{
  "best_metric": 0.967810869216919,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.09752925877763328,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006501950585175553,
      "grad_norm": 0.24665670096874237,
      "learning_rate": 1e-05,
      "loss": 0.9802,
      "step": 1
    },
    {
      "epoch": 0.0006501950585175553,
      "eval_loss": 1.2826741933822632,
      "eval_runtime": 285.8077,
      "eval_samples_per_second": 9.066,
      "eval_steps_per_second": 2.267,
      "step": 1
    },
    {
      "epoch": 0.0013003901170351106,
      "grad_norm": 0.2848244607448578,
      "learning_rate": 2e-05,
      "loss": 1.0425,
      "step": 2
    },
    {
      "epoch": 0.0019505851755526658,
      "grad_norm": 0.30411669611930847,
      "learning_rate": 3e-05,
      "loss": 0.9926,
      "step": 3
    },
    {
      "epoch": 0.002600780234070221,
      "grad_norm": 0.29294437170028687,
      "learning_rate": 4e-05,
      "loss": 1.0576,
      "step": 4
    },
    {
      "epoch": 0.003250975292587776,
      "grad_norm": 0.2660481631755829,
      "learning_rate": 5e-05,
      "loss": 1.0194,
      "step": 5
    },
    {
      "epoch": 0.0039011703511053317,
      "grad_norm": 0.22930045425891876,
      "learning_rate": 6e-05,
      "loss": 1.0524,
      "step": 6
    },
    {
      "epoch": 0.004551365409622887,
      "grad_norm": 0.24841156601905823,
      "learning_rate": 7e-05,
      "loss": 0.9826,
      "step": 7
    },
    {
      "epoch": 0.005201560468140442,
      "grad_norm": 0.29712122678756714,
      "learning_rate": 8e-05,
      "loss": 0.9425,
      "step": 8
    },
    {
      "epoch": 0.005851755526657998,
      "grad_norm": 0.3075281083583832,
      "learning_rate": 9e-05,
      "loss": 1.0433,
      "step": 9
    },
    {
      "epoch": 0.006501950585175552,
      "grad_norm": 0.29364797472953796,
      "learning_rate": 0.0001,
      "loss": 0.9954,
      "step": 10
    },
    {
      "epoch": 0.007152145643693108,
      "grad_norm": 0.26937392354011536,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.047,
      "step": 11
    },
    {
      "epoch": 0.007802340702210663,
      "grad_norm": 0.2536260485649109,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0071,
      "step": 12
    },
    {
      "epoch": 0.008452535760728219,
      "grad_norm": 0.2693924307823181,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9835,
      "step": 13
    },
    {
      "epoch": 0.009102730819245773,
      "grad_norm": 0.2723298966884613,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9502,
      "step": 14
    },
    {
      "epoch": 0.00975292587776333,
      "grad_norm": 0.30060645937919617,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1353,
      "step": 15
    },
    {
      "epoch": 0.010403120936280884,
      "grad_norm": 0.2966339588165283,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0607,
      "step": 16
    },
    {
      "epoch": 0.011053315994798439,
      "grad_norm": 0.29817983508110046,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.0409,
      "step": 17
    },
    {
      "epoch": 0.011703511053315995,
      "grad_norm": 0.29946982860565186,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9976,
      "step": 18
    },
    {
      "epoch": 0.01235370611183355,
      "grad_norm": 0.31542253494262695,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0846,
      "step": 19
    },
    {
      "epoch": 0.013003901170351105,
      "grad_norm": 0.3208790719509125,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0423,
      "step": 20
    },
    {
      "epoch": 0.013654096228868661,
      "grad_norm": 0.3385937809944153,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9577,
      "step": 21
    },
    {
      "epoch": 0.014304291287386216,
      "grad_norm": 0.35345029830932617,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1097,
      "step": 22
    },
    {
      "epoch": 0.01495448634590377,
      "grad_norm": 0.3454449474811554,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9912,
      "step": 23
    },
    {
      "epoch": 0.015604681404421327,
      "grad_norm": 0.37376976013183594,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0444,
      "step": 24
    },
    {
      "epoch": 0.016254876462938883,
      "grad_norm": 0.40058329701423645,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0641,
      "step": 25
    },
    {
      "epoch": 0.016905071521456438,
      "grad_norm": 0.4044893682003021,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0345,
      "step": 26
    },
    {
      "epoch": 0.017555266579973992,
      "grad_norm": 0.4948595464229584,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.1932,
      "step": 27
    },
    {
      "epoch": 0.018205461638491547,
      "grad_norm": 0.4825793206691742,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.0423,
      "step": 28
    },
    {
      "epoch": 0.0188556566970091,
      "grad_norm": 0.4661653935909271,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9377,
      "step": 29
    },
    {
      "epoch": 0.01950585175552666,
