{
  "best_metric": 0.3980286419391632,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.3468208092485549,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023121387283236996,
      "grad_norm": 0.344505250453949,
      "learning_rate": 1e-05,
      "loss": 0.5623,
      "step": 1
    },
    {
      "epoch": 0.0023121387283236996,
      "eval_loss": 0.9265726208686829,
      "eval_runtime": 54.8916,
      "eval_samples_per_second": 13.281,
      "eval_steps_per_second": 3.334,
      "step": 1
    },
    {
      "epoch": 0.004624277456647399,
      "grad_norm": 0.4038516879081726,
      "learning_rate": 2e-05,
      "loss": 0.626,
      "step": 2
    },
    {
      "epoch": 0.006936416184971098,
      "grad_norm": 0.4837007224559784,
      "learning_rate": 3e-05,
      "loss": 0.6542,
      "step": 3
    },
    {
      "epoch": 0.009248554913294798,
      "grad_norm": 0.5408232808113098,
      "learning_rate": 4e-05,
      "loss": 0.6802,
      "step": 4
    },
    {
      "epoch": 0.011560693641618497,
      "grad_norm": 0.5839534997940063,
      "learning_rate": 5e-05,
      "loss": 0.7069,
      "step": 5
    },
    {
      "epoch": 0.013872832369942197,
      "grad_norm": 0.5539509057998657,
      "learning_rate": 6e-05,
      "loss": 0.6477,
      "step": 6
    },
    {
      "epoch": 0.016184971098265895,
      "grad_norm": 0.5237308144569397,
      "learning_rate": 7e-05,
      "loss": 0.6347,
      "step": 7
    },
    {
      "epoch": 0.018497109826589597,
      "grad_norm": 0.6599310040473938,
      "learning_rate": 8e-05,
      "loss": 0.6573,
      "step": 8
    },
    {
      "epoch": 0.020809248554913295,
      "grad_norm": 0.7445451021194458,
      "learning_rate": 9e-05,
      "loss": 0.63,
      "step": 9
    },
    {
      "epoch": 0.023121387283236993,
      "grad_norm": 0.5941464900970459,
      "learning_rate": 0.0001,
      "loss": 0.5799,
      "step": 10
    },
    {
      "epoch": 0.025433526011560695,
      "grad_norm": 0.575706422328949,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5875,
      "step": 11
    },
    {
      "epoch": 0.027745664739884393,
      "grad_norm": 0.5437912940979004,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6073,
      "step": 12
    },
    {
      "epoch": 0.03005780346820809,
      "grad_norm": 0.5555635690689087,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.552,
      "step": 13
    },
    {
      "epoch": 0.03236994219653179,
      "grad_norm": 0.5008283853530884,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5755,
      "step": 14
    },
    {
      "epoch": 0.03468208092485549,
      "grad_norm": 0.4697621464729309,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5487,
      "step": 15
    },
    {
      "epoch": 0.03699421965317919,
      "grad_norm": 0.49196502566337585,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5603,
      "step": 16
    },
    {
      "epoch": 0.03930635838150289,
      "grad_norm": 0.5358009338378906,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.553,
      "step": 17
    },
    {
      "epoch": 0.04161849710982659,
      "grad_norm": 0.5355182886123657,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.565,
      "step": 18
    },
    {
      "epoch": 0.04393063583815029,
      "grad_norm": 0.5132077932357788,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5302,
      "step": 19
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 0.4611286222934723,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5371,
      "step": 20
    },
    {
      "epoch": 0.048554913294797684,
      "grad_norm": 0.540475070476532,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5539,
      "step": 21
    },
    {
      "epoch": 0.05086705202312139,
      "grad_norm": 0.5050294399261475,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5331,
      "step": 22
    },
    {
      "epoch": 0.05317919075144509,
      "grad_norm": 0.486613005399704,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5144,
      "step": 23
    },
    {
      "epoch": 0.055491329479768786,
      "grad_norm": 0.4772755205631256,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5127,
      "step": 24
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 0.4679744243621826,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5098,
      "step": 25
    },
    {
      "epoch": 0.06011560693641618,
      "grad_norm": 0.5049153566360474,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.506,
      "step": 26
    },
    {
      "epoch": 0.06242774566473988,
      "grad_norm": 0.521531879901886,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5017,
      "step": 27
    },
    {
      "epoch": 0.06473988439306358,
      "grad_norm": 0.4882335066795349,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4765,
      "step": 28
    },
    {
      "epoch": 0.06705202312138728,
      "grad_norm": 0.44829580187797546,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4982,
      "step": 29
    },
    {
      "epoch": 0.06936416184971098,
      "grad_norm": 0.4319728910923004,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4354,
