{
  "best_metric": 0.12525896728038788,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.018264840182648,
  "eval_steps": 25,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 5.516948699951172,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 6.9436,
      "step": 1
    },
    {
      "epoch": 0.0182648401826484,
      "eval_loss": 2.470696210861206,
      "eval_runtime": 3.3615,
      "eval_samples_per_second": 14.874,
      "eval_steps_per_second": 2.082,
      "step": 1
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 6.3923020362854,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 8.2395,
      "step": 2
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 7.493215560913086,
      "learning_rate": 8.999999999999999e-05,
      "loss": 8.8171,
      "step": 3
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 6.273920059204102,
      "learning_rate": 0.00011999999999999999,
      "loss": 8.226,
      "step": 4
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 10.592157363891602,
      "learning_rate": 0.00015,
      "loss": 7.53,
      "step": 5
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 9.920427322387695,
      "learning_rate": 0.00017999999999999998,
      "loss": 7.9559,
      "step": 6
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 7.29619836807251,
      "learning_rate": 0.00020999999999999998,
      "loss": 6.8911,
      "step": 7
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 7.143266201019287,
      "learning_rate": 0.00023999999999999998,
      "loss": 6.2679,
      "step": 8
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 9.101966857910156,
      "learning_rate": 0.00027,
      "loss": 5.7364,
      "step": 9
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 9.976201057434082,
      "learning_rate": 0.0003,
      "loss": 5.0311,
      "step": 10
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 9.90187931060791,
      "learning_rate": 0.0002999259840548597,
      "loss": 3.6094,
      "step": 11
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 14.418813705444336,
      "learning_rate": 0.0002997040092642407,
      "loss": 2.6951,
      "step": 12
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 11.6867094039917,
      "learning_rate": 0.000299334294690462,
      "loss": 1.4153,
      "step": 13
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 19.670818328857422,
      "learning_rate": 0.0002988172051971717,
      "loss": 2.9618,
      "step": 14
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 7.9418044090271,
      "learning_rate": 0.00029815325108927063,
      "loss": 1.7467,
      "step": 15
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 4.048381805419922,
      "learning_rate": 0.0002973430876093033,
      "loss": 1.1227,
      "step": 16
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 4.352411270141602,
      "learning_rate": 0.0002963875142908121,
      "loss": 0.887,
      "step": 17
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 3.2712793350219727,
      "learning_rate": 0.00029528747416929463,
      "loss": 0.7917,
      "step": 18
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 3.5658321380615234,
      "learning_rate": 0.0002940440528515414,
      "loss": 0.8631,
      "step": 19
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 2.2600252628326416,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.6248,
      "step": 20
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 3.6815826892852783,
      "learning_rate": 0.0002911321153431338,
      "loss": 0.7136,
      "step": 21
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 2.6013550758361816,
      "learning_rate": 0.00028946647288323766,
      "loss": 0.54,
      "step": 22
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 5.8350043296813965,
      "learning_rate": 0.00028766319385259713,
      "loss": 0.8035,
