{
  "best_metric": 1.9997398853302002,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03611412062116288,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018057060310581438,
      "grad_norm": 0.6624407768249512,
      "learning_rate": 1e-05,
      "loss": 2.5655,
      "step": 1
    },
    {
      "epoch": 0.00018057060310581438,
      "eval_loss": 2.7124359607696533,
      "eval_runtime": 685.9613,
      "eval_samples_per_second": 13.597,
      "eval_steps_per_second": 3.4,
      "step": 1
    },
    {
      "epoch": 0.00036114120621162876,
      "grad_norm": 0.7581428289413452,
      "learning_rate": 2e-05,
      "loss": 2.5189,
      "step": 2
    },
    {
      "epoch": 0.0005417118093174431,
      "grad_norm": 0.724696695804596,
      "learning_rate": 3e-05,
      "loss": 2.485,
      "step": 3
    },
    {
      "epoch": 0.0007222824124232575,
      "grad_norm": 0.8178666234016418,
      "learning_rate": 4e-05,
      "loss": 2.4495,
      "step": 4
    },
    {
      "epoch": 0.0009028530155290719,
      "grad_norm": 0.7225940823554993,
      "learning_rate": 5e-05,
      "loss": 2.5998,
      "step": 5
    },
    {
      "epoch": 0.0010834236186348862,
      "grad_norm": 0.6008687615394592,
      "learning_rate": 6e-05,
      "loss": 2.5265,
      "step": 6
    },
    {
      "epoch": 0.0012639942217407005,
      "grad_norm": 0.6511266827583313,
      "learning_rate": 7e-05,
      "loss": 2.4456,
      "step": 7
    },
    {
      "epoch": 0.001444564824846515,
      "grad_norm": 0.5716150999069214,
      "learning_rate": 8e-05,
      "loss": 2.2869,
      "step": 8
    },
    {
      "epoch": 0.0016251354279523294,
      "grad_norm": 0.6196761131286621,
      "learning_rate": 9e-05,
      "loss": 2.4605,
      "step": 9
    },
    {
      "epoch": 0.0018057060310581437,
      "grad_norm": 0.8213319182395935,
      "learning_rate": 0.0001,
      "loss": 2.3148,
      "step": 10
    },
    {
      "epoch": 0.0019862766341639583,
      "grad_norm": 0.6406309604644775,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.2636,
      "step": 11
    },
    {
      "epoch": 0.0021668472372697724,
      "grad_norm": 0.5477151870727539,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.1784,
      "step": 12
    },
    {
      "epoch": 0.002347417840375587,
      "grad_norm": 0.5454879403114319,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.2564,
      "step": 13
    },
    {
      "epoch": 0.002527988443481401,
      "grad_norm": 0.44204509258270264,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.1552,
      "step": 14
    },
    {
      "epoch": 0.0027085590465872156,
      "grad_norm": 0.43791064620018005,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.105,
      "step": 15
    },
    {
      "epoch": 0.00288912964969303,
      "grad_norm": 0.43272435665130615,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1747,
      "step": 16
    },
    {
      "epoch": 0.0030697002527988442,
      "grad_norm": 0.41262441873550415,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.2292,
      "step": 17
    },
    {
      "epoch": 0.0032502708559046588,
      "grad_norm": 0.4293859302997589,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1232,
      "step": 18
    },
    {
      "epoch": 0.0034308414590104733,
      "grad_norm": 0.460185706615448,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.0791,
      "step": 19
    },
    {
      "epoch": 0.0036114120621162874,
      "grad_norm": 0.4025264382362366,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.0914,
      "step": 20
    },
    {
      "epoch": 0.003791982665222102,
      "grad_norm": 0.43764618039131165,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.168,
      "step": 21
    },
    {
      "epoch": 0.0039725532683279165,
      "grad_norm": 0.474251389503479,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.1354,
      "step": 22
    },
    {
      "epoch": 0.004153123871433731,
      "grad_norm": 0.4564894437789917,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.1433,
      "step": 23
    },
    {
      "epoch": 0.004333694474539545,
      "grad_norm": 0.4421786665916443,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.2349,
      "step": 24
    },
    {
      "epoch": 0.00451426507764536,
      "grad_norm": 0.4256881773471832,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.1171,
      "step": 25
    },
    {
      "epoch": 0.004694835680751174,
      "grad_norm": 0.41441676020622253,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.0831,
      "step": 26
    },
    {
      "epoch": 0.004875406283856988,
      "grad_norm": 0.4659394919872284,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.0631,
      "step": 27
    },
    {
      "epoch": 0.005055976886962802,
      "grad_norm": 0.46133676171302795,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.1254,