      "grad_norm": 0.5018226504325867,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9872,
      "step": 30
    },
    {
      "epoch": 0.020156046814044214,
      "grad_norm": 0.5678668022155762,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2176,
      "step": 31
    },
    {
      "epoch": 0.02080624187256177,
      "grad_norm": 0.6238282918930054,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0809,
      "step": 32
    },
    {
      "epoch": 0.021456436931079324,
      "grad_norm": 0.6968820691108704,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.0575,
      "step": 33
    },
    {
      "epoch": 0.022106631989596878,
      "grad_norm": 0.6839820742607117,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0284,
      "step": 34
    },
    {
      "epoch": 0.022756827048114433,
      "grad_norm": 0.8115527629852295,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9048,
      "step": 35
    },
    {
      "epoch": 0.02340702210663199,
      "grad_norm": 0.9514137506484985,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.2285,
      "step": 36
    },
    {
      "epoch": 0.024057217165149546,
      "grad_norm": 0.9252752065658569,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0755,
      "step": 37
    },
    {
      "epoch": 0.0247074122236671,
      "grad_norm": 0.8530341386795044,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0974,
      "step": 38
    },
    {
      "epoch": 0.025357607282184655,
      "grad_norm": 1.0147374868392944,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9775,
      "step": 39
    },
    {
      "epoch": 0.02600780234070221,
      "grad_norm": 0.9851258397102356,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1015,
      "step": 40
    },
    {
      "epoch": 0.026657997399219768,
      "grad_norm": 0.9220011830329895,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9734,
      "step": 41
    },
    {
      "epoch": 0.027308192457737322,
      "grad_norm": 1.1411608457565308,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.895,
      "step": 42
    },
    {
      "epoch": 0.027958387516254877,
      "grad_norm": 1.1889772415161133,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0677,
      "step": 43
    },
    {
      "epoch": 0.02860858257477243,
      "grad_norm": 1.5893051624298096,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9913,
      "step": 44
    },
    {
      "epoch": 0.029258777633289986,
      "grad_norm": 1.3745660781860352,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9134,
      "step": 45
    },
    {
      "epoch": 0.02990897269180754,
      "grad_norm": 1.3050737380981445,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9877,
      "step": 46
    },
    {
      "epoch": 0.0305591677503251,
      "grad_norm": 1.6141232252120972,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9998,
      "step": 47
    },
    {
      "epoch": 0.031209362808842653,
      "grad_norm": 1.4593380689620972,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8818,
      "step": 48
    },
    {
      "epoch": 0.03185955786736021,
      "grad_norm": 2.6730148792266846,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0781,
      "step": 49
    },
    {
      "epoch": 0.032509752925877766,
      "grad_norm": 1.7183367013931274,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9071,
      "step": 50
    },
    {
      "epoch": 0.032509752925877766,
      "eval_loss": 1.054203987121582,
      "eval_runtime": 287.5454,
      "eval_samples_per_second": 9.011,
      "eval_steps_per_second": 2.254,
      "step": 50
    },
    {
      "epoch": 0.03315994798439532,
      "grad_norm": 0.3386886715888977,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0257,
      "step": 51
    },
    {
      "epoch": 0.033810143042912875,
      "grad_norm": 0.3361884355545044,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9614,
      "step": 52
    },
    {
      "epoch": 0.03446033810143043,
      "grad_norm": 0.3084128499031067,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0583,
      "step": 53
    },
    {
      "epoch": 0.035110533159947985,
      "grad_norm": 0.2674861550331116,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9485,
      "step": 54
    },
    {
      "epoch": 0.03576072821846554,
      "grad_norm": 0.24764272570610046,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.948,
      "step": 55
    },
    {
      "epoch": 0.036410923276983094,
      "grad_norm": 0.24586255848407745,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.0632,
      "step": 56
    },
    {
      "epoch": 0.03706111833550065,
      "grad_norm": 0.23815371096134186,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0403,
      "step": 57
    },
    {
      "epoch": 0.0377113133940182,
      "grad_norm": 0.24708771705627441,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9634,
      "step": 58
    },
    {
      "epoch": 0.03836150845253576,
      "grad_norm": 0.2594657242298126,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9434,
      "step": 59
    },
    {
      "epoch": 0.03901170351105332,
