{
  "best_metric": 1.3403688669204712,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.9197080291970803,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014598540145985401,
      "grad_norm": 0.3319084048271179,
      "learning_rate": 1e-05,
      "loss": 1.181,
      "step": 1
    },
    {
      "epoch": 0.014598540145985401,
      "eval_loss": 1.5133534669876099,
      "eval_runtime": 9.3557,
      "eval_samples_per_second": 12.399,
      "eval_steps_per_second": 3.1,
      "step": 1
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 0.22725151479244232,
      "learning_rate": 2e-05,
      "loss": 1.4452,
      "step": 2
    },
    {
      "epoch": 0.043795620437956206,
      "grad_norm": 0.37818995118141174,
      "learning_rate": 3e-05,
      "loss": 1.4239,
      "step": 3
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 0.2617124021053314,
      "learning_rate": 4e-05,
      "loss": 1.4074,
      "step": 4
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.25760477781295776,
      "learning_rate": 5e-05,
      "loss": 1.344,
      "step": 5
    },
    {
      "epoch": 0.08759124087591241,
      "grad_norm": 0.26329246163368225,
      "learning_rate": 6e-05,
      "loss": 1.3305,
      "step": 6
    },
    {
      "epoch": 0.10218978102189781,
      "grad_norm": 0.2981898784637451,
      "learning_rate": 7e-05,
      "loss": 1.4307,
      "step": 7
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.3114420175552368,
      "learning_rate": 8e-05,
      "loss": 1.5268,
      "step": 8
    },
    {
      "epoch": 0.13138686131386862,
      "grad_norm": 0.32977601885795593,
      "learning_rate": 9e-05,
      "loss": 1.5578,
      "step": 9
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 0.31535661220550537,
      "learning_rate": 0.0001,
      "loss": 1.5351,
      "step": 10
    },
    {
      "epoch": 0.16058394160583941,
      "grad_norm": 0.3439582288265228,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3774,
      "step": 11
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 0.3495965600013733,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.511,
      "step": 12
    },
    {
      "epoch": 0.1897810218978102,
      "grad_norm": 0.3981321454048157,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.6021,
      "step": 13
    },
    {
      "epoch": 0.20437956204379562,
      "grad_norm": 0.4625013768672943,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6555,
      "step": 14
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 0.5185847282409668,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.5121,
      "step": 15
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.7690638303756714,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.554,
      "step": 16
    },
    {
      "epoch": 0.24817518248175183,
      "grad_norm": 1.0918235778808594,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.5652,
      "step": 17
    },
    {
      "epoch": 0.26277372262773724,
      "grad_norm": 0.22662238776683807,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1163,
      "step": 18
    },
    {
      "epoch": 0.2773722627737226,
      "grad_norm": 0.27852508425712585,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3158,
      "step": 19
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.32316264510154724,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4931,
      "step": 20
    },
    {
      "epoch": 0.30656934306569344,
      "grad_norm": 0.27580755949020386,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.417,
      "step": 21
    },
    {
      "epoch": 0.32116788321167883,
      "grad_norm": 0.2609208822250366,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.3314,
      "step": 22
    },
    {
      "epoch": 0.3357664233576642,
      "grad_norm": 0.2764696478843689,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2404,
      "step": 23
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 0.2756406366825104,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2966,
      "step": 24
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 0.2725580632686615,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.3265,
      "step": 25
    },
    {
      "epoch": 0.3795620437956204,
      "grad_norm": 0.2775367498397827,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5218,
      "step": 26
    },
    {
      "epoch": 0.39416058394160586,
      "grad_norm": 0.28412678837776184,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4691,
      "step": 27
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 0.30747267603874207,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4605,
      "step": 28
    },
    {
      "epoch": 0.4233576642335766,
      "grad_norm": 0.304932564496994,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2849,
      "step": 29
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 0.3320886790752411,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.511,
      "step": 30
    },
    {
      "epoch": 0.45255474452554745,
      "grad_norm": 0.3978860676288605,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.5502,
      "step": 31
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 0.42493936419487,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3821,
      "step": 32
    },
    {
      "epoch": 0.48175182481751827,
      "grad_norm": 0.5989923477172852,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.266,
      "step": 33
    },
    {
      "epoch": 0.49635036496350365,
      "grad_norm": 1.149406909942627,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.7671,
