_norm": 0.6081542372703552,
      "learning_rate": 7.083909302476453e-05,
      "loss": 4.2878,
      "step": 79
    },
    {
      "epoch": 0.012966489728108918,
      "grad_norm": 0.5877219438552856,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.9882,
      "step": 80
    },
    {
      "epoch": 0.01312857084971028,
      "grad_norm": 0.6087138652801514,
      "learning_rate": 6.932495846462261e-05,
      "loss": 3.9351,
      "step": 81
    },
    {
      "epoch": 0.013290651971311641,
      "grad_norm": 0.6984849572181702,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.0993,
      "step": 82
    },
    {
      "epoch": 0.013452733092913003,
      "grad_norm": 0.7047072649002075,
      "learning_rate": 6.778969234612584e-05,
      "loss": 4.4722,
      "step": 83
    },
    {
      "epoch": 0.013614814214514364,
      "grad_norm": 0.6677774786949158,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.1163,
      "step": 84
    },
    {
      "epoch": 0.013776895336115726,
      "grad_norm": 0.7007635831832886,
      "learning_rate": 6.623497346023418e-05,
      "loss": 4.5499,
      "step": 85
    },
    {
      "epoch": 0.013938976457717087,
      "grad_norm": 0.7800924181938171,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.535,
      "step": 86
    },
    {
      "epoch": 0.01410105757931845,
      "grad_norm": 0.7068495154380798,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.5603,
      "step": 87
    },
    {
      "epoch": 0.01426313870091981,
      "grad_norm": 0.7155495285987854,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.2512,
      "step": 88
    },
    {
      "epoch": 0.014425219822521172,
      "grad_norm": 0.7719190716743469,
      "learning_rate": 6.307399704769099e-05,
      "loss": 4.9387,
      "step": 89
    },
    {
      "epoch": 0.014587300944122533,
      "grad_norm": 0.7631606459617615,
      "learning_rate": 6.227427435703997e-05,
      "loss": 4.6449,
      "step": 90
    },
    {
      "epoch": 0.014749382065723895,
      "grad_norm": 0.8474345803260803,
      "learning_rate": 6.147119600233758e-05,
      "loss": 4.7862,
      "step": 91
    },
    {
      "epoch": 0.014911463187325256,
      "grad_norm": 0.922042727470398,
      "learning_rate": 6.066498153718735e-05,
      "loss": 4.9097,
      "step": 92
    },
    {
      "epoch": 0.015073544308926618,
      "grad_norm": 0.9074467420578003,
      "learning_rate": 5.985585137257401e-05,
      "loss": 4.6718,
      "step": 93
    },
    {
      "epoch": 0.015235625430527979,
      "grad_norm": 0.9892921447753906,
      "learning_rate": 5.90440267166055e-05,
      "loss": 4.8383,
      "step": 94
    },
    {
      "epoch": 0.015397706552129341,
      "grad_norm": 1.0625590085983276,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 4.9755,
      "step": 95
    },
    {
      "epoch": 0.015559787673730702,
      "grad_norm": 1.2702600955963135,
      "learning_rate": 5.74131823855921e-05,
      "loss": 5.1954,
      "step": 96
    },
    {
      "epoch": 0.015721868795332064,
      "grad_norm": 1.2826322317123413,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 5.0106,
      "step": 97
    },
    {
      "epoch": 0.015883949916933426,
      "grad_norm": 1.510257363319397,
      "learning_rate": 5.577423184847932e-05,
      "loss": 5.2868,
      "step": 98
    },
    {
      "epoch": 0.016046031038534785,
      "grad_norm": 1.7453159093856812,
      "learning_rate": 5.495227651252315e-05,
      "loss": 5.1547,
      "step": 99
    },
    {
      "epoch": 0.016208112160136148,
      "grad_norm": 2.375579357147217,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 5.0376,
      "step": 100
    },
    {
      "epoch": 0.016208112160136148,
      "eval_loss": 1.0881792306900024,
      "eval_runtime": 624.3364,
      "eval_samples_per_second": 16.645,
      "eval_steps_per_second": 4.161,
      "step": 100
    },
    {
      "epoch": 0.01637019328173751,
      "grad_norm": 0.6187580823898315,
      "learning_rate": 5.330452921628497e-05,
      "loss": 4.5156,
      "step": 101
    },
    {
      "epoch": 0.016532274403338872,
      "grad_norm": 0.6246799826622009,
      "learning_rate": 5.247918773366112e-05,
      "loss": 4.0469,
      "step": 102
    },
    {
      "epoch": 0.01669435552494023,