      "step": 23
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 29.41618537902832,
      "learning_rate": 0.00028572405786990294,
      "loss": 1.2182,
      "step": 24
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 18.41824722290039,
      "learning_rate": 0.00028365097862825513,
      "loss": 1.031,
      "step": 25
    },
    {
      "epoch": 0.45662100456621,
      "eval_loss": 0.21980659663677216,
      "eval_runtime": 3.4137,
      "eval_samples_per_second": 14.647,
      "eval_steps_per_second": 2.051,
      "step": 25
    },
    {
      "epoch": 0.4748858447488584,
      "grad_norm": 8.772796630859375,
      "learning_rate": 0.0002814460020065795,
      "loss": 0.8542,
      "step": 26
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 12.31684398651123,
      "learning_rate": 0.0002791113040505915,
      "loss": 1.0956,
      "step": 27
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 5.33599853515625,
      "learning_rate": 0.00027664918882530225,
      "loss": 0.9314,
      "step": 28
    },
    {
      "epoch": 0.5296803652968036,
      "grad_norm": 2.71724534034729,
      "learning_rate": 0.00027406208614118424,
      "loss": 0.715,
      "step": 29
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 3.253049850463867,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.6381,
      "step": 30
    },
    {
      "epoch": 0.5662100456621004,
      "grad_norm": 1.2586455345153809,
      "learning_rate": 0.00026852325185635354,
      "loss": 0.54,
      "step": 31
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 1.543694257736206,
      "learning_rate": 0.00026557698641636835,
      "loss": 0.5199,
      "step": 32
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 1.3013904094696045,
      "learning_rate": 0.0002625166604445689,
      "loss": 0.5086,
      "step": 33
    },
    {
      "epoch": 0.6210045662100456,
      "grad_norm": 1.0573995113372803,
      "learning_rate": 0.0002593452941132117,
      "loss": 0.4737,
      "step": 34
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 1.4775699377059937,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.5643,
      "step": 35
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 3.0288829803466797,
      "learning_rate": 0.0002526820658893033,
      "loss": 0.6765,
      "step": 36
    },
    {
      "epoch": 0.6757990867579908,
      "grad_norm": 3.3613500595092773,
      "learning_rate": 0.00024919677979854776,
      "loss": 1.127,
      "step": 37
    },
    {
      "epoch": 0.6940639269406392,
      "grad_norm": 3.1534173488616943,
      "learning_rate": 0.0002456135984623034,
      "loss": 1.0773,
      "step": 38
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 3.1169755458831787,
      "learning_rate": 0.00024193605804794646,
      "loss": 0.7896,
      "step": 39
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 1.863209843635559,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.567,
      "step": 40
    },
    {
      "epoch": 0.7488584474885844,
      "grad_norm": 1.6382339000701904,
      "learning_rate": 0.00023431250667781958,
      "loss": 0.6118,
      "step": 41
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 1.7901109457015991,
      "learning_rate": 0.00023037401924684946,
      "loss": 0.5655,
      "step": 42
    },
    {
      "epoch": 0.7853881278538812,
      "grad_norm": 2.449873685836792,
      "learning_rate": 0.00022635621236255567,
      "loss": 0.5795,
      "step": 43
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 2.9242568016052246,
      "learning_rate": 0.00022226305111525726,
      "loss": 0.5427,
      "step": 44
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 1.5985544919967651,
      "learning_rate": 0.00021809857496093199,
      "loss": 0.4842,
      "step": 45
    },
    {
      "epoch": 0.8401826484018264,
      "grad_norm": 1.5843843221664429,
