{
  "best_metric": 0.11256761848926544,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.3986013986013985,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006993006993006993,
      "grad_norm": 2.4450721740722656,
      "learning_rate": 1e-05,
      "loss": 1.0557,
      "step": 1
    },
    {
      "epoch": 0.006993006993006993,
      "eval_loss": 1.2505520582199097,
      "eval_runtime": 38.1928,
      "eval_samples_per_second": 6.31,
      "eval_steps_per_second": 1.597,
      "step": 1
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 2.790501832962036,
      "learning_rate": 2e-05,
      "loss": 1.1818,
      "step": 2
    },
    {
      "epoch": 0.02097902097902098,
      "grad_norm": 2.6383352279663086,
      "learning_rate": 3e-05,
      "loss": 1.0842,
      "step": 3
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 2.526608943939209,
      "learning_rate": 4e-05,
      "loss": 1.1868,
      "step": 4
    },
    {
      "epoch": 0.03496503496503497,
      "grad_norm": 2.4500818252563477,
      "learning_rate": 5e-05,
      "loss": 1.2812,
      "step": 5
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 2.384549856185913,
      "learning_rate": 6e-05,
      "loss": 1.261,
      "step": 6
    },
    {
      "epoch": 0.04895104895104895,
      "grad_norm": 2.039846897125244,
      "learning_rate": 7e-05,
      "loss": 1.1098,
      "step": 7
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 1.9305548667907715,
      "learning_rate": 8e-05,
      "loss": 1.1444,
      "step": 8
    },
    {
      "epoch": 0.06293706293706294,
      "grad_norm": 1.6787424087524414,
      "learning_rate": 9e-05,
      "loss": 1.0747,
      "step": 9
    },
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 1.5759395360946655,
      "learning_rate": 0.0001,
      "loss": 0.9809,
      "step": 10
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.568303108215332,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.016,
      "step": 11
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 1.4762561321258545,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8924,
      "step": 12
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.7786035537719727,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0509,
      "step": 13
    },
    {
      "epoch": 0.0979020979020979,
      "grad_norm": 1.5409046411514282,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.0747,
      "step": 14
    },
    {
      "epoch": 0.1048951048951049,
      "grad_norm": 1.8837014436721802,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0796,
      "step": 15
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 1.5557585954666138,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9906,
      "step": 16
    },
    {
      "epoch": 0.11888111888111888,
      "grad_norm": 1.611653447151184,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8306,
      "step": 17
    },
    {
      "epoch": 0.1258741258741259,
      "grad_norm": 1.5436105728149414,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8,
      "step": 18
    },
    {
      "epoch": 0.13286713286713286,
      "grad_norm": 1.5179784297943115,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9461,
      "step": 19
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 1.5441638231277466,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8452,
      "step": 20
    },
    {
      "epoch": 0.14685314685314685,
      "grad_norm": 1.486792802810669,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9058,
      "step": 21
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 2.221353769302368,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0114,
      "step": 22
    },
    {
      "epoch": 0.16083916083916083,
      "grad_norm": 1.4807649850845337,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.772,
      "step": 23
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 1.706774353981018,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9292,
      "step": 24
    },
    {
      "epoch": 0.17482517482517482,
      "grad_norm": 1.4606592655181885,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8584,
      "step": 25
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.413172721862793,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8386,
      "step": 26
    },
    {
      "epoch": 0.1888111888111888,
      "grad_norm": 1.6635881662368774,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9414,
      "step": 27
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 1.5321897268295288,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8953,
      "step": 28
    },
    {
      "epoch": 0.20279720279720279,
      "grad_norm": 1.4051462411880493,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8023,
      "step": 29
    },
    {
      "epoch": 0.2097902097902098,
      "grad_norm": 1.4940423965454102,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6277,
      "step": 30
    },
    {
      "epoch": 0.21678321678321677,
      "grad_norm": 1.606011986732483,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7768,
      "step": 31
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 1.5925713777542114,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7869,
      "step": 32
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 1.4228204488754272,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.632,
      "step": 33
    },
    {
      "epoch": 0.23776223776223776,