      "grad_norm": 0.2581363916397095,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.0236,
      "step": 60
    },
    {
      "epoch": 0.03966189856957087,
      "grad_norm": 0.28572535514831543,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0167,
      "step": 61
    },
    {
      "epoch": 0.04031209362808843,
      "grad_norm": 0.27552080154418945,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0812,
      "step": 62
    },
    {
      "epoch": 0.04096228868660598,
      "grad_norm": 0.2638622522354126,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0145,
      "step": 63
    },
    {
      "epoch": 0.04161248374512354,
      "grad_norm": 0.28032687306404114,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9644,
      "step": 64
    },
    {
      "epoch": 0.04226267880364109,
      "grad_norm": 0.2831994891166687,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0199,
      "step": 65
    },
    {
      "epoch": 0.04291287386215865,
      "grad_norm": 0.2876667380332947,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0307,
      "step": 66
    },
    {
      "epoch": 0.043563068920676205,
      "grad_norm": 0.30388614535331726,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0459,
      "step": 67
    },
    {
      "epoch": 0.044213263979193757,
      "grad_norm": 0.30665335059165955,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.005,
      "step": 68
    },
    {
      "epoch": 0.044863459037711315,
      "grad_norm": 0.3081737160682678,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9645,
      "step": 69
    },
    {
      "epoch": 0.045513654096228866,
      "grad_norm": 0.34367161989212036,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1134,
      "step": 70
    },
    {
      "epoch": 0.046163849154746424,
      "grad_norm": 0.3611394762992859,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0236,
      "step": 71
    },
    {
      "epoch": 0.04681404421326398,
      "grad_norm": 0.3540930449962616,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.015,
      "step": 72
    },
    {
      "epoch": 0.04746423927178153,
      "grad_norm": 0.3631446361541748,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0907,
      "step": 73
    },
    {
      "epoch": 0.04811443433029909,
      "grad_norm": 0.3827061057090759,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9582,
      "step": 74
    },
    {
      "epoch": 0.04876462938881664,
      "grad_norm": 0.37133488059043884,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9584,
      "step": 75
    },
    {
      "epoch": 0.0494148244473342,
      "grad_norm": 0.4201424717903137,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.1141,
      "step": 76
    },
    {
      "epoch": 0.05006501950585176,
      "grad_norm": 0.446561723947525,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.04,
      "step": 77
    },
    {
      "epoch": 0.05071521456436931,
      "grad_norm": 0.45327770709991455,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.911,
      "step": 78
    },
    {
      "epoch": 0.05136540962288687,
      "grad_norm": 0.488609254360199,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9535,
      "step": 79
    },
    {
      "epoch": 0.05201560468140442,
      "grad_norm": 0.5082444548606873,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.9659,
      "step": 80
    },
    {
      "epoch": 0.05266579973992198,
      "grad_norm": 0.5167144536972046,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8035,
      "step": 81
    },
    {
      "epoch": 0.053315994798439535,
      "grad_norm": 0.7916758060455322,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9813,
      "step": 82
    },
    {
      "epoch": 0.053966189856957086,
      "grad_norm": 0.6592386364936829,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9619,
      "step": 83
    },
    {
      "epoch": 0.054616384915474644,
      "grad_norm": 0.6843824982643127,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9291,
      "step": 84
    },
    {
      "epoch": 0.055266579973992196,
      "grad_norm": 0.7502142190933228,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9775,
      "step": 85
    },
    {
      "epoch": 0.055916775032509754,
      "grad_norm": 0.7345762252807617,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9682,
      "step": 86
    },
    {
      "epoch": 0.056566970091027305,
      "grad_norm": 1.0729334354400635,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1668,
      "step": 87
    },
    {
      "epoch": 0.05721716514954486,
      "grad_norm": 0.9465899467468262,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.066,
      "step": 88
    },
    {
      "epoch": 0.05786736020806242,
      "grad_norm": 0.8934149146080017,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0943,
      "step": 89
    },
    {
      "epoch": 0.05851755526657997,
      "grad_norm": 0.8732466101646423,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8848,
      "step": 90
    },
    {
      "epoch": 0.05916775032509753,
      "grad_norm": 1.4022270441055298,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0353,