      "learning_rate": 0.00021386689373476087,
      "loss": 0.5753,
      "step": 46
    },
    {
      "epoch": 0.8584474885844748,
      "grad_norm": 20.6035213470459,
      "learning_rate": 0.00020957218359521706,
      "loss": 0.6594,
      "step": 47
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 2.7331109046936035,
      "learning_rate": 0.0002052186829027017,
      "loss": 0.6428,
      "step": 48
    },
    {
      "epoch": 0.8949771689497716,
      "grad_norm": 2.2731661796569824,
      "learning_rate": 0.00020081068803679371,
      "loss": 0.6238,
      "step": 49
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 2.2776832580566406,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.6169,
      "step": 50
    },
    {
      "epoch": 0.91324200913242,
      "eval_loss": 0.1614273190498352,
      "eval_runtime": 3.4091,
      "eval_samples_per_second": 14.666,
      "eval_steps_per_second": 2.053,
      "step": 50
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 2.19893741607666,
      "learning_rate": 0.00019184866590588439,
      "loss": 0.7239,
      "step": 51
    },
    {
      "epoch": 0.9497716894977168,
      "grad_norm": 2.0520899295806885,
      "learning_rate": 0.00018730348307472824,
      "loss": 0.6,
      "step": 52
    },
    {
      "epoch": 0.9680365296803652,
      "grad_norm": 1.9806722402572632,
      "learning_rate": 0.0001827214862094814,
      "loss": 0.7017,
      "step": 53
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 3.993856906890869,
      "learning_rate": 0.0001781071971878587,
      "loss": 0.9841,
      "step": 54
    },
    {
      "epoch": 1.009132420091324,
      "grad_norm": 1.4181034564971924,
      "learning_rate": 0.00017346516975603462,
      "loss": 0.5512,
      "step": 55
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 1.4350292682647705,
      "learning_rate": 0.00016879998503464561,
      "loss": 0.5089,
      "step": 56
    },
    {
      "epoch": 1.045662100456621,
      "grad_norm": 4.159196853637695,
      "learning_rate": 0.00016411624699777717,
      "loss": 0.5528,
      "step": 57
    },
    {
      "epoch": 1.0639269406392695,
      "grad_norm": 1.3114010095596313,
      "learning_rate": 0.000159418577929397,
      "loss": 0.4571,
      "step": 58
    },
    {
      "epoch": 1.0821917808219177,
      "grad_norm": 1.4728926420211792,
      "learning_rate": 0.00015471161386171922,
      "loss": 0.5557,
      "step": 59
    },
    {
      "epoch": 1.1004566210045663,
      "grad_norm": 1.4644254446029663,
      "learning_rate": 0.00015,
      "loss": 0.442,
      "step": 60
    },
    {
      "epoch": 1.1187214611872145,
      "grad_norm": 1.3919850587844849,
      "learning_rate": 0.00014528838613828076,
      "loss": 0.5105,
      "step": 61
    },
    {
      "epoch": 1.1369863013698631,
      "grad_norm": 1.4340811967849731,
      "learning_rate": 0.000140581422070603,
      "loss": 0.4391,
      "step": 62
    },
    {
      "epoch": 1.1552511415525113,
      "grad_norm": 2.5181379318237305,
      "learning_rate": 0.00013588375300222283,
      "loss": 0.6491,
      "step": 63
    },
    {
      "epoch": 1.17351598173516,
      "grad_norm": 6.064093112945557,
      "learning_rate": 0.00013120001496535433,
      "loss": 0.8979,
      "step": 64
    },
    {
      "epoch": 1.191780821917808,
      "grad_norm": 2.5452799797058105,
      "learning_rate": 0.00012653483024396533,
      "loss": 0.7953,
      "step": 65
    },
    {
      "epoch": 1.2100456621004567,
      "grad_norm": 3.304936647415161,
      "learning_rate": 0.00012189280281214126,
      "loss": 0.925,
      "step": 66
    },
    {
      "epoch": 1.228310502283105,
      "grad_norm": 3.181483745574951,
      "learning_rate": 0.00011727851379051865,
      "loss": 0.9497,
      "step": 67
    },
    {
      "epoch": 1.2465753424657535,
      "grad_norm": 1.3087420463562012,