      "step": 34
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 0.23337000608444214,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0535,
      "step": 35
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 0.28200414776802063,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.2415,
      "step": 36
    },
    {
      "epoch": 0.5401459854014599,
      "grad_norm": 0.3330218493938446,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3914,
      "step": 37
    },
    {
      "epoch": 0.5547445255474452,
      "grad_norm": 0.3114831745624542,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3058,
      "step": 38
    },
    {
      "epoch": 0.5693430656934306,
      "grad_norm": 0.2618398368358612,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4523,
      "step": 39
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.3096972405910492,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4264,
      "step": 40
    },
    {
      "epoch": 0.5985401459854015,
      "grad_norm": 0.24860817193984985,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.257,
      "step": 41
    },
    {
      "epoch": 0.6131386861313869,
      "grad_norm": 0.23159250617027283,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2942,
      "step": 42
    },
    {
      "epoch": 0.6277372262773723,
      "grad_norm": 0.28607460856437683,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6693,
      "step": 43
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 0.25008460879325867,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.5108,
      "step": 44
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 0.2586262822151184,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.5485,
      "step": 45
    },
    {
      "epoch": 0.6715328467153284,
      "grad_norm": 0.2964994013309479,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.5025,
      "step": 46
    },
    {
      "epoch": 0.6861313868613139,
      "grad_norm": 0.3088851571083069,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6587,
      "step": 47
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 0.3277207911014557,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.364,
      "step": 48
    },
    {
      "epoch": 0.7153284671532847,
      "grad_norm": 0.40233856439590454,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.4351,
      "step": 49
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.5175507664680481,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5454,
      "step": 50
    },
    {
      "epoch": 0.7299270072992701,
      "eval_loss": 1.3493497371673584,
      "eval_runtime": 9.5289,
      "eval_samples_per_second": 12.174,
      "eval_steps_per_second": 3.043,
      "step": 50
    },
    {
      "epoch": 0.7445255474452555,
      "grad_norm": 0.8519311547279358,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.8453,
      "step": 51
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 0.1970771849155426,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.2331,
      "step": 52
    },
    {
      "epoch": 0.7737226277372263,
      "grad_norm": 0.19372014701366425,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1412,
      "step": 53
    },
    {
      "epoch": 0.7883211678832117,
      "grad_norm": 0.26107850670814514,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2772,
      "step": 54
    },
    {
      "epoch": 0.8029197080291971,
      "grad_norm": 0.24381400644779205,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.3942,
      "step": 55
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 0.24780312180519104,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.3295,
      "step": 56
    },
    {
      "epoch": 0.8321167883211679,
      "grad_norm": 0.2396429479122162,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2814,
      "step": 57
    },
    {
      "epoch": 0.8467153284671532,
      "grad_norm": 0.24088458716869354,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3758,
      "step": 58
    },
    {
      "epoch": 0.8613138686131386,
      "grad_norm": 0.3038870096206665,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.506,
      "step": 59
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.3055610954761505,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5193,
      "step": 60
    },
    {
      "epoch": 0.8905109489051095,
      "grad_norm": 0.2869257926940918,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3251,
      "step": 61
    },
    {
      "epoch": 0.9051094890510949,
      "grad_norm": 0.2942329943180084,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3577,
      "step": 62
    },
    {
      "epoch": 0.9197080291970803,
      "grad_norm": 0.3005514442920685,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.4487,
      "step": 63
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 0.3311644494533539,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.6169,
      "step": 64
    },
    {
      "epoch": 0.948905109489051,
      "grad_norm": 0.3842598497867584,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.5142,
      "step": 65
    },
    {
      "epoch": 0.9635036496350365,
      "grad_norm": 0.45574358105659485,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.4748,
      "step": 66
    },
    {
      "epoch": 0.9781021897810219,
      "grad_norm": 0.6635696291923523,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2936,
      "step": 67
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 0.8519755005836487,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5073,