      "grad_norm": 0.5039684772491455,
      "learning_rate": 5.165316846586541e-05,
      "loss": 3.6826,
      "step": 103
    },
    {
      "epoch": 0.016856436646541594,
      "grad_norm": 0.5332962870597839,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 3.9748,
      "step": 104
    },
    {
      "epoch": 0.017018517768142956,
      "grad_norm": 0.5618225336074829,
      "learning_rate": 5e-05,
      "loss": 3.8567,
      "step": 105
    },
    {
      "epoch": 0.017180598889744318,
      "grad_norm": 0.5520845651626587,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.9198,
      "step": 106
    },
    {
      "epoch": 0.017342680011345677,
      "grad_norm": 0.5245534777641296,
      "learning_rate": 4.834683153413459e-05,
      "loss": 4.2026,
      "step": 107
    },
    {
      "epoch": 0.01750476113294704,
      "grad_norm": 0.5384763479232788,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.7675,
      "step": 108
    },
    {
      "epoch": 0.017666842254548402,
      "grad_norm": 0.4949337840080261,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.9239,
      "step": 109
    },
    {
      "epoch": 0.017828923376149764,
      "grad_norm": 0.4994608163833618,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 4.1418,
      "step": 110
    },
    {
      "epoch": 0.017991004497751123,
      "grad_norm": 0.5684775710105896,
      "learning_rate": 4.504772348747687e-05,
      "loss": 4.5623,
      "step": 111
    },
    {
      "epoch": 0.018153085619352485,
      "grad_norm": 0.574091374874115,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.7195,
      "step": 112
    },
    {
      "epoch": 0.018315166740953848,
      "grad_norm": 0.4859822690486908,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.6939,
      "step": 113
    },
    {
      "epoch": 0.01847724786255521,
      "grad_norm": 0.5301849842071533,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 4.1891,
      "step": 114
    },
    {
      "epoch": 0.01863932898415657,
      "grad_norm": 0.5311679840087891,
      "learning_rate": 4.17702704859633e-05,
      "loss": 4.2976,
      "step": 115
    },
    {
      "epoch": 0.01880141010575793,
      "grad_norm": 0.5156587958335876,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.7888,
      "step": 116
    },
    {
      "epoch": 0.018963491227359294,
      "grad_norm": 0.5405213832855225,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.9363,
      "step": 117
    },
    {
      "epoch": 0.019125572348960656,
      "grad_norm": 0.5533437132835388,
      "learning_rate": 3.933501846281267e-05,
      "loss": 3.8027,
      "step": 118
    },
    {
      "epoch": 0.019287653470562015,
      "grad_norm": 0.5277832746505737,
      "learning_rate": 3.852880399766243e-05,
      "loss": 4.0641,
      "step": 119
    },
    {
      "epoch": 0.019449734592163377,
      "grad_norm": 0.5131419897079468,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.798,
      "step": 120
    },
    {
      "epoch": 0.01961181571376474,
      "grad_norm": 0.5670085549354553,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.9544,
      "step": 121
    },
    {
      "epoch": 0.019773896835366102,
      "grad_norm": 0.5438392162322998,
      "learning_rate": 3.612985456190778e-05,
      "loss": 3.9227,
      "step": 122
    },
    {
      "epoch": 0.01993597795696746,
      "grad_norm": 0.6062509417533875,
      "learning_rate": 3.533749813077677e-05,
      "loss": 4.2162,
      "step": 123
    },
    {
      "epoch": 0.020098059078568823,
      "grad_norm": 0.7059042453765869,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.1398,
      "step": 124
    },
    {
      "epoch": 0.020260140200170185,
      "grad_norm": 0.607876181602478,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 4.1374,
      "step": 125
    },
    {
      "epoch": 0.020422221321771548,
      "grad_norm": 1.104274868965149,
      "learning_rate": 3.298534127791785e-05,
      "loss": 4.0907,
      "step": 126
    },
    {
      "epoch": 0.020584302443372907,
      "grad_norm": 0.581818163394928,
      "learning_rate": 3.221030765387417e-05,
      "loss": 4.2269,
      "step": 127
    },
    {
      "epoch": 0.02074638356497427,
      "grad_norm": 0.6129099130630493,