      "step": 91
    },
    {
      "epoch": 0.05981794538361508,
      "grad_norm": 1.1805094480514526,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0968,
      "step": 92
    },
    {
      "epoch": 0.06046814044213264,
      "grad_norm": 1.171386957168579,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.967,
      "step": 93
    },
    {
      "epoch": 0.0611183355006502,
      "grad_norm": 1.0938076972961426,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.843,
      "step": 94
    },
    {
      "epoch": 0.06176853055916775,
      "grad_norm": 1.217340111732483,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.0096,
      "step": 95
    },
    {
      "epoch": 0.06241872561768531,
      "grad_norm": 1.255969762802124,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9087,
      "step": 96
    },
    {
      "epoch": 0.06306892067620286,
      "grad_norm": 1.2926132678985596,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8561,
      "step": 97
    },
    {
      "epoch": 0.06371911573472042,
      "grad_norm": 1.38904869556427,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8413,
      "step": 98
    },
    {
      "epoch": 0.06436931079323797,
      "grad_norm": 1.2619047164916992,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7125,
      "step": 99
    },
    {
      "epoch": 0.06501950585175553,
      "grad_norm": 1.9958139657974243,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9771,
      "step": 100
    },
    {
      "epoch": 0.06501950585175553,
      "eval_loss": 1.0209071636199951,
      "eval_runtime": 287.4426,
      "eval_samples_per_second": 9.014,
      "eval_steps_per_second": 2.254,
      "step": 100
    },
    {
      "epoch": 0.06566970091027308,
      "grad_norm": 0.28578314185142517,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9529,
      "step": 101
    },
    {
      "epoch": 0.06631989596879063,
      "grad_norm": 0.2959822416305542,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9612,
      "step": 102
    },
    {
      "epoch": 0.06697009102730819,
      "grad_norm": 0.3045414984226227,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.964,
      "step": 103
    },
    {
      "epoch": 0.06762028608582575,
      "grad_norm": 0.30599191784858704,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.0214,
      "step": 104
    },
    {
      "epoch": 0.06827048114434331,
      "grad_norm": 0.2823450565338135,
      "learning_rate": 5e-05,
      "loss": 0.9976,
      "step": 105
    },
    {
      "epoch": 0.06892067620286085,
      "grad_norm": 0.2601260840892792,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9564,
      "step": 106
    },
    {
      "epoch": 0.06957087126137841,
      "grad_norm": 0.25662875175476074,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0077,
      "step": 107
    },
    {
      "epoch": 0.07022106631989597,
      "grad_norm": 0.262192964553833,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.0157,
      "step": 108
    },
    {
      "epoch": 0.07087126137841353,
      "grad_norm": 0.24229338765144348,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9839,
      "step": 109
    },
    {
      "epoch": 0.07152145643693109,
      "grad_norm": 0.2540320158004761,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0461,
      "step": 110
    },
    {
      "epoch": 0.07217165149544863,
      "grad_norm": 0.24910147488117218,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9477,
      "step": 111
    },
    {
      "epoch": 0.07282184655396619,
      "grad_norm": 0.25390809774398804,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.0516,
      "step": 112
    },
    {
      "epoch": 0.07347204161248375,
      "grad_norm": 0.2431602030992508,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.951,
      "step": 113
    },
    {
      "epoch": 0.0741222366710013,
      "grad_norm": 0.2595900893211365,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9707,
      "step": 114
    },
    {
      "epoch": 0.07477243172951886,
      "grad_norm": 0.2788005471229553,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.0803,
      "step": 115
    },
    {
      "epoch": 0.0754226267880364,
      "grad_norm": 0.2638980746269226,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9675,
      "step": 116
    },
    {
      "epoch": 0.07607282184655396,
      "grad_norm": 0.28652435541152954,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.0481,
      "step": 117
    },
    {
      "epoch": 0.07672301690507152,
      "grad_norm": 0.30259060859680176,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.0613,
      "step": 118
    },
    {
      "epoch": 0.07737321196358908,
      "grad_norm": 0.30677303671836853,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.0147,
      "step": 119
    },
    {
      "epoch": 0.07802340702210664,
      "grad_norm": 0.3172067701816559,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.0589,
      "step": 120
    },
    {
      "epoch": 0.07867360208062418,
      "grad_norm": 0.34852272272109985,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9957,