      "step": 28
    },
    {
      "epoch": 0.005236547490068617,
      "grad_norm": 0.4646921753883362,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1308,
      "step": 29
    },
    {
      "epoch": 0.005417118093174431,
      "grad_norm": 0.4502306878566742,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0584,
      "step": 30
    },
    {
      "epoch": 0.005597688696280245,
      "grad_norm": 0.5119293928146362,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.0493,
      "step": 31
    },
    {
      "epoch": 0.00577825929938606,
      "grad_norm": 0.5046262741088867,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.1177,
      "step": 32
    },
    {
      "epoch": 0.005958829902491874,
      "grad_norm": 0.4912949204444885,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.1225,
      "step": 33
    },
    {
      "epoch": 0.0061394005055976884,
      "grad_norm": 0.5434021353721619,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.1468,
      "step": 34
    },
    {
      "epoch": 0.006319971108703503,
      "grad_norm": 0.480820894241333,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.999,
      "step": 35
    },
    {
      "epoch": 0.0065005417118093175,
      "grad_norm": 0.49585434794425964,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.978,
      "step": 36
    },
    {
      "epoch": 0.006681112314915132,
      "grad_norm": 0.5492971539497375,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1228,
      "step": 37
    },
    {
      "epoch": 0.006861682918020947,
      "grad_norm": 0.511803925037384,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.1231,
      "step": 38
    },
    {
      "epoch": 0.007042253521126761,
      "grad_norm": 0.5920349359512329,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.101,
      "step": 39
    },
    {
      "epoch": 0.007222824124232575,
      "grad_norm": 0.5832512974739075,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.0776,
      "step": 40
    },
    {
      "epoch": 0.007403394727338389,
      "grad_norm": 0.6450849175453186,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.1303,
      "step": 41
    },
    {
      "epoch": 0.007583965330444204,
      "grad_norm": 0.6384161114692688,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.1216,
      "step": 42
    },
    {
      "epoch": 0.007764535933550018,
      "grad_norm": 0.5975738763809204,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.0778,
      "step": 43
    },
    {
      "epoch": 0.007945106536655833,
      "grad_norm": 0.6410922408103943,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.2383,
      "step": 44
    },
    {
      "epoch": 0.008125677139761646,
      "grad_norm": 0.6352540850639343,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.161,
      "step": 45
    },
    {
      "epoch": 0.008306247742867461,
      "grad_norm": 0.644791841506958,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.2545,
      "step": 46
    },
    {
      "epoch": 0.008486818345973276,
      "grad_norm": 0.7133358120918274,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.2299,
      "step": 47
    },
    {
      "epoch": 0.00866738894907909,
      "grad_norm": 0.7115877270698547,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4298,
      "step": 48
    },
    {
      "epoch": 0.008847959552184904,
      "grad_norm": 0.841839075088501,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.3537,
      "step": 49
    },
    {
      "epoch": 0.00902853015529072,
      "grad_norm": 0.7993963956832886,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.5511,
      "step": 50
    },
    {
      "epoch": 0.00902853015529072,
      "eval_loss": 2.129507541656494,
      "eval_runtime": 689.754,
      "eval_samples_per_second": 13.522,
      "eval_steps_per_second": 3.381,
      "step": 50
    },
    {
      "epoch": 0.009209100758396533,
      "grad_norm": 0.42209938168525696,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.0888,
      "step": 51
    },
    {
      "epoch": 0.009389671361502348,
      "grad_norm": 0.46093735098838806,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.054,
      "step": 52
    },
    {
      "epoch": 0.009570241964608163,
      "grad_norm": 0.43566620349884033,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.0435,
      "step": 53
    },
    {
      "epoch": 0.009750812567713976,
      "grad_norm": 0.3839430809020996,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.1214,
      "step": 54
    },
    {
      "epoch": 0.00993138317081979,
      "grad_norm": 0.38588741421699524,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.9208,
      "step": 55
    },
    {
      "epoch": 0.010111953773925604,
      "grad_norm": 0.307731956243515,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.9611,
      "step": 56
    },
    {
      "epoch": 0.010292524377031419,