      "step": 30
    },
    {
      "epoch": 0.07167630057803469,
      "grad_norm": 0.48326531052589417,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.468,
      "step": 31
    },
    {
      "epoch": 0.07398843930635839,
      "grad_norm": 0.4748351275920868,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4528,
      "step": 32
    },
    {
      "epoch": 0.07630057803468208,
      "grad_norm": 0.4739306569099426,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4549,
      "step": 33
    },
    {
      "epoch": 0.07861271676300578,
      "grad_norm": 0.4773447513580322,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4487,
      "step": 34
    },
    {
      "epoch": 0.08092485549132948,
      "grad_norm": 0.49284377694129944,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4354,
      "step": 35
    },
    {
      "epoch": 0.08323699421965318,
      "grad_norm": 0.4919143319129944,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.4212,
      "step": 36
    },
    {
      "epoch": 0.08554913294797688,
      "grad_norm": 0.5333304405212402,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4497,
      "step": 37
    },
    {
      "epoch": 0.08786127167630058,
      "grad_norm": 0.5420262217521667,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4353,
      "step": 38
    },
    {
      "epoch": 0.09017341040462427,
      "grad_norm": 0.5163606405258179,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4633,
      "step": 39
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 0.5579794645309448,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4468,
      "step": 40
    },
    {
      "epoch": 0.09479768786127167,
      "grad_norm": 0.5031202435493469,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4671,
      "step": 41
    },
    {
      "epoch": 0.09710982658959537,
      "grad_norm": 0.5082544088363647,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4218,
      "step": 42
    },
    {
      "epoch": 0.09942196531791908,
      "grad_norm": 0.4667387008666992,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4441,
      "step": 43
    },
    {
      "epoch": 0.10173410404624278,
      "grad_norm": 0.5056141018867493,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4283,
      "step": 44
    },
    {
      "epoch": 0.10404624277456648,
      "grad_norm": 0.5060005784034729,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4364,
      "step": 45
    },
    {
      "epoch": 0.10635838150289018,
      "grad_norm": 0.5063457489013672,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4323,
      "step": 46
    },
    {
      "epoch": 0.10867052023121387,
      "grad_norm": 0.5484075546264648,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4661,
      "step": 47
    },
    {
      "epoch": 0.11098265895953757,
      "grad_norm": 0.5662423372268677,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4161,
      "step": 48
    },
    {
      "epoch": 0.11329479768786127,
      "grad_norm": 0.6517870426177979,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4972,
      "step": 49
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": 0.8288584351539612,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4407,
      "step": 50
    },
    {
      "epoch": 0.11560693641618497,
      "eval_loss": 0.48895522952079773,
      "eval_runtime": 55.484,
      "eval_samples_per_second": 13.139,
      "eval_steps_per_second": 3.298,
      "step": 50
    },
    {
      "epoch": 0.11791907514450867,
      "grad_norm": 0.48289260268211365,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5234,
      "step": 51
    },
    {
      "epoch": 0.12023121387283237,
      "grad_norm": 0.5483802556991577,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5555,
      "step": 52
    },
    {
      "epoch": 0.12254335260115606,
      "grad_norm": 0.4908915162086487,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5437,
      "step": 53
    },
    {
      "epoch": 0.12485549132947976,
      "grad_norm": 0.44201579689979553,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.532,
      "step": 54
    },
    {
      "epoch": 0.12716763005780346,
      "grad_norm": 0.35535645484924316,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4679,
      "step": 55
    },
    {
      "epoch": 0.12947976878612716,
      "grad_norm": 0.36609333753585815,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5125,
      "step": 56
    },
    {
      "epoch": 0.13179190751445086,
      "grad_norm": 0.4033358693122864,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4996,
      "step": 57
    },
    {
      "epoch": 0.13410404624277455,
      "grad_norm": 0.4537183940410614,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5015,
      "step": 58
    },
    {
      "epoch": 0.13641618497109825,
      "grad_norm": 0.42289552092552185,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4932,
      "step": 59
    },
    {
      "epoch": 0.13872832369942195,
      "grad_norm": 0.37897226214408875,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4721,