      "learning_rate": 3.144013755408895e-05,
      "loss": 4.4692,
      "step": 128
    },
    {
      "epoch": 0.02090846468657563,
      "grad_norm": 0.5961942076683044,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 4.2893,
      "step": 129
    },
    {
      "epoch": 0.021070545808176994,
      "grad_norm": 0.5990215539932251,
      "learning_rate": 2.991522876735154e-05,
      "loss": 4.183,
      "step": 130
    },
    {
      "epoch": 0.021232626929778353,
      "grad_norm": 0.8488620519638062,
      "learning_rate": 2.916090697523549e-05,
      "loss": 4.1374,
      "step": 131
    },
    {
      "epoch": 0.021394708051379715,
      "grad_norm": 0.6188662648200989,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 4.188,
      "step": 132
    },
    {
      "epoch": 0.021556789172981077,
      "grad_norm": 0.6537730097770691,
      "learning_rate": 2.766955965735968e-05,
      "loss": 4.2448,
      "step": 133
    },
    {
      "epoch": 0.02171887029458244,
      "grad_norm": 0.6773059964179993,
      "learning_rate": 2.693294185106562e-05,
      "loss": 4.2455,
      "step": 134
    },
    {
      "epoch": 0.0218809514161838,
      "grad_norm": 0.7234086394309998,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 4.3657,
      "step": 135
    },
    {
      "epoch": 0.02204303253778516,
      "grad_norm": 0.6728505492210388,
      "learning_rate": 2.547882480847461e-05,
      "loss": 4.2846,
      "step": 136
    },
    {
      "epoch": 0.022205113659386523,
      "grad_norm": 0.6895965933799744,
      "learning_rate": 2.476172311325783e-05,
      "loss": 4.2759,
      "step": 137
    },
    {
      "epoch": 0.022367194780987885,
      "grad_norm": 0.7353618144989014,
      "learning_rate": 2.405152131093926e-05,
      "loss": 4.3118,
      "step": 138
    },
    {
      "epoch": 0.022529275902589244,
      "grad_norm": 0.7913398146629333,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 4.499,
      "step": 139
    },
    {
      "epoch": 0.022691357024190607,
      "grad_norm": 0.7670764923095703,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 4.452,
      "step": 140
    },
    {
      "epoch": 0.02285343814579197,
      "grad_norm": 0.8304184675216675,
      "learning_rate": 2.196424713241637e-05,
      "loss": 4.6864,
      "step": 141
    },
    {
      "epoch": 0.02301551926739333,
      "grad_norm": 0.8822210431098938,
      "learning_rate": 2.128356686585282e-05,
      "loss": 4.978,
      "step": 142
    },
    {
      "epoch": 0.02317760038899469,
      "grad_norm": 0.9127869009971619,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.9103,
      "step": 143
    },
    {
      "epoch": 0.023339681510596053,
      "grad_norm": 1.2543188333511353,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 5.0991,
      "step": 144
    },
    {
      "epoch": 0.023501762632197415,
      "grad_norm": 1.0401294231414795,
      "learning_rate": 1.928936436551661e-05,
      "loss": 4.8208,
      "step": 145
    },
    {
      "epoch": 0.023663843753798777,
      "grad_norm": 1.1212679147720337,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 4.992,
      "step": 146
    },
    {
      "epoch": 0.023825924875400136,
      "grad_norm": 1.1991173028945923,
      "learning_rate": 1.800157297483417e-05,
      "loss": 4.8723,
      "step": 147
    },
    {
      "epoch": 0.0239880059970015,
      "grad_norm": 1.3392255306243896,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 5.266,
      "step": 148
    },
    {
      "epoch": 0.02415008711860286,
      "grad_norm": 1.649901032447815,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 4.7033,
      "step": 149
    },
    {
      "epoch": 0.024312168240204223,
      "grad_norm": 2.471477746963501,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 4.3645,
      "step": 150
    },
    {
      "epoch": 0.024312168240204223,
      "eval_loss": 1.0702276229858398,
      "eval_runtime": 625.1523,
      "eval_samples_per_second": 16.623,
      "eval_steps_per_second": 4.156,
      "step": 150
    },
    {
      "epoch": 0.024474249361805582,
      "grad_norm": 0.45151543617248535,
      "learning_rate": 1.553232954407171e-05,
      "loss": 4.4925,
      "step": 151
    },
    {
      "epoch": 0.024636330483406944,