      "grad_norm": 1.6678287982940674,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6638,
      "step": 34
    },
    {
      "epoch": 0.24475524475524477,
      "grad_norm": 1.908482313156128,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5813,
      "step": 35
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 1.5889215469360352,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8351,
      "step": 36
    },
    {
      "epoch": 0.25874125874125875,
      "grad_norm": 1.2572404146194458,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8073,
      "step": 37
    },
    {
      "epoch": 0.26573426573426573,
      "grad_norm": 1.1582667827606201,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6831,
      "step": 38
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.286945104598999,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7785,
      "step": 39
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 1.1870123147964478,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7402,
      "step": 40
    },
    {
      "epoch": 0.2867132867132867,
      "grad_norm": 1.2967826128005981,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.794,
      "step": 41
    },
    {
      "epoch": 0.2937062937062937,
      "grad_norm": 1.2907445430755615,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.817,
      "step": 42
    },
    {
      "epoch": 0.3006993006993007,
      "grad_norm": 1.3614184856414795,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7418,
      "step": 43
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.3672399520874023,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6303,
      "step": 44
    },
    {
      "epoch": 0.3146853146853147,
      "grad_norm": 1.1191858053207397,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6083,
      "step": 45
    },
    {
      "epoch": 0.32167832167832167,
      "grad_norm": 1.3804144859313965,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7408,
      "step": 46
    },
    {
      "epoch": 0.32867132867132864,
      "grad_norm": 1.3644160032272339,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7545,
      "step": 47
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 1.179352045059204,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7074,
      "step": 48
    },
    {
      "epoch": 0.34265734265734266,
      "grad_norm": 1.4680413007736206,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.685,
      "step": 49
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 1.2795792818069458,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5851,
      "step": 50
    },
    {
      "epoch": 0.34965034965034963,
      "eval_loss": 0.5820824503898621,
      "eval_runtime": 38.949,
      "eval_samples_per_second": 6.188,
      "eval_steps_per_second": 1.566,
      "step": 50
    },
    {
      "epoch": 0.35664335664335667,
      "grad_norm": 1.3142274618148804,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7223,
      "step": 51
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.0938032865524292,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.587,
      "step": 52
    },
    {
      "epoch": 0.3706293706293706,
      "grad_norm": 1.3187650442123413,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7011,
      "step": 53
    },
    {
      "epoch": 0.3776223776223776,
      "grad_norm": 1.0964183807373047,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6155,
      "step": 54
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.2609574794769287,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5969,
      "step": 55
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 1.2467068433761597,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5787,
      "step": 56
    },
    {
      "epoch": 0.3986013986013986,
      "grad_norm": 1.4265246391296387,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6597,
      "step": 57
    },
    {
      "epoch": 0.40559440559440557,
      "grad_norm": 1.4541116952896118,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6255,
      "step": 58
    },
    {
      "epoch": 0.4125874125874126,
      "grad_norm": 1.3444572687149048,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5837,
      "step": 59
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 1.2142887115478516,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5114,
      "step": 60
    },
    {
      "epoch": 0.42657342657342656,
      "grad_norm": 1.4293973445892334,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6031,
      "step": 61
    },
    {
      "epoch": 0.43356643356643354,
      "grad_norm": 1.5404058694839478,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5718,
      "step": 62
    },
    {
      "epoch": 0.4405594405594406,
      "grad_norm": 1.392652153968811,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.503,
      "step": 63
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 1.7504690885543823,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5305,
      "step": 64
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.0840989351272583,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3149,
      "step": 65
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 1.6667064428329468,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5053,
      "step": 66
    },
    {
      "epoch": 0.46853146853146854,
      "grad_norm": 1.2787916660308838,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4226,