      "learning_rate": 0.0001126965169252718,
      "loss": 0.5897,
      "step": 68
    },
    {
      "epoch": 1.2648401826484017,
      "grad_norm": 0.7273179888725281,
      "learning_rate": 0.00010815133409411562,
      "loss": 0.3759,
      "step": 69
    },
    {
      "epoch": 1.2831050228310503,
      "grad_norm": 1.104803442955017,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.4504,
      "step": 70
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.9511451125144958,
      "learning_rate": 9.918931196320629e-05,
      "loss": 0.4821,
      "step": 71
    },
    {
      "epoch": 1.3196347031963471,
      "grad_norm": 0.8015011548995972,
      "learning_rate": 9.47813170972983e-05,
      "loss": 0.5017,
      "step": 72
    },
    {
      "epoch": 1.3378995433789953,
      "grad_norm": 0.999840497970581,
      "learning_rate": 9.042781640478291e-05,
      "loss": 0.5061,
      "step": 73
    },
    {
      "epoch": 1.356164383561644,
      "grad_norm": 1.2065320014953613,
      "learning_rate": 8.613310626523909e-05,
      "loss": 0.5695,
      "step": 74
    },
    {
      "epoch": 1.374429223744292,
      "grad_norm": 0.9272903203964233,
      "learning_rate": 8.190142503906798e-05,
      "loss": 0.5145,
      "step": 75
    },
    {
      "epoch": 1.374429223744292,
      "eval_loss": 0.1285880208015442,
      "eval_runtime": 3.4101,
      "eval_samples_per_second": 14.662,
      "eval_steps_per_second": 2.053,
      "step": 75
    },
    {
      "epoch": 1.3926940639269407,
      "grad_norm": 1.0205509662628174,
      "learning_rate": 7.773694888474267e-05,
      "loss": 0.558,
      "step": 76
    },
    {
      "epoch": 1.410958904109589,
      "grad_norm": 0.7290596961975098,
      "learning_rate": 7.364378763744429e-05,
      "loss": 0.5247,
      "step": 77
    },
    {
      "epoch": 1.4292237442922375,
      "grad_norm": 1.1354948282241821,
      "learning_rate": 6.962598075315046e-05,
      "loss": 0.5803,
      "step": 78
    },
    {
      "epoch": 1.4474885844748857,
      "grad_norm": 1.6320542097091675,
      "learning_rate": 6.568749332218044e-05,
      "loss": 0.6953,
      "step": 79
    },
    {
      "epoch": 1.4657534246575343,
      "grad_norm": 2.266536235809326,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.8087,
      "step": 80
    },
    {
      "epoch": 1.4840182648401825,
      "grad_norm": 1.3406983613967896,
      "learning_rate": 5.806394195205356e-05,
      "loss": 0.5684,
      "step": 81
    },
    {
      "epoch": 1.5022831050228311,
      "grad_norm": 0.8310356736183167,
      "learning_rate": 5.4386401537696536e-05,
      "loss": 0.3706,
      "step": 82
    },
    {
      "epoch": 1.5205479452054793,
      "grad_norm": 0.6109088659286499,
      "learning_rate": 5.080322020145224e-05,
      "loss": 0.4452,
      "step": 83
    },
    {
      "epoch": 1.538812785388128,
      "grad_norm": 0.797944188117981,
      "learning_rate": 4.7317934110696685e-05,
      "loss": 0.4388,
      "step": 84
    },
    {
      "epoch": 1.5570776255707761,
      "grad_norm": 0.48338568210601807,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.4493,
      "step": 85
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.8341657519340515,
      "learning_rate": 4.06547058867883e-05,
      "loss": 0.4436,
      "step": 86
    },
    {
      "epoch": 1.593607305936073,
      "grad_norm": 0.9702841639518738,
      "learning_rate": 3.7483339555431055e-05,
      "loss": 0.4903,
      "step": 87
    },
    {
      "epoch": 1.6118721461187215,
      "grad_norm": 0.7687260508537292,
      "learning_rate": 3.442301358363163e-05,
      "loss": 0.4799,
      "step": 88
    },
    {
      "epoch": 1.6301369863013697,
      "grad_norm": 0.8309193849563599,
      "learning_rate": 3.1476748143646435e-05,
      "loss": 0.5022,
      "step": 89
    },
    {
      "epoch": 1.6484018264840183,