      "grad_norm": 0.44492843747138977,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 4.247,
      "step": 152
    },
    {
      "epoch": 0.024798411605008307,
      "grad_norm": 0.4191572666168213,
      "learning_rate": 1.435357758543015e-05,
      "loss": 4.2931,
      "step": 153
    },
    {
      "epoch": 0.02496049272660967,
      "grad_norm": 0.575943648815155,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 4.0529,
      "step": 154
    },
    {
      "epoch": 0.025122573848211028,
      "grad_norm": 0.42892712354660034,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.9695,
      "step": 155
    },
    {
      "epoch": 0.02528465496981239,
      "grad_norm": 0.476820170879364,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 4.2619,
      "step": 156
    },
    {
      "epoch": 0.025446736091413753,
      "grad_norm": 0.4546341300010681,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.125,
      "step": 157
    },
    {
      "epoch": 0.025608817213015115,
      "grad_norm": 0.4715096652507782,
      "learning_rate": 1.157994445715706e-05,
      "loss": 3.8411,
      "step": 158
    },
    {
      "epoch": 0.025770898334616474,
      "grad_norm": 0.5720945000648499,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 4.2697,
      "step": 159
    },
    {
      "epoch": 0.025932979456217836,
      "grad_norm": 0.4990689754486084,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.9126,
      "step": 160
    },
    {
      "epoch": 0.0260950605778192,
      "grad_norm": 0.4868318736553192,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 4.0911,
      "step": 161
    },
    {
      "epoch": 0.02625714169942056,
      "grad_norm": 0.5039429068565369,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.116,
      "step": 162
    },
    {
      "epoch": 0.02641922282102192,
      "grad_norm": 0.4937736690044403,
      "learning_rate": 9.068759265665384e-06,
      "loss": 4.305,
      "step": 163
    },
    {
      "epoch": 0.026581303942623282,
      "grad_norm": 0.48124879598617554,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.7253,
      "step": 164
    },
    {
      "epoch": 0.026743385064224644,
      "grad_norm": 0.5081772208213806,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.9544,
      "step": 165
    },
    {
      "epoch": 0.026905466185826007,
      "grad_norm": 0.5072429180145264,
      "learning_rate": 7.695237378953223e-06,
      "loss": 4.0707,
      "step": 166
    },
    {
      "epoch": 0.02706754730742737,
      "grad_norm": 0.5537675619125366,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.8029,
      "step": 167
    },
    {
      "epoch": 0.027229628429028728,
      "grad_norm": 0.5490080714225769,
      "learning_rate": 6.837175952121306e-06,
      "loss": 4.1744,
      "step": 168
    },
    {
      "epoch": 0.02739170955063009,
      "grad_norm": 0.5347091555595398,
      "learning_rate": 6.425787818636131e-06,
      "loss": 4.128,
      "step": 169
    },
    {
      "epoch": 0.027553790672231453,
      "grad_norm": 0.5489059686660767,
      "learning_rate": 6.026312439675552e-06,
      "loss": 4.0855,
      "step": 170
    },
    {
      "epoch": 0.027715871793832815,
      "grad_norm": 0.5701624751091003,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 4.1832,
      "step": 171
    },
    {
      "epoch": 0.027877952915434174,
      "grad_norm": 0.5340564846992493,
      "learning_rate": 5.263533508961827e-06,
      "loss": 3.8612,
      "step": 172
    },
    {
      "epoch": 0.028040034037035536,
      "grad_norm": 0.5689954161643982,
      "learning_rate": 4.900438493352055e-06,
      "loss": 4.2416,
      "step": 173
    },
    {
      "epoch": 0.0282021151586369,
      "grad_norm": 0.5659968256950378,
      "learning_rate": 4.549673247541875e-06,
      "loss": 4.0771,
      "step": 174
    },
    {
      "epoch": 0.02836419628023826,
      "grad_norm": 0.5875797867774963,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 4.0752,
      "step": 175
    },
    {
      "epoch": 0.02852627740183962,
      "grad_norm": 0.5654675960540771,
      "learning_rate": 3.885512251130763e-06,
      "loss": 4.0586,
      "step": 176
    },
    {
      "epoch": 0.028688358523440982,
      "grad_norm": 0.5972083210945129,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 4.0985,