      "step": 67
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 1.9564926624298096,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5534,
      "step": 68
    },
    {
      "epoch": 0.4825174825174825,
      "grad_norm": 1.4535070657730103,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3568,
      "step": 69
    },
    {
      "epoch": 0.48951048951048953,
      "grad_norm": 2.071007490158081,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3668,
      "step": 70
    },
    {
      "epoch": 0.4965034965034965,
      "grad_norm": 1.2199947834014893,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6202,
      "step": 71
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 1.1931997537612915,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5707,
      "step": 72
    },
    {
      "epoch": 0.5104895104895105,
      "grad_norm": 1.364689826965332,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.532,
      "step": 73
    },
    {
      "epoch": 0.5174825174825175,
      "grad_norm": 1.1490163803100586,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4902,
      "step": 74
    },
    {
      "epoch": 0.5244755244755245,
      "grad_norm": 1.2804994583129883,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6154,
      "step": 75
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 1.2607134580612183,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5263,
      "step": 76
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 1.4895960092544556,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6092,
      "step": 77
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.0777106285095215,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4386,
      "step": 78
    },
    {
      "epoch": 0.5524475524475524,
      "grad_norm": 1.3500018119812012,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3931,
      "step": 79
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 1.1880335807800293,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5051,
      "step": 80
    },
    {
      "epoch": 0.5664335664335665,
      "grad_norm": 1.3600882291793823,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4967,
      "step": 81
    },
    {
      "epoch": 0.5734265734265734,
      "grad_norm": 1.3902755975723267,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4757,
      "step": 82
    },
    {
      "epoch": 0.5804195804195804,
      "grad_norm": 1.3870673179626465,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4349,
      "step": 83
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 1.2921574115753174,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3726,
      "step": 84
    },
    {
      "epoch": 0.5944055944055944,
      "grad_norm": 1.2701841592788696,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3558,
      "step": 85
    },
    {
      "epoch": 0.6013986013986014,
      "grad_norm": 1.6290758848190308,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4596,
      "step": 86
    },
    {
      "epoch": 0.6083916083916084,
      "grad_norm": 1.2988293170928955,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.4448,
      "step": 87
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2133945226669312,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3929,
      "step": 88
    },
    {
      "epoch": 0.6223776223776224,
      "grad_norm": 1.153152346611023,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3666,
      "step": 89
    },
    {
      "epoch": 0.6293706293706294,
      "grad_norm": 1.4179494380950928,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3923,
      "step": 90
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.7598042488098145,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5465,
      "step": 91
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 1.4074292182922363,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3956,
      "step": 92
    },
    {
      "epoch": 0.6503496503496503,
      "grad_norm": 1.5160378217697144,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3628,
      "step": 93
    },
    {
      "epoch": 0.6573426573426573,
      "grad_norm": 1.414318561553955,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3208,
      "step": 94
    },
    {
      "epoch": 0.6643356643356644,
      "grad_norm": 1.5458487272262573,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4029,
      "step": 95
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 1.5665245056152344,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3595,
      "step": 96
    },
    {
      "epoch": 0.6783216783216783,
      "grad_norm": 1.7124160528182983,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3811,
      "step": 97
    },
    {
      "epoch": 0.6853146853146853,
      "grad_norm": 1.2954429388046265,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2587,
      "step": 98
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 1.5806289911270142,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3238,
      "step": 99
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 1.3570256233215332,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2318,
      "step": 100
    },
    {
      "epoch": 0.6993006993006993,
      "eval_loss": 0.3027082085609436,
      "eval_runtime": 38.9643,
      "eval_samples_per_second": 6.185,
      "eval_steps_per_second": 1.566,
      "step": 100
    },
    {
      "epoch": 0.7062937062937062,