      "step": 68
    },
    {
      "epoch": 1.0072992700729928,
      "grad_norm": 0.39179447293281555,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.9242,
      "step": 69
    },
    {
      "epoch": 1.0218978102189782,
      "grad_norm": 0.2011762112379074,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2559,
      "step": 70
    },
    {
      "epoch": 1.0364963503649636,
      "grad_norm": 0.1856110841035843,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2009,
      "step": 71
    },
    {
      "epoch": 1.051094890510949,
      "grad_norm": 0.22846055030822754,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3111,
      "step": 72
    },
    {
      "epoch": 1.0656934306569343,
      "grad_norm": 0.2386132776737213,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2684,
      "step": 73
    },
    {
      "epoch": 1.0802919708029197,
      "grad_norm": 0.2123902589082718,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.224,
      "step": 74
    },
    {
      "epoch": 1.094890510948905,
      "grad_norm": 0.20894300937652588,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.148,
      "step": 75
    },
    {
      "epoch": 1.1094890510948905,
      "grad_norm": 0.22821173071861267,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.162,
      "step": 76
    },
    {
      "epoch": 1.1240875912408759,
      "grad_norm": 0.24483856558799744,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.3635,
      "step": 77
    },
    {
      "epoch": 1.1386861313868613,
      "grad_norm": 0.2564138174057007,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.4746,
      "step": 78
    },
    {
      "epoch": 1.1532846715328466,
      "grad_norm": 0.2763598561286926,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.4397,
      "step": 79
    },
    {
      "epoch": 1.167883211678832,
      "grad_norm": 0.29855528473854065,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3006,
      "step": 80
    },
    {
      "epoch": 1.1824817518248176,
      "grad_norm": 0.3115018308162689,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2798,
      "step": 81
    },
    {
      "epoch": 1.197080291970803,
      "grad_norm": 0.37384000420570374,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.5078,
      "step": 82
    },
    {
      "epoch": 1.2116788321167884,
      "grad_norm": 0.4091534912586212,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.218,
      "step": 83
    },
    {
      "epoch": 1.2262773722627738,
      "grad_norm": 0.4912202060222626,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1225,
      "step": 84
    },
    {
      "epoch": 1.2408759124087592,
      "grad_norm": 0.6514554619789124,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.0204,
      "step": 85
    },
    {
      "epoch": 1.2554744525547445,
      "grad_norm": 0.5131337642669678,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0472,
      "step": 86
    },
    {
      "epoch": 1.27007299270073,
      "grad_norm": 0.26548564434051514,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1701,
      "step": 87
    },
    {
      "epoch": 1.2846715328467153,
      "grad_norm": 0.34225356578826904,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.3138,
      "step": 88
    },
    {
      "epoch": 1.2992700729927007,
      "grad_norm": 0.30046388506889343,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2964,
      "step": 89
    },
    {
      "epoch": 1.313868613138686,
      "grad_norm": 0.2987300157546997,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3948,
      "step": 90
    },
    {
      "epoch": 1.3284671532846715,
      "grad_norm": 0.2773885130882263,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.3389,
      "step": 91
    },
    {
      "epoch": 1.343065693430657,
      "grad_norm": 0.2685887813568115,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0811,
      "step": 92
    },
    {
      "epoch": 1.3576642335766422,
      "grad_norm": 0.2982064485549927,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2969,
      "step": 93
    },
    {
      "epoch": 1.3722627737226278,
      "grad_norm": 0.3466685116291046,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3993,
      "step": 94
    },
    {
      "epoch": 1.3868613138686132,
      "grad_norm": 0.3619859218597412,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.2985,
      "step": 95
    },
    {
      "epoch": 1.4014598540145986,
      "grad_norm": 0.34207260608673096,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.2145,
      "step": 96
    },
    {
      "epoch": 1.416058394160584,
      "grad_norm": 0.3797200620174408,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.3519,
      "step": 97
    },
    {
      "epoch": 1.4306569343065694,
      "grad_norm": 0.4334133565425873,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.3534,
      "step": 98
    },
    {
      "epoch": 1.4452554744525548,
      "grad_norm": 0.4691706597805023,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4453,
      "step": 99
    },
    {
      "epoch": 1.4598540145985401,
      "grad_norm": 0.49701106548309326,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.215,
      "step": 100
    },
    {
      "epoch": 1.4598540145985401,
      "eval_loss": 1.3403688669204712,
      "eval_runtime": 9.5466,
      "eval_samples_per_second": 12.151,
      "eval_steps_per_second": 3.038,
      "step": 100
    },
    {
      "epoch": 1.4744525547445255,
      "grad_norm": 0.6068786978721619,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0087,