      "grad_norm": 0.31476905941963196,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.1076,
      "step": 57
    },
    {
      "epoch": 0.010473094980137234,
      "grad_norm": 0.36871978640556335,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.0672,
      "step": 58
    },
    {
      "epoch": 0.010653665583243047,
      "grad_norm": 0.40399834513664246,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.0905,
      "step": 59
    },
    {
      "epoch": 0.010834236186348862,
      "grad_norm": 0.6111615896224976,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.896,
      "step": 60
    },
    {
      "epoch": 0.011014806789454677,
      "grad_norm": 0.37530985474586487,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.1393,
      "step": 61
    },
    {
      "epoch": 0.01119537739256049,
      "grad_norm": 0.41041845083236694,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.1757,
      "step": 62
    },
    {
      "epoch": 0.011375947995666305,
      "grad_norm": 0.3588217496871948,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.9678,
      "step": 63
    },
    {
      "epoch": 0.01155651859877212,
      "grad_norm": 0.3710726499557495,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.0829,
      "step": 64
    },
    {
      "epoch": 0.011737089201877934,
      "grad_norm": 0.3658828139305115,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.9924,
      "step": 65
    },
    {
      "epoch": 0.011917659804983749,
      "grad_norm": 0.3595665395259857,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.0748,
      "step": 66
    },
    {
      "epoch": 0.012098230408089564,
      "grad_norm": 0.3625120222568512,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0614,
      "step": 67
    },
    {
      "epoch": 0.012278801011195377,
      "grad_norm": 0.3999013900756836,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9798,
      "step": 68
    },
    {
      "epoch": 0.012459371614301192,
      "grad_norm": 0.4314456582069397,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.1344,
      "step": 69
    },
    {
      "epoch": 0.012639942217407007,
      "grad_norm": 0.4366953372955322,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.9307,
      "step": 70
    },
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 0.3855569362640381,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.0309,
      "step": 71
    },
    {
      "epoch": 0.013001083423618635,
      "grad_norm": 0.409615159034729,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.0181,
      "step": 72
    },
    {
      "epoch": 0.01318165402672445,
      "grad_norm": 0.41800588369369507,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.9527,
      "step": 73
    },
    {
      "epoch": 0.013362224629830263,
      "grad_norm": 0.4262048602104187,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.1873,
      "step": 74
    },
    {
      "epoch": 0.013542795232936078,
      "grad_norm": 0.4645998179912567,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.2557,
      "step": 75
    },
    {
      "epoch": 0.013723365836041893,
      "grad_norm": 0.3942699432373047,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.9468,
      "step": 76
    },
    {
      "epoch": 0.013903936439147706,
      "grad_norm": 0.4233456254005432,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.2922,
      "step": 77
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 0.4349347949028015,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.0787,
      "step": 78
    },
    {
      "epoch": 0.014265077645359335,
      "grad_norm": 0.40108171105384827,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.7189,
      "step": 79
    },
    {
      "epoch": 0.01444564824846515,
      "grad_norm": 0.42598074674606323,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.9847,
      "step": 80
    },
    {
      "epoch": 0.014626218851570965,
      "grad_norm": 0.4288007915019989,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.9231,
      "step": 81
    },
    {
      "epoch": 0.014806789454676778,
      "grad_norm": 0.4508149325847626,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.9797,
      "step": 82
    },
    {
      "epoch": 0.014987360057782593,
      "grad_norm": 0.442592978477478,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.0614,
      "step": 83
    },
    {
      "epoch": 0.015167930660888408,
      "grad_norm": 0.4825979173183441,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.9582,
      "step": 84
    },
    {
      "epoch": 0.015348501263994221,
      "grad_norm": 0.5308371782302856,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.0677,
      "step": 85
    },
    {
      "epoch": 0.015529071867100036,
      "grad_norm": 0.46342289447784424,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9101,
      "step": 86
    },
    {