      "step": 60
    },
    {
      "epoch": 0.14104046242774568,
      "grad_norm": 0.38306698203086853,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4902,
      "step": 61
    },
    {
      "epoch": 0.14335260115606938,
      "grad_norm": 0.39026594161987305,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4543,
      "step": 62
    },
    {
      "epoch": 0.14566473988439307,
      "grad_norm": 0.42585158348083496,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4673,
      "step": 63
    },
    {
      "epoch": 0.14797687861271677,
      "grad_norm": 0.42971956729888916,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4389,
      "step": 64
    },
    {
      "epoch": 0.15028901734104047,
      "grad_norm": 0.4161655306816101,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4708,
      "step": 65
    },
    {
      "epoch": 0.15260115606936417,
      "grad_norm": 0.40648549795150757,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4559,
      "step": 66
    },
    {
      "epoch": 0.15491329479768787,
      "grad_norm": 0.4191438555717468,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4522,
      "step": 67
    },
    {
      "epoch": 0.15722543352601157,
      "grad_norm": 0.47340279817581177,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.444,
      "step": 68
    },
    {
      "epoch": 0.15953757225433526,
      "grad_norm": 0.4360640048980713,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4421,
      "step": 69
    },
    {
      "epoch": 0.16184971098265896,
      "grad_norm": 0.4308934807777405,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4379,
      "step": 70
    },
    {
      "epoch": 0.16416184971098266,
      "grad_norm": 0.40363365411758423,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3989,
      "step": 71
    },
    {
      "epoch": 0.16647398843930636,
      "grad_norm": 0.44806885719299316,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4373,
      "step": 72
    },
    {
      "epoch": 0.16878612716763006,
      "grad_norm": 0.41386452317237854,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4112,
      "step": 73
    },
    {
      "epoch": 0.17109826589595376,
      "grad_norm": 0.4437868893146515,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4328,
      "step": 74
    },
    {
      "epoch": 0.17341040462427745,
      "grad_norm": 0.4278442859649658,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4141,
      "step": 75
    },
    {
      "epoch": 0.17572254335260115,
      "grad_norm": 0.4373546540737152,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.428,
      "step": 76
    },
    {
      "epoch": 0.17803468208092485,
      "grad_norm": 0.42723631858825684,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.398,
      "step": 77
    },
    {
      "epoch": 0.18034682080924855,
      "grad_norm": 0.4368928074836731,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4067,
      "step": 78
    },
    {
      "epoch": 0.18265895953757225,
      "grad_norm": 0.4366152286529541,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4172,
      "step": 79
    },
    {
      "epoch": 0.18497109826589594,
      "grad_norm": 0.4488803446292877,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.407,
      "step": 80
    },
    {
      "epoch": 0.18728323699421964,
      "grad_norm": 0.4308355450630188,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3983,
      "step": 81
    },
    {
      "epoch": 0.18959537572254334,
      "grad_norm": 0.43071937561035156,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4044,
      "step": 82
    },
    {
      "epoch": 0.19190751445086704,
      "grad_norm": 0.49217772483825684,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.412,
      "step": 83
    },
    {
      "epoch": 0.19421965317919074,
      "grad_norm": 0.4487551152706146,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3821,
      "step": 84
    },
    {
      "epoch": 0.19653179190751446,
      "grad_norm": 0.42099928855895996,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3856,
      "step": 85
    },
    {
      "epoch": 0.19884393063583816,
      "grad_norm": 0.4627571702003479,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3734,
      "step": 86
    },
    {
      "epoch": 0.20115606936416186,
      "grad_norm": 0.42417681217193604,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3633,
      "step": 87
    },
    {
      "epoch": 0.20346820809248556,
      "grad_norm": 0.44514182209968567,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3745,
      "step": 88
    },
    {
      "epoch": 0.20578034682080926,
      "grad_norm": 0.4584387540817261,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3893,
      "step": 89
    },
    {
      "epoch": 0.20809248554913296,
      "grad_norm": 0.4498540759086609,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3769,
      "step": 90
    },
    {
      "epoch": 0.21040462427745665,
      "grad_norm": 0.4657157361507416,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3816,