      "step": 177
    },
    {
      "epoch": 0.028850439645042344,
      "grad_norm": 0.6124581098556519,
      "learning_rate": 3.271776770026963e-06,
      "loss": 4.1543,
      "step": 178
    },
    {
      "epoch": 0.029012520766643707,
      "grad_norm": 0.6020548343658447,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 4.1047,
      "step": 179
    },
    {
      "epoch": 0.029174601888245066,
      "grad_norm": 0.6259830594062805,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 4.3088,
      "step": 180
    },
    {
      "epoch": 0.029336683009846428,
      "grad_norm": 0.6594240665435791,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 4.3692,
      "step": 181
    },
    {
      "epoch": 0.02949876413144779,
      "grad_norm": 0.643122136592865,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 4.3304,
      "step": 182
    },
    {
      "epoch": 0.029660845253049153,
      "grad_norm": 0.6499927639961243,
      "learning_rate": 1.962316193157593e-06,
      "loss": 4.0114,
      "step": 183
    },
    {
      "epoch": 0.02982292637465051,
      "grad_norm": 0.6731805205345154,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 4.3205,
      "step": 184
    },
    {
      "epoch": 0.029985007496251874,
      "grad_norm": 0.6507833003997803,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 4.4322,
      "step": 185
    },
    {
      "epoch": 0.030147088617853236,
      "grad_norm": 0.6833333373069763,
      "learning_rate": 1.333670137599713e-06,
      "loss": 4.2044,
      "step": 186
    },
    {
      "epoch": 0.0303091697394546,
      "grad_norm": 0.7622047662734985,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 4.7197,
      "step": 187
    },
    {
      "epoch": 0.030471250861055958,
      "grad_norm": 0.7042948007583618,
      "learning_rate": 9.810017062595322e-07,
      "loss": 4.4021,
      "step": 188
    },
    {
      "epoch": 0.03063333198265732,
      "grad_norm": 0.7219006419181824,
      "learning_rate": 8.247462563808817e-07,
      "loss": 4.2489,
      "step": 189
    },
    {
      "epoch": 0.030795413104258682,
      "grad_norm": 0.7981518507003784,
      "learning_rate": 6.819348298638839e-07,
      "loss": 5.094,
      "step": 190
    },
    {
      "epoch": 0.030957494225860045,
      "grad_norm": 0.8223955035209656,
      "learning_rate": 5.526064699265753e-07,
      "loss": 4.8105,
      "step": 191
    },
    {
      "epoch": 0.031119575347461403,
      "grad_norm": 0.8462647795677185,
      "learning_rate": 4.367965336512403e-07,
      "loss": 4.7003,
      "step": 192
    },
    {
      "epoch": 0.031281656469062766,
      "grad_norm": 0.9850577116012573,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 4.9163,
      "step": 193
    },
    {
      "epoch": 0.03144373759066413,
      "grad_norm": 0.9707556962966919,
      "learning_rate": 2.458548727494292e-07,
      "loss": 5.2005,
      "step": 194
    },
    {
      "epoch": 0.03160581871226549,
      "grad_norm": 1.0337095260620117,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 4.8567,
      "step": 195
    },
    {
      "epoch": 0.03176789983386685,
      "grad_norm": 1.1223312616348267,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 4.8641,
      "step": 196
    },
    {
      "epoch": 0.031929980955468215,
      "grad_norm": 1.1983397006988525,
      "learning_rate": 6.150154258476315e-08,
      "loss": 4.9544,
      "step": 197
    },
    {
      "epoch": 0.03209206207706957,
      "grad_norm": 1.4124658107757568,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 5.1328,
      "step": 198
    },
    {
      "epoch": 0.03225414319867093,
      "grad_norm": 1.7166236639022827,
      "learning_rate": 6.834750376549792e-09,
      "loss": 5.0142,
      "step": 199
    },
    {
      "epoch": 0.032416224320272295,
      "grad_norm": 2.20459246635437,
      "learning_rate": 0.0,
      "loss": 4.7875,
      "step": 200
    },
    {
      "epoch": 0.032416224320272295,
      "eval_loss": 1.0687636137008667,
      "eval_runtime": 624.2339,
      "eval_samples_per_second": 16.648,
      "eval_steps_per_second": 4.162,
      "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": 1.816715023267922e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}