      "epoch": 0.01570964247020585,
      "grad_norm": 0.48983103036880493,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.8399,
      "step": 87
    },
    {
      "epoch": 0.015890213073311666,
      "grad_norm": 0.5859423279762268,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.1832,
      "step": 88
    },
    {
      "epoch": 0.01607078367641748,
      "grad_norm": 0.5067974925041199,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.9312,
      "step": 89
    },
    {
      "epoch": 0.016251354279523293,
      "grad_norm": 0.5896835327148438,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.1292,
      "step": 90
    },
    {
      "epoch": 0.01643192488262911,
      "grad_norm": 0.5307599902153015,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.8862,
      "step": 91
    },
    {
      "epoch": 0.016612495485734922,
      "grad_norm": 0.5295412540435791,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.0057,
      "step": 92
    },
    {
      "epoch": 0.016793066088840736,
      "grad_norm": 0.5694815516471863,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.9578,
      "step": 93
    },
    {
      "epoch": 0.016973636691946552,
      "grad_norm": 0.6204591393470764,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.0074,
      "step": 94
    },
    {
      "epoch": 0.017154207295052366,
      "grad_norm": 0.6003352999687195,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.072,
      "step": 95
    },
    {
      "epoch": 0.01733477789815818,
      "grad_norm": 0.6216194033622742,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.052,
      "step": 96
    },
    {
      "epoch": 0.017515348501263996,
      "grad_norm": 0.6048287749290466,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.1365,
      "step": 97
    },
    {
      "epoch": 0.01769591910436981,
      "grad_norm": 0.666451632976532,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.3475,
      "step": 98
    },
    {
      "epoch": 0.017876489707475622,
      "grad_norm": 0.7967808842658997,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.282,
      "step": 99
    },
    {
      "epoch": 0.01805706031058144,
      "grad_norm": 1.0120813846588135,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.5553,
      "step": 100
    },
    {
      "epoch": 0.01805706031058144,
      "eval_loss": 2.059274911880493,
      "eval_runtime": 689.9216,
      "eval_samples_per_second": 13.519,
      "eval_steps_per_second": 3.38,
      "step": 100
    },
    {
      "epoch": 0.018237630913687252,
      "grad_norm": 0.3895765542984009,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.2459,
      "step": 101
    },
    {
      "epoch": 0.018418201516793065,
      "grad_norm": 0.4267996549606323,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.9942,
      "step": 102
    },
    {
      "epoch": 0.018598772119898882,
      "grad_norm": 0.39692366123199463,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.1023,
      "step": 103
    },
    {
      "epoch": 0.018779342723004695,
      "grad_norm": 0.373115599155426,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.9709,
      "step": 104
    },
    {
      "epoch": 0.01895991332611051,
      "grad_norm": 0.38031432032585144,
      "learning_rate": 5e-05,
      "loss": 2.0388,
      "step": 105
    },
    {
      "epoch": 0.019140483929216325,
      "grad_norm": 0.4079199433326721,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.2443,
      "step": 106
    },
    {
      "epoch": 0.01932105453232214,
      "grad_norm": 0.34905269742012024,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.0283,
      "step": 107
    },
    {
      "epoch": 0.01950162513542795,
      "grad_norm": 0.4155385196208954,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.0262,
      "step": 108
    },
    {
      "epoch": 0.01968219573853377,
      "grad_norm": 0.43362778425216675,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.9427,
      "step": 109
    },
    {
      "epoch": 0.01986276634163958,
      "grad_norm": 0.37069815397262573,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.9019,
      "step": 110
    },
    {
      "epoch": 0.020043336944745395,
      "grad_norm": 0.3514178693294525,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.8921,
      "step": 111
    },
    {
      "epoch": 0.020223907547851208,
      "grad_norm": 0.3448438048362732,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.9658,
      "step": 112
    },
    {
      "epoch": 0.020404478150957025,
      "grad_norm": 0.373558908700943,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.0503,
      "step": 113
    },
    {
      "epoch": 0.020585048754062838,
      "grad_norm": 0.3926731050014496,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.9073,
      "step": 114
    },
    {
      "epoch": 0.02076561935716865,