      "step": 121
    },
    {
      "epoch": 0.07932379713914174,
      "grad_norm": 0.3528114855289459,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.0282,
      "step": 122
    },
    {
      "epoch": 0.0799739921976593,
      "grad_norm": 0.36736923456192017,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.0874,
      "step": 123
    },
    {
      "epoch": 0.08062418725617686,
      "grad_norm": 0.36461472511291504,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9643,
      "step": 124
    },
    {
      "epoch": 0.0812743823146944,
      "grad_norm": 0.3944953382015228,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1273,
      "step": 125
    },
    {
      "epoch": 0.08192457737321196,
      "grad_norm": 0.4044293165206909,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9938,
      "step": 126
    },
    {
      "epoch": 0.08257477243172952,
      "grad_norm": 0.4210696220397949,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9924,
      "step": 127
    },
    {
      "epoch": 0.08322496749024708,
      "grad_norm": 0.39872685074806213,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8994,
      "step": 128
    },
    {
      "epoch": 0.08387516254876463,
      "grad_norm": 0.45271793007850647,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9762,
      "step": 129
    },
    {
      "epoch": 0.08452535760728218,
      "grad_norm": 0.47246426343917847,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8418,
      "step": 130
    },
    {
      "epoch": 0.08517555266579974,
      "grad_norm": 0.5041539669036865,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.0256,
      "step": 131
    },
    {
      "epoch": 0.0858257477243173,
      "grad_norm": 0.5535305142402649,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.005,
      "step": 132
    },
    {
      "epoch": 0.08647594278283485,
      "grad_norm": 0.5784163475036621,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.9101,
      "step": 133
    },
    {
      "epoch": 0.08712613784135241,
      "grad_norm": 0.6768215894699097,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.0046,
      "step": 134
    },
    {
      "epoch": 0.08777633289986995,
      "grad_norm": 0.6812559366226196,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9294,
      "step": 135
    },
    {
      "epoch": 0.08842652795838751,
      "grad_norm": 0.6950148344039917,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.976,
      "step": 136
    },
    {
      "epoch": 0.08907672301690507,
      "grad_norm": 0.6829755902290344,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8025,
      "step": 137
    },
    {
      "epoch": 0.08972691807542263,
      "grad_norm": 0.8887941837310791,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0147,
      "step": 138
    },
    {
      "epoch": 0.09037711313394019,
      "grad_norm": 0.853938102722168,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.9148,
      "step": 139
    },
    {
      "epoch": 0.09102730819245773,
      "grad_norm": 0.9662453532218933,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0474,
      "step": 140
    },
    {
      "epoch": 0.09167750325097529,
      "grad_norm": 0.9367502927780151,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8101,
      "step": 141
    },
    {
      "epoch": 0.09232769830949285,
      "grad_norm": 0.881011426448822,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.781,
      "step": 142
    },
    {
      "epoch": 0.0929778933680104,
      "grad_norm": 0.9794203639030457,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9776,
      "step": 143
    },
    {
      "epoch": 0.09362808842652796,
      "grad_norm": 1.0850703716278076,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9974,
      "step": 144
    },
    {
      "epoch": 0.09427828348504551,
      "grad_norm": 0.9639971256256104,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7316,
      "step": 145
    },
    {
      "epoch": 0.09492847854356307,
      "grad_norm": 1.1075059175491333,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8347,
      "step": 146
    },
    {
      "epoch": 0.09557867360208062,
      "grad_norm": 1.1604466438293457,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6836,
      "step": 147
    },
    {
      "epoch": 0.09622886866059818,
      "grad_norm": 1.4200111627578735,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9519,
      "step": 148
    },
    {
      "epoch": 0.09687906371911574,
      "grad_norm": 1.2869455814361572,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.823,
      "step": 149
    },
    {
      "epoch": 0.09752925877763328,
      "grad_norm": 1.7294621467590332,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.7738,
      "step": 150
    },
    {
      "epoch": 0.09752925877763328,
      "eval_loss": 0.967810869216919,
      "eval_runtime": 287.4762,
      "eval_samples_per_second": 9.013,
      "eval_steps_per_second": 2.254,
      "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": 2.1363877497274368e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}