      "grad_norm": 1.1130985021591187,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.5636,
      "step": 90
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.946800708770752,
      "learning_rate": 2.5937913858815708e-05,
      "loss": 0.5647,
      "step": 91
    },
    {
      "epoch": 1.6849315068493151,
      "grad_norm": 1.5327059030532837,
      "learning_rate": 2.335081117469777e-05,
      "loss": 0.6487,
      "step": 92
    },
    {
      "epoch": 1.7031963470319633,
      "grad_norm": 1.5970087051391602,
      "learning_rate": 2.0888695949408468e-05,
      "loss": 0.6578,
      "step": 93
    },
    {
      "epoch": 1.721461187214612,
      "grad_norm": 0.8410404920578003,
      "learning_rate": 1.8553997993420495e-05,
      "loss": 0.4998,
      "step": 94
    },
    {
      "epoch": 1.7397260273972601,
      "grad_norm": 0.6193436980247498,
      "learning_rate": 1.634902137174483e-05,
      "loss": 0.3661,
      "step": 95
    },
    {
      "epoch": 1.7579908675799087,
      "grad_norm": 0.6613103747367859,
      "learning_rate": 1.4275942130097096e-05,
      "loss": 0.4159,
      "step": 96
    },
    {
      "epoch": 1.776255707762557,
      "grad_norm": 0.6441118717193604,
      "learning_rate": 1.2336806147402828e-05,
      "loss": 0.4134,
      "step": 97
    },
    {
      "epoch": 1.7945205479452055,
      "grad_norm": 0.4714259207248688,
      "learning_rate": 1.0533527116762296e-05,
      "loss": 0.4379,
      "step": 98
    },
    {
      "epoch": 1.8127853881278537,
      "grad_norm": 0.8632249236106873,
      "learning_rate": 8.867884656866181e-06,
      "loss": 0.453,
      "step": 99
    },
    {
      "epoch": 1.8310502283105023,
      "grad_norm": 0.6782150268554688,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.4734,
      "step": 100
    },
    {
      "epoch": 1.8310502283105023,
      "eval_loss": 0.12525896728038788,
      "eval_runtime": 3.4138,
      "eval_samples_per_second": 14.646,
      "eval_steps_per_second": 2.05,
      "step": 100
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.7789422273635864,
      "learning_rate": 5.95594714845854e-06,
      "loss": 0.4551,
      "step": 101
    },
    {
      "epoch": 1.8675799086757991,
      "grad_norm": 0.9181280732154846,
      "learning_rate": 4.712525830705338e-06,
      "loss": 0.4778,
      "step": 102
    },
    {
      "epoch": 1.8858447488584473,
      "grad_norm": 0.6837835311889648,
      "learning_rate": 3.6124857091878845e-06,
      "loss": 0.4939,
      "step": 103
    },
    {
      "epoch": 1.904109589041096,
      "grad_norm": 0.522508978843689,
      "learning_rate": 2.656912390696708e-06,
      "loss": 0.5255,
      "step": 104
    },
    {
      "epoch": 1.9223744292237441,
      "grad_norm": 1.1073154211044312,
      "learning_rate": 1.8467489107293509e-06,
      "loss": 0.6029,
      "step": 105
    },
    {
      "epoch": 1.9406392694063928,
      "grad_norm": 1.4917099475860596,
      "learning_rate": 1.1827948028283352e-06,
      "loss": 0.6545,
      "step": 106
    },
    {
      "epoch": 1.958904109589041,
      "grad_norm": 0.9225929379463196,
      "learning_rate": 6.657053095380005e-07,
      "loss": 0.5178,
      "step": 107
    },
    {
      "epoch": 1.9771689497716896,
      "grad_norm": 0.7463716864585876,
      "learning_rate": 2.959907357592661e-07,
      "loss": 0.4391,
      "step": 108
    },
    {
      "epoch": 1.9954337899543377,
      "grad_norm": 0.6585250496864319,
      "learning_rate": 7.401594514025999e-08,
      "loss": 0.5468,
      "step": 109
    },
    {
      "epoch": 2.018264840182648,
      "grad_norm": 0.6586726307868958,
      "learning_rate": 0.0,
      "loss": 0.3368,
      "step": 110
    }
  ],
  "logging_steps": 1,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.5274585469485056e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}