      "grad_norm": 1.42549729347229,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2856,
      "step": 101
    },
    {
      "epoch": 0.7132867132867133,
      "grad_norm": 1.640339970588684,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2475,
      "step": 102
    },
    {
      "epoch": 0.7202797202797203,
      "grad_norm": 1.113348364830017,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.1614,
      "step": 103
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.3114198446273804,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1492,
      "step": 104
    },
    {
      "epoch": 0.7342657342657343,
      "grad_norm": 1.5878783464431763,
      "learning_rate": 5e-05,
      "loss": 0.1694,
      "step": 105
    },
    {
      "epoch": 0.7412587412587412,
      "grad_norm": 1.2930468320846558,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4157,
      "step": 106
    },
    {
      "epoch": 0.7482517482517482,
      "grad_norm": 1.6409896612167358,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.489,
      "step": 107
    },
    {
      "epoch": 0.7552447552447552,
      "grad_norm": 1.267659068107605,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3622,
      "step": 108
    },
    {
      "epoch": 0.7622377622377622,
      "grad_norm": 1.1827614307403564,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3118,
      "step": 109
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.281274676322937,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3804,
      "step": 110
    },
    {
      "epoch": 0.7762237762237763,
      "grad_norm": 1.2029186487197876,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3833,
      "step": 111
    },
    {
      "epoch": 0.7832167832167832,
      "grad_norm": 1.048230767250061,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3507,
      "step": 112
    },
    {
      "epoch": 0.7902097902097902,
      "grad_norm": 1.5066605806350708,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4854,
      "step": 113
    },
    {
      "epoch": 0.7972027972027972,
      "grad_norm": 1.5561763048171997,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.3928,
      "step": 114
    },
    {
      "epoch": 0.8041958041958042,
      "grad_norm": 0.9923309087753296,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2804,
      "step": 115
    },
    {
      "epoch": 0.8111888111888111,
      "grad_norm": 1.3982666730880737,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3017,
      "step": 116
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.958275556564331,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4333,
      "step": 117
    },
    {
      "epoch": 0.8251748251748252,
      "grad_norm": 1.2285205125808716,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.2469,
      "step": 118
    },
    {
      "epoch": 0.8321678321678322,
      "grad_norm": 1.149312138557434,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.245,
      "step": 119
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 1.2875862121582031,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2705,
      "step": 120
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.3865101337432861,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2639,
      "step": 121
    },
    {
      "epoch": 0.8531468531468531,
      "grad_norm": 1.2344775199890137,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.208,
      "step": 122
    },
    {
      "epoch": 0.8601398601398601,
      "grad_norm": 1.248934268951416,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.202,
      "step": 123
    },
    {
      "epoch": 0.8671328671328671,
      "grad_norm": 2.433309316635132,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3051,
      "step": 124
    },
    {
      "epoch": 0.8741258741258742,
      "grad_norm": 2.0636985301971436,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2826,
      "step": 125
    },
    {
      "epoch": 0.8811188811188811,
      "grad_norm": 2.1663825511932373,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.334,
      "step": 126
    },
    {
      "epoch": 0.8881118881118881,
      "grad_norm": 1.739748239517212,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2098,
      "step": 127
    },
    {
      "epoch": 0.8951048951048951,
      "grad_norm": 1.2999457120895386,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1715,
      "step": 128
    },
    {
      "epoch": 0.9020979020979021,
      "grad_norm": 2.2448084354400635,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.333,
      "step": 129
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.0075722932815552,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1686,
      "step": 130
    },
    {
      "epoch": 0.916083916083916,
      "grad_norm": 1.3515135049819946,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2231,
      "step": 131
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 1.40211021900177,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1831,
      "step": 132
    },
    {
      "epoch": 0.9300699300699301,
      "grad_norm": 1.3439240455627441,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1374,
      "step": 133
    },
    {
      "epoch": 0.9370629370629371,
      "grad_norm": 1.0980956554412842,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.1317,
      "step": 134
    },
    {
      "epoch": 0.9440559440559441,
      "grad_norm": 1.2026312351226807,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1448,