      "grad_norm": 0.40110158920288086,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.0409,
      "step": 115
    },
    {
      "epoch": 0.020946189960274468,
      "grad_norm": 0.37772661447525024,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.9971,
      "step": 116
    },
    {
      "epoch": 0.02112676056338028,
      "grad_norm": 0.40943604707717896,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.878,
      "step": 117
    },
    {
      "epoch": 0.021307331166486095,
      "grad_norm": 0.4381054937839508,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.0748,
      "step": 118
    },
    {
      "epoch": 0.02148790176959191,
      "grad_norm": 0.4295724034309387,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.1721,
      "step": 119
    },
    {
      "epoch": 0.021668472372697724,
      "grad_norm": 0.4464626908302307,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.0626,
      "step": 120
    },
    {
      "epoch": 0.021849042975803538,
      "grad_norm": 0.43986180424690247,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.9922,
      "step": 121
    },
    {
      "epoch": 0.022029613578909354,
      "grad_norm": 0.4166202247142792,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.9705,
      "step": 122
    },
    {
      "epoch": 0.022210184182015168,
      "grad_norm": 0.4246368110179901,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.9834,
      "step": 123
    },
    {
      "epoch": 0.02239075478512098,
      "grad_norm": 0.4012325406074524,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9898,
      "step": 124
    },
    {
      "epoch": 0.022571325388226798,
      "grad_norm": 0.44190362095832825,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.0085,
      "step": 125
    },
    {
      "epoch": 0.02275189599133261,
      "grad_norm": 0.4317069947719574,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.9294,
      "step": 126
    },
    {
      "epoch": 0.022932466594438424,
      "grad_norm": 0.4211461544036865,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.8911,
      "step": 127
    },
    {
      "epoch": 0.02311303719754424,
      "grad_norm": 0.4544403851032257,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.9197,
      "step": 128
    },
    {
      "epoch": 0.023293607800650054,
      "grad_norm": 0.43215247988700867,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.9928,
      "step": 129
    },
    {
      "epoch": 0.023474178403755867,
      "grad_norm": 0.43440431356430054,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.9714,
      "step": 130
    },
    {
      "epoch": 0.023654749006861684,
      "grad_norm": 0.4638649523258209,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.9549,
      "step": 131
    },
    {
      "epoch": 0.023835319609967497,
      "grad_norm": 0.4485500156879425,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.7946,
      "step": 132
    },
    {
      "epoch": 0.02401589021307331,
      "grad_norm": 0.471426784992218,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.0043,
      "step": 133
    },
    {
      "epoch": 0.024196460816179127,
      "grad_norm": 0.4864135980606079,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.9737,
      "step": 134
    },
    {
      "epoch": 0.02437703141928494,
      "grad_norm": 0.49553418159484863,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.9599,
      "step": 135
    },
    {
      "epoch": 0.024557602022390754,
      "grad_norm": 0.48198094964027405,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.7155,
      "step": 136
    },
    {
      "epoch": 0.02473817262549657,
      "grad_norm": 0.5210572481155396,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.0872,
      "step": 137
    },
    {
      "epoch": 0.024918743228602384,
      "grad_norm": 0.517304539680481,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.8473,
      "step": 138
    },
    {
      "epoch": 0.025099313831708197,
      "grad_norm": 0.5049439668655396,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.9836,
      "step": 139
    },
    {
      "epoch": 0.025279884434814014,
      "grad_norm": 0.5623946189880371,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.9298,
      "step": 140
    },
    {
      "epoch": 0.025460455037919827,
      "grad_norm": 0.5387139320373535,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.0437,
      "step": 141
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.5679649114608765,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.0832,
      "step": 142
    },
    {
      "epoch": 0.025821596244131457,
      "grad_norm": 0.5492368340492249,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.9627,
      "step": 143
    },
    {
      "epoch": 0.02600216684723727,
      "grad_norm": 0.5792611241340637,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.9441,
      "step": 144
    },
    {