      "step": 101
    },
    {
      "epoch": 1.489051094890511,
      "grad_norm": 0.870746910572052,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.1942,
      "step": 102
    },
    {
      "epoch": 1.5036496350364965,
      "grad_norm": 0.6751657128334045,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9958,
      "step": 103
    },
    {
      "epoch": 1.5182481751824817,
      "grad_norm": 0.2680055797100067,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.1099,
      "step": 104
    },
    {
      "epoch": 1.5328467153284673,
      "grad_norm": 0.4004400372505188,
      "learning_rate": 5e-05,
      "loss": 1.3338,
      "step": 105
    },
    {
      "epoch": 1.5474452554744524,
      "grad_norm": 0.3412664234638214,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2776,
      "step": 106
    },
    {
      "epoch": 1.562043795620438,
      "grad_norm": 0.34415391087532043,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.2537,
      "step": 107
    },
    {
      "epoch": 1.5766423357664232,
      "grad_norm": 0.3119634687900543,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.2474,
      "step": 108
    },
    {
      "epoch": 1.5912408759124088,
      "grad_norm": 0.30623722076416016,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.208,
      "step": 109
    },
    {
      "epoch": 1.6058394160583942,
      "grad_norm": 0.2884502112865448,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1903,
      "step": 110
    },
    {
      "epoch": 1.6204379562043796,
      "grad_norm": 0.31739604473114014,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3905,
      "step": 111
    },
    {
      "epoch": 1.635036496350365,
      "grad_norm": 0.3529512286186218,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4715,
      "step": 112
    },
    {
      "epoch": 1.6496350364963503,
      "grad_norm": 0.3551652729511261,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.2401,
      "step": 113
    },
    {
      "epoch": 1.6642335766423357,
      "grad_norm": 0.38121482729911804,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.2832,
      "step": 114
    },
    {
      "epoch": 1.6788321167883211,
      "grad_norm": 0.39327099919319153,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.4636,
      "step": 115
    },
    {
      "epoch": 1.6934306569343067,
      "grad_norm": 0.448539674282074,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.4401,
      "step": 116
    },
    {
      "epoch": 1.7080291970802919,
      "grad_norm": 0.5393117070198059,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2598,
      "step": 117
    },
    {
      "epoch": 1.7226277372262775,
      "grad_norm": 0.6297147274017334,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1409,
      "step": 118
    },
    {
      "epoch": 1.7372262773722627,
      "grad_norm": 0.8002923130989075,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.088,
      "step": 119
    },
    {
      "epoch": 1.7518248175182483,
      "grad_norm": 0.4918464720249176,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.754,
      "step": 120
    },
    {
      "epoch": 1.7664233576642334,
      "grad_norm": 0.45180532336235046,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1759,
      "step": 121
    },
    {
      "epoch": 1.781021897810219,
      "grad_norm": 0.30924010276794434,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.2694,
      "step": 122
    },
    {
      "epoch": 1.7956204379562044,
      "grad_norm": 0.3288983106613159,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.3413,
      "step": 123
    },
    {
      "epoch": 1.8102189781021898,
      "grad_norm": 0.30453771352767944,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2433,
      "step": 124
    },
    {
      "epoch": 1.8248175182481752,
      "grad_norm": 0.29526111483573914,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1677,
      "step": 125
    },
    {
      "epoch": 1.8394160583941606,
      "grad_norm": 0.2940791845321655,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2167,
      "step": 126
    },
    {
      "epoch": 1.854014598540146,
      "grad_norm": 0.3172758221626282,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.3569,
      "step": 127
    },
    {
      "epoch": 1.8686131386861313,
      "grad_norm": 0.32221782207489014,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.5569,
      "step": 128
    },
    {
      "epoch": 1.883211678832117,
      "grad_norm": 0.3492722809314728,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4811,
      "step": 129
    },
    {
      "epoch": 1.897810218978102,
      "grad_norm": 0.3398060202598572,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.1588,
      "step": 130
    },
    {
      "epoch": 1.9124087591240877,
      "grad_norm": 0.3653400242328644,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2553,
      "step": 131
    },
    {
      "epoch": 1.9270072992700729,
      "grad_norm": 0.39235830307006836,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.3216,
      "step": 132
    },
    {
      "epoch": 1.9416058394160585,
      "grad_norm": 0.45246440172195435,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.3392,
      "step": 133
    },
    {
      "epoch": 1.9562043795620438,
      "grad_norm": 0.5468692779541016,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.3313,
      "step": 134
    },
    {
      "epoch": 1.9708029197080292,
      "grad_norm": 0.6530583500862122,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2808,