      "step": 91
    },
    {
      "epoch": 0.21271676300578035,
      "grad_norm": 0.47834116220474243,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3824,
      "step": 92
    },
    {
      "epoch": 0.21502890173410405,
      "grad_norm": 0.5006725788116455,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4205,
      "step": 93
    },
    {
      "epoch": 0.21734104046242775,
      "grad_norm": 0.4631800949573517,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3384,
      "step": 94
    },
    {
      "epoch": 0.21965317919075145,
      "grad_norm": 0.4934702515602112,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3953,
      "step": 95
    },
    {
      "epoch": 0.22196531791907514,
      "grad_norm": 0.5679356455802917,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4398,
      "step": 96
    },
    {
      "epoch": 0.22427745664739884,
      "grad_norm": 0.5142523050308228,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3823,
      "step": 97
    },
    {
      "epoch": 0.22658959537572254,
      "grad_norm": 0.5662355422973633,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4076,
      "step": 98
    },
    {
      "epoch": 0.22890173410404624,
      "grad_norm": 0.5996310710906982,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4301,
      "step": 99
    },
    {
      "epoch": 0.23121387283236994,
      "grad_norm": 0.6809976100921631,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3711,
      "step": 100
    },
    {
      "epoch": 0.23121387283236994,
      "eval_loss": 0.4530438780784607,
      "eval_runtime": 55.434,
      "eval_samples_per_second": 13.151,
      "eval_steps_per_second": 3.301,
      "step": 100
    },
    {
      "epoch": 0.23352601156069364,
      "grad_norm": 0.2852354049682617,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4976,
      "step": 101
    },
    {
      "epoch": 0.23583815028901733,
      "grad_norm": 0.35582005977630615,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5344,
      "step": 102
    },
    {
      "epoch": 0.23815028901734103,
      "grad_norm": 0.4306597411632538,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5123,
      "step": 103
    },
    {
      "epoch": 0.24046242774566473,
      "grad_norm": 0.4623056948184967,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4795,
      "step": 104
    },
    {
      "epoch": 0.24277456647398843,
      "grad_norm": 0.45900461077690125,
      "learning_rate": 5e-05,
      "loss": 0.4629,
      "step": 105
    },
    {
      "epoch": 0.24508670520231213,
      "grad_norm": 0.3884137272834778,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4861,
      "step": 106
    },
    {
      "epoch": 0.24739884393063583,
      "grad_norm": 0.38582172989845276,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4635,
      "step": 107
    },
    {
      "epoch": 0.24971098265895952,
      "grad_norm": 0.36394259333610535,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4533,
      "step": 108
    },
    {
      "epoch": 0.2520231213872832,
      "grad_norm": 0.3826720416545868,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4762,
      "step": 109
    },
    {
      "epoch": 0.2543352601156069,
      "grad_norm": 0.4032803177833557,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4543,
      "step": 110
    },
    {
      "epoch": 0.2566473988439306,
      "grad_norm": 0.4062879979610443,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4138,
      "step": 111
    },
    {
      "epoch": 0.2589595375722543,
      "grad_norm": 0.40897321701049805,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.437,
      "step": 112
    },
    {
      "epoch": 0.261271676300578,
      "grad_norm": 0.38823291659355164,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4179,
      "step": 113
    },
    {
      "epoch": 0.2635838150289017,
      "grad_norm": 0.4021931290626526,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4432,
      "step": 114
    },
    {
      "epoch": 0.2658959537572254,
      "grad_norm": 0.38717618584632874,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4293,
      "step": 115
    },
    {
      "epoch": 0.2682080924855491,
      "grad_norm": 0.37913429737091064,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4331,
      "step": 116
    },
    {
      "epoch": 0.2705202312138728,
      "grad_norm": 0.37779611349105835,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4313,
      "step": 117
    },
    {
      "epoch": 0.2728323699421965,
      "grad_norm": 0.3787301182746887,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4174,
      "step": 118
    },
    {
      "epoch": 0.2751445086705202,
      "grad_norm": 0.37400850653648376,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3715,
      "step": 119
    },
    {
      "epoch": 0.2774566473988439,
      "grad_norm": 0.4016834795475006,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3909,
      "step": 120
    },
    {
      "epoch": 0.27976878612716766,
      "grad_norm": 0.41165751218795776,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3953,