      "epoch": 0.026182737450343083,
      "grad_norm": 0.566913902759552,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.9718,
      "step": 145
    },
    {
      "epoch": 0.0263633080534489,
      "grad_norm": 0.6455346941947937,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.1376,
      "step": 146
    },
    {
      "epoch": 0.026543878656554713,
      "grad_norm": 0.6583056449890137,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.143,
      "step": 147
    },
    {
      "epoch": 0.026724449259660527,
      "grad_norm": 0.6932365298271179,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.1724,
      "step": 148
    },
    {
      "epoch": 0.026905019862766343,
      "grad_norm": 0.735855221748352,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.5011,
      "step": 149
    },
    {
      "epoch": 0.027085590465872156,
      "grad_norm": 0.8176823258399963,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.5626,
      "step": 150
    },
    {
      "epoch": 0.027085590465872156,
      "eval_loss": 2.012115478515625,
      "eval_runtime": 689.2055,
      "eval_samples_per_second": 13.533,
      "eval_steps_per_second": 3.384,
      "step": 150
    },
    {
      "epoch": 0.02726616106897797,
      "grad_norm": 0.3280618488788605,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.1242,
      "step": 151
    },
    {
      "epoch": 0.027446731672083786,
      "grad_norm": 0.376322478055954,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.0758,
      "step": 152
    },
    {
      "epoch": 0.0276273022751896,
      "grad_norm": 0.39415812492370605,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.1176,
      "step": 153
    },
    {
      "epoch": 0.027807872878295413,
      "grad_norm": 0.38797420263290405,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.2395,
      "step": 154
    },
    {
      "epoch": 0.027988443481401226,
      "grad_norm": 0.4005449414253235,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.1176,
      "step": 155
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.3990994989871979,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.0359,
      "step": 156
    },
    {
      "epoch": 0.028349584687612856,
      "grad_norm": 0.4104321300983429,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 2.0776,
      "step": 157
    },
    {
      "epoch": 0.02853015529071867,
      "grad_norm": 0.3822646737098694,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.1051,
      "step": 158
    },
    {
      "epoch": 0.028710725893824486,
      "grad_norm": 0.3958430886268616,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.8198,
      "step": 159
    },
    {
      "epoch": 0.0288912964969303,
      "grad_norm": 0.47039517760276794,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6944,
      "step": 160
    },
    {
      "epoch": 0.029071867100036113,
      "grad_norm": 0.37155014276504517,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.8661,
      "step": 161
    },
    {
      "epoch": 0.02925243770314193,
      "grad_norm": 0.38018548488616943,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.9036,
      "step": 162
    },
    {
      "epoch": 0.029433008306247743,
      "grad_norm": 0.4522913098335266,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.1851,
      "step": 163
    },
    {
      "epoch": 0.029613578909353556,
      "grad_norm": 0.42370957136154175,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.0044,
      "step": 164
    },
    {
      "epoch": 0.029794149512459372,
      "grad_norm": 0.40131139755249023,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.927,
      "step": 165
    },
    {
      "epoch": 0.029974720115565186,
      "grad_norm": 0.3930165469646454,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.0277,
      "step": 166
    },
    {
      "epoch": 0.030155290718671,
      "grad_norm": 0.405367910861969,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.0332,
      "step": 167
    },
    {
      "epoch": 0.030335861321776816,
      "grad_norm": 0.3978680372238159,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.9382,
      "step": 168
    },
    {
      "epoch": 0.03051643192488263,
      "grad_norm": 0.41161930561065674,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.8757,
      "step": 169
    },
    {
      "epoch": 0.030697002527988442,
      "grad_norm": 0.3971489667892456,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.8836,
      "step": 170
    },
    {
      "epoch": 0.03087757313109426,
      "grad_norm": 0.42250388860702515,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.0028,
      "step": 171
    },
    {
      "epoch": 0.031058143734200072,
      "grad_norm": 0.43362781405448914,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.8517,
      "step": 172
    },
    {
      "epoch": 0.031238714337305885,