      "step": 135
    },
    {
      "epoch": 1.9854014598540146,
      "grad_norm": 0.9565390348434448,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.2142,
      "step": 136
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7995310425758362,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.8118,
      "step": 137
    },
    {
      "epoch": 2.0145985401459856,
      "grad_norm": 0.28269508481025696,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0355,
      "step": 138
    },
    {
      "epoch": 2.0291970802919708,
      "grad_norm": 0.25445064902305603,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2398,
      "step": 139
    },
    {
      "epoch": 2.0437956204379564,
      "grad_norm": 0.2695455551147461,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3301,
      "step": 140
    },
    {
      "epoch": 2.0583941605839415,
      "grad_norm": 0.28496482968330383,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.2391,
      "step": 141
    },
    {
      "epoch": 2.072992700729927,
      "grad_norm": 0.29637178778648376,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1768,
      "step": 142
    },
    {
      "epoch": 2.0875912408759123,
      "grad_norm": 0.28458163142204285,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1282,
      "step": 143
    },
    {
      "epoch": 2.102189781021898,
      "grad_norm": 0.30355146527290344,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2139,
      "step": 144
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 0.3055032193660736,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1664,
      "step": 145
    },
    {
      "epoch": 2.1313868613138687,
      "grad_norm": 0.31824806332588196,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2404,
      "step": 146
    },
    {
      "epoch": 2.145985401459854,
      "grad_norm": 0.3455633223056793,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.274,
      "step": 147
    },
    {
      "epoch": 2.1605839416058394,
      "grad_norm": 0.35035890340805054,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0409,
      "step": 148
    },
    {
      "epoch": 2.1751824817518246,
      "grad_norm": 0.40098950266838074,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.362,
      "step": 149
    },
    {
      "epoch": 2.18978102189781,
      "grad_norm": 0.4153252840042114,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3051,
      "step": 150
    },
    {
      "epoch": 2.18978102189781,
      "eval_loss": 1.350590705871582,
      "eval_runtime": 9.8003,
      "eval_samples_per_second": 11.836,
      "eval_steps_per_second": 2.959,
      "step": 150
    },
    {
      "epoch": 2.204379562043796,
      "grad_norm": 0.473540723323822,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.3304,
      "step": 151
    },
    {
      "epoch": 2.218978102189781,
      "grad_norm": 0.6200093626976013,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.0544,
      "step": 152
    },
    {
      "epoch": 2.2335766423357666,
      "grad_norm": 0.6468912363052368,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7966,
      "step": 153
    },
    {
      "epoch": 2.2481751824817517,
      "grad_norm": 0.9516965746879578,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7722,
      "step": 154
    },
    {
      "epoch": 2.2627737226277373,
      "grad_norm": 0.2620222866535187,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.1091,
      "step": 155
    },
    {
      "epoch": 2.2773722627737225,
      "grad_norm": 0.30072930455207825,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2845,
      "step": 156
    },
    {
      "epoch": 2.291970802919708,
      "grad_norm": 0.3151152729988098,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.2673,
      "step": 157
    },
    {
      "epoch": 2.3065693430656933,
      "grad_norm": 0.33394792675971985,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.2977,
      "step": 158
    },
    {
      "epoch": 2.321167883211679,
      "grad_norm": 0.3527221083641052,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.2271,
      "step": 159
    },
    {
      "epoch": 2.335766423357664,
      "grad_norm": 0.3590930998325348,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.1932,
      "step": 160
    },
    {
      "epoch": 2.3503649635036497,
      "grad_norm": 0.3208116292953491,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.0758,
      "step": 161
    },
    {
      "epoch": 2.3649635036496353,
      "grad_norm": 0.344931960105896,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2569,
      "step": 162
    },
    {
      "epoch": 2.3795620437956204,
      "grad_norm": 0.3697018325328827,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4106,
      "step": 163
    },
    {
      "epoch": 2.394160583941606,
      "grad_norm": 0.3989783525466919,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.1972,
      "step": 164
    },
    {
      "epoch": 2.408759124087591,
      "grad_norm": 0.4073117971420288,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2266,
      "step": 165
    },
    {
      "epoch": 2.423357664233577,
      "grad_norm": 0.419900506734848,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2993,
      "step": 166
    },
    {
      "epoch": 2.437956204379562,
      "grad_norm": 0.4584241509437561,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.1547,
      "step": 167
    },
    {
      "epoch": 2.4525547445255476,
      "grad_norm": 0.5514969229698181,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.2562,