      "step": 135
    },
    {
      "epoch": 0.951048951048951,
      "grad_norm": 1.1151537895202637,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1298,
      "step": 136
    },
    {
      "epoch": 0.958041958041958,
      "grad_norm": 1.1032382249832153,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0883,
      "step": 137
    },
    {
      "epoch": 0.965034965034965,
      "grad_norm": 0.8003612160682678,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0696,
      "step": 138
    },
    {
      "epoch": 0.972027972027972,
      "grad_norm": 1.1572051048278809,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0838,
      "step": 139
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 3.915778160095215,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.261,
      "step": 140
    },
    {
      "epoch": 0.986013986013986,
      "grad_norm": 1.014407992362976,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.265,
      "step": 141
    },
    {
      "epoch": 0.993006993006993,
      "grad_norm": 1.044299602508545,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.167,
      "step": 142
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8381390571594238,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1049,
      "step": 143
    },
    {
      "epoch": 1.006993006993007,
      "grad_norm": 1.0972381830215454,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2547,
      "step": 144
    },
    {
      "epoch": 1.013986013986014,
      "grad_norm": 1.1938369274139404,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2103,
      "step": 145
    },
    {
      "epoch": 1.020979020979021,
      "grad_norm": 0.928747832775116,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1521,
      "step": 146
    },
    {
      "epoch": 1.027972027972028,
      "grad_norm": 1.03361177444458,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.14,
      "step": 147
    },
    {
      "epoch": 1.034965034965035,
      "grad_norm": 1.1349563598632812,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1717,
      "step": 148
    },
    {
      "epoch": 1.0419580419580419,
      "grad_norm": 1.0472331047058105,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1569,
      "step": 149
    },
    {
      "epoch": 1.048951048951049,
      "grad_norm": 1.2580304145812988,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1743,
      "step": 150
    },
    {
      "epoch": 1.048951048951049,
      "eval_loss": 0.14278081059455872,
      "eval_runtime": 38.9542,
      "eval_samples_per_second": 6.187,
      "eval_steps_per_second": 1.566,
      "step": 150
    },
    {
      "epoch": 1.055944055944056,
      "grad_norm": 1.1998547315597534,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1618,
      "step": 151
    },
    {
      "epoch": 1.062937062937063,
      "grad_norm": 1.0802581310272217,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.12,
      "step": 152
    },
    {
      "epoch": 1.06993006993007,
      "grad_norm": 1.015791654586792,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1058,
      "step": 153
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.0316447019577026,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1163,
      "step": 154
    },
    {
      "epoch": 1.083916083916084,
      "grad_norm": 0.9844825863838196,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1201,
      "step": 155
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.009963035583496,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0993,
      "step": 156
    },
    {
      "epoch": 1.097902097902098,
      "grad_norm": 0.778262197971344,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0826,
      "step": 157
    },
    {
      "epoch": 1.104895104895105,
      "grad_norm": 0.777290940284729,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0857,
      "step": 158
    },
    {
      "epoch": 1.1118881118881119,
      "grad_norm": 1.045178771018982,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1038,
      "step": 159
    },
    {
      "epoch": 1.118881118881119,
      "grad_norm": 0.8928464651107788,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0874,
      "step": 160
    },
    {
      "epoch": 1.1258741258741258,
      "grad_norm": 0.8857114315032959,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0773,
      "step": 161
    },
    {
      "epoch": 1.132867132867133,
      "grad_norm": 0.7998533248901367,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0725,
      "step": 162
    },
    {
      "epoch": 1.1398601398601398,
      "grad_norm": 0.848217248916626,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0745,
      "step": 163
    },
    {
      "epoch": 1.1468531468531469,
      "grad_norm": 0.9138949513435364,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0684,
      "step": 164
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.9241153001785278,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0976,
      "step": 165
    },
    {
      "epoch": 1.1608391608391608,
      "grad_norm": 0.7542672157287598,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0479,
      "step": 166
    },
    {
      "epoch": 1.167832167832168,
      "grad_norm": 1.1764851808547974,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0904,
      "step": 167
    },
    {
      "epoch": 1.1748251748251748,
      "grad_norm": 0.629348635673523,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0521,