      "step": 121
    },
    {
      "epoch": 0.28208092485549136,
      "grad_norm": 0.397403359413147,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3943,
      "step": 122
    },
    {
      "epoch": 0.28439306358381505,
      "grad_norm": 0.42636638879776,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4129,
      "step": 123
    },
    {
      "epoch": 0.28670520231213875,
      "grad_norm": 0.40113964676856995,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4056,
      "step": 124
    },
    {
      "epoch": 0.28901734104046245,
      "grad_norm": 0.397616446018219,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3683,
      "step": 125
    },
    {
      "epoch": 0.29132947976878615,
      "grad_norm": 0.40275707840919495,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3787,
      "step": 126
    },
    {
      "epoch": 0.29364161849710985,
      "grad_norm": 0.44181469082832336,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3794,
      "step": 127
    },
    {
      "epoch": 0.29595375722543354,
      "grad_norm": 0.4472711682319641,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3897,
      "step": 128
    },
    {
      "epoch": 0.29826589595375724,
      "grad_norm": 0.42659565806388855,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3889,
      "step": 129
    },
    {
      "epoch": 0.30057803468208094,
      "grad_norm": 0.4072771370410919,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3523,
      "step": 130
    },
    {
      "epoch": 0.30289017341040464,
      "grad_norm": 0.3996623456478119,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3353,
      "step": 131
    },
    {
      "epoch": 0.30520231213872834,
      "grad_norm": 0.3975715637207031,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3361,
      "step": 132
    },
    {
      "epoch": 0.30751445086705204,
      "grad_norm": 0.4468100368976593,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3838,
      "step": 133
    },
    {
      "epoch": 0.30982658959537573,
      "grad_norm": 0.42215695977211,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3393,
      "step": 134
    },
    {
      "epoch": 0.31213872832369943,
      "grad_norm": 0.4449115991592407,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4239,
      "step": 135
    },
    {
      "epoch": 0.31445086705202313,
      "grad_norm": 0.4244880676269531,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3593,
      "step": 136
    },
    {
      "epoch": 0.31676300578034683,
      "grad_norm": 0.43322813510894775,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3543,
      "step": 137
    },
    {
      "epoch": 0.3190751445086705,
      "grad_norm": 0.43968623876571655,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3778,
      "step": 138
    },
    {
      "epoch": 0.3213872832369942,
      "grad_norm": 0.44799986481666565,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3564,
      "step": 139
    },
    {
      "epoch": 0.3236994219653179,
      "grad_norm": 0.4537672996520996,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3249,
      "step": 140
    },
    {
      "epoch": 0.3260115606936416,
      "grad_norm": 0.44438549876213074,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.369,
      "step": 141
    },
    {
      "epoch": 0.3283236994219653,
      "grad_norm": 0.47159919142723083,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3804,
      "step": 142
    },
    {
      "epoch": 0.330635838150289,
      "grad_norm": 0.45272132754325867,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3509,
      "step": 143
    },
    {
      "epoch": 0.3329479768786127,
      "grad_norm": 0.4658597409725189,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3796,
      "step": 144
    },
    {
      "epoch": 0.3352601156069364,
      "grad_norm": 0.4488268196582794,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3464,
      "step": 145
    },
    {
      "epoch": 0.3375722543352601,
      "grad_norm": 0.4805041253566742,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3794,
      "step": 146
    },
    {
      "epoch": 0.3398843930635838,
      "grad_norm": 0.5441201329231262,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3796,
      "step": 147
    },
    {
      "epoch": 0.3421965317919075,
      "grad_norm": 0.7714905142784119,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4142,
      "step": 148
    },
    {
      "epoch": 0.3445086705202312,
      "grad_norm": 0.5890783071517944,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3823,
      "step": 149
    },
    {
      "epoch": 0.3468208092485549,
      "grad_norm": 0.6957663893699646,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3374,
      "step": 150
    },
    {
      "epoch": 0.3468208092485549,
      "eval_loss": 0.3980286419391632,
      "eval_runtime": 55.4876,
      "eval_samples_per_second": 13.138,
      "eval_steps_per_second": 3.298,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2665416520656486e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}