      "step": 168
    },
    {
      "epoch": 2.4671532846715327,
      "grad_norm": 0.588891863822937,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.0881,
      "step": 169
    },
    {
      "epoch": 2.4817518248175183,
      "grad_norm": 0.6882247924804688,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.759,
      "step": 170
    },
    {
      "epoch": 2.4963503649635035,
      "grad_norm": 0.9549835324287415,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6763,
      "step": 171
    },
    {
      "epoch": 2.510948905109489,
      "grad_norm": 0.2518211007118225,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.1072,
      "step": 172
    },
    {
      "epoch": 2.5255474452554747,
      "grad_norm": 0.22837506234645844,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.9739,
      "step": 173
    },
    {
      "epoch": 2.54014598540146,
      "grad_norm": 0.28022444248199463,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.1546,
      "step": 174
    },
    {
      "epoch": 2.554744525547445,
      "grad_norm": 0.29569241404533386,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1373,
      "step": 175
    },
    {
      "epoch": 2.5693430656934306,
      "grad_norm": 0.30761557817459106,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.1849,
      "step": 176
    },
    {
      "epoch": 2.5839416058394162,
      "grad_norm": 0.3126266598701477,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.1253,
      "step": 177
    },
    {
      "epoch": 2.5985401459854014,
      "grad_norm": 0.31830742955207825,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1849,
      "step": 178
    },
    {
      "epoch": 2.613138686131387,
      "grad_norm": 0.3462705612182617,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2175,
      "step": 179
    },
    {
      "epoch": 2.627737226277372,
      "grad_norm": 0.3554275333881378,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4267,
      "step": 180
    },
    {
      "epoch": 2.6423357664233578,
      "grad_norm": 0.36749497056007385,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2966,
      "step": 181
    },
    {
      "epoch": 2.656934306569343,
      "grad_norm": 0.3893539011478424,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.0501,
      "step": 182
    },
    {
      "epoch": 2.6715328467153285,
      "grad_norm": 0.41343075037002563,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1616,
      "step": 183
    },
    {
      "epoch": 2.686131386861314,
      "grad_norm": 0.4954538345336914,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1895,
      "step": 184
    },
    {
      "epoch": 2.7007299270072993,
      "grad_norm": 0.5604075789451599,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.0457,
      "step": 185
    },
    {
      "epoch": 2.7153284671532845,
      "grad_norm": 0.6301850080490112,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8334,
      "step": 186
    },
    {
      "epoch": 2.72992700729927,
      "grad_norm": 0.7159302234649658,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7245,
      "step": 187
    },
    {
      "epoch": 2.7445255474452557,
      "grad_norm": 0.9656034708023071,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9942,
      "step": 188
    },
    {
      "epoch": 2.759124087591241,
      "grad_norm": 0.22405803203582764,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9238,
      "step": 189
    },
    {
      "epoch": 2.7737226277372264,
      "grad_norm": 0.2776642441749573,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.2475,
      "step": 190
    },
    {
      "epoch": 2.7883211678832116,
      "grad_norm": 0.29509037733078003,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.217,
      "step": 191
    },
    {
      "epoch": 2.802919708029197,
      "grad_norm": 0.3248222768306732,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.253,
      "step": 192
    },
    {
      "epoch": 2.8175182481751824,
      "grad_norm": 0.3120918571949005,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.1979,
      "step": 193
    },
    {
      "epoch": 2.832116788321168,
      "grad_norm": 0.3346730172634125,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.1486,
      "step": 194
    },
    {
      "epoch": 2.846715328467153,
      "grad_norm": 0.34315040707588196,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.246,
      "step": 195
    },
    {
      "epoch": 2.8613138686131387,
      "grad_norm": 0.33361443877220154,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2958,
      "step": 196
    },
    {
      "epoch": 2.875912408759124,
      "grad_norm": 0.3689609169960022,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.3806,
      "step": 197
    },
    {
      "epoch": 2.8905109489051095,
      "grad_norm": 0.37266358733177185,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.2632,
      "step": 198
    },
    {
      "epoch": 2.905109489051095,
      "grad_norm": 0.3840593099594116,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.2378,
      "step": 199
    },
    {
      "epoch": 2.9197080291970803,
      "grad_norm": 0.4111122190952301,
      "learning_rate": 0.0,
      "loss": 1.181,
      "step": 200
    },
    {
      "epoch": 2.9197080291970803,
      "eval_loss": 1.350307822227478,
      "eval_runtime": 9.802,
      "eval_samples_per_second": 11.834,
      "eval_steps_per_second": 2.959,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.105049416617165e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}