      "step": 168
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.6395772099494934,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0538,
      "step": 169
    },
    {
      "epoch": 1.1888111888111887,
      "grad_norm": 0.6519189476966858,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0466,
      "step": 170
    },
    {
      "epoch": 1.1958041958041958,
      "grad_norm": 0.538361132144928,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0298,
      "step": 171
    },
    {
      "epoch": 1.2027972027972027,
      "grad_norm": 0.6215816736221313,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0358,
      "step": 172
    },
    {
      "epoch": 1.2097902097902098,
      "grad_norm": 0.46716615557670593,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.024,
      "step": 173
    },
    {
      "epoch": 1.2167832167832167,
      "grad_norm": 0.5309239029884338,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0291,
      "step": 174
    },
    {
      "epoch": 1.2237762237762237,
      "grad_norm": 0.5153325796127319,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0278,
      "step": 175
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4547761380672455,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0181,
      "step": 176
    },
    {
      "epoch": 1.2377622377622377,
      "grad_norm": 0.5819584131240845,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0233,
      "step": 177
    },
    {
      "epoch": 1.2447552447552448,
      "grad_norm": 0.7680311799049377,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0375,
      "step": 178
    },
    {
      "epoch": 1.2517482517482517,
      "grad_norm": 1.0343384742736816,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.1615,
      "step": 179
    },
    {
      "epoch": 1.2587412587412588,
      "grad_norm": 1.0792516469955444,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1559,
      "step": 180
    },
    {
      "epoch": 1.2657342657342658,
      "grad_norm": 1.0544278621673584,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.104,
      "step": 181
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.081142544746399,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1125,
      "step": 182
    },
    {
      "epoch": 1.2797202797202798,
      "grad_norm": 1.1026910543441772,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.1071,
      "step": 183
    },
    {
      "epoch": 1.2867132867132867,
      "grad_norm": 0.9672271609306335,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.1231,
      "step": 184
    },
    {
      "epoch": 1.2937062937062938,
      "grad_norm": 1.0266520977020264,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.11,
      "step": 185
    },
    {
      "epoch": 1.3006993006993006,
      "grad_norm": 0.8104790449142456,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0741,
      "step": 186
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.7459039688110352,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0626,
      "step": 187
    },
    {
      "epoch": 1.3146853146853146,
      "grad_norm": 0.9654370546340942,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0897,
      "step": 188
    },
    {
      "epoch": 1.3216783216783217,
      "grad_norm": 1.0074461698532104,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.103,
      "step": 189
    },
    {
      "epoch": 1.3286713286713288,
      "grad_norm": 0.705643892288208,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.048,
      "step": 190
    },
    {
      "epoch": 1.3356643356643356,
      "grad_norm": 0.6816481351852417,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0555,
      "step": 191
    },
    {
      "epoch": 1.3426573426573427,
      "grad_norm": 0.7838186621665955,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0555,
      "step": 192
    },
    {
      "epoch": 1.3496503496503496,
      "grad_norm": 0.9687144160270691,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0725,
      "step": 193
    },
    {
      "epoch": 1.3566433566433567,
      "grad_norm": 0.8559790253639221,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0586,
      "step": 194
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.6095675826072693,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0423,
      "step": 195
    },
    {
      "epoch": 1.3706293706293706,
      "grad_norm": 0.6279594898223877,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0487,
      "step": 196
    },
    {
      "epoch": 1.3776223776223775,
      "grad_norm": 0.5631357431411743,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0452,
      "step": 197
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.8297536969184875,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0728,
      "step": 198
    },
    {
      "epoch": 1.3916083916083917,
      "grad_norm": 1.10988450050354,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0676,
      "step": 199
    },
    {
      "epoch": 1.3986013986013985,
      "grad_norm": 0.8506512641906738,
      "learning_rate": 0.0,
      "loss": 0.0564,
      "step": 200
    },
    {
      "epoch": 1.3986013986013985,
      "eval_loss": 0.11256761848926544,
      "eval_runtime": 38.9807,
      "eval_samples_per_second": 6.183,
      "eval_steps_per_second": 1.565,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.862855422037197e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}