      "grad_norm": 0.4665611684322357,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.9923,
      "step": 173
    },
    {
      "epoch": 0.0314192849404117,
      "grad_norm": 0.4335770606994629,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.9364,
      "step": 174
    },
    {
      "epoch": 0.03159985554351752,
      "grad_norm": 0.4319969415664673,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.0736,
      "step": 175
    },
    {
      "epoch": 0.03178042614662333,
      "grad_norm": 0.48032429814338684,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.9101,
      "step": 176
    },
    {
      "epoch": 0.031960996749729145,
      "grad_norm": 0.47980910539627075,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.9445,
      "step": 177
    },
    {
      "epoch": 0.03214156735283496,
      "grad_norm": 0.4643956422805786,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.9368,
      "step": 178
    },
    {
      "epoch": 0.03232213795594077,
      "grad_norm": 0.46265125274658203,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.0272,
      "step": 179
    },
    {
      "epoch": 0.032502708559046585,
      "grad_norm": 0.4877752363681793,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.8422,
      "step": 180
    },
    {
      "epoch": 0.0326832791621524,
      "grad_norm": 0.48772457242012024,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0428,
      "step": 181
    },
    {
      "epoch": 0.03286384976525822,
      "grad_norm": 0.45916715264320374,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.8086,
      "step": 182
    },
    {
      "epoch": 0.03304442036836403,
      "grad_norm": 0.4550033211708069,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.0127,
      "step": 183
    },
    {
      "epoch": 0.033224990971469845,
      "grad_norm": 0.5124539732933044,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.8886,
      "step": 184
    },
    {
      "epoch": 0.03340556157457566,
      "grad_norm": 0.4621534049510956,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.9027,
      "step": 185
    },
    {
      "epoch": 0.03358613217768147,
      "grad_norm": 0.4838806092739105,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.9198,
      "step": 186
    },
    {
      "epoch": 0.033766702780787285,
      "grad_norm": 0.4880743622779846,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.9477,
      "step": 187
    },
    {
      "epoch": 0.033947273383893105,
      "grad_norm": 0.6479881405830383,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.9241,
      "step": 188
    },
    {
      "epoch": 0.03412784398699892,
      "grad_norm": 0.5301950573921204,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.104,
      "step": 189
    },
    {
      "epoch": 0.03430841459010473,
      "grad_norm": 0.53728848695755,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9955,
      "step": 190
    },
    {
      "epoch": 0.034488985193210545,
      "grad_norm": 0.5534414052963257,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.0029,
      "step": 191
    },
    {
      "epoch": 0.03466955579631636,
      "grad_norm": 0.563531219959259,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.9819,
      "step": 192
    },
    {
      "epoch": 0.03485012639942217,
      "grad_norm": 0.5725007057189941,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.947,
      "step": 193
    },
    {
      "epoch": 0.03503069700252799,
      "grad_norm": 0.610448956489563,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.97,
      "step": 194
    },
    {
      "epoch": 0.035211267605633804,
      "grad_norm": 0.6770745515823364,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.1646,
      "step": 195
    },
    {
      "epoch": 0.03539183820873962,
      "grad_norm": 0.5982887744903564,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.8725,
      "step": 196
    },
    {
      "epoch": 0.03557240881184543,
      "grad_norm": 0.5943398475646973,
      "learning_rate": 6.150154258476315e-08,
      "loss": 2.0284,
      "step": 197
    },
    {
      "epoch": 0.035752979414951244,
      "grad_norm": 0.7149994373321533,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.1589,
      "step": 198
    },
    {
      "epoch": 0.03593355001805706,
      "grad_norm": 0.8116176128387451,
      "learning_rate": 6.834750376549792e-09,
      "loss": 2.3804,
      "step": 199
    },
    {
      "epoch": 0.03611412062116288,
      "grad_norm": 0.8255523443222046,
      "learning_rate": 0.0,
      "loss": 2.4566,
      "step": 200
    },
    {
      "epoch": 0.03611412062116288,
      "eval_loss": 1.9997398853302002,
      "eval_runtime": 689.5883,
      "eval_samples_per_second": 13.525,
      "eval_steps_per_second": 3.382,
      "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": 2.70499288449024e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}