{
  "best_metric": 0.004337400663644075,
  "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": 0.8473725318908691,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.7975,
      "step": 1
    },
    {
      "epoch": 0.0182648401826484,
      "eval_loss": 1.8122729063034058,
      "eval_runtime": 3.8568,
      "eval_samples_per_second": 12.964,
      "eval_steps_per_second": 1.815,
      "step": 1
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.9350575804710388,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.764,
      "step": 2
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.995567798614502,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.0446,
      "step": 3
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 1.407714605331421,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.0893,
      "step": 4
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 1.8826767206192017,
      "learning_rate": 0.00015,
      "loss": 2.7079,
      "step": 5
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 1.0161590576171875,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.9996,
      "step": 6
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 1.010097861289978,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.9585,
      "step": 7
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 1.0560206174850464,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.7454,
      "step": 8
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 1.162116527557373,
      "learning_rate": 0.00027,
      "loss": 1.6178,
      "step": 9
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 1.4233083724975586,
      "learning_rate": 0.0003,
      "loss": 1.5871,
      "step": 10
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 1.7879890203475952,
      "learning_rate": 0.0002999259840548597,
      "loss": 1.364,
      "step": 11
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 1.9744043350219727,
      "learning_rate": 0.0002997040092642407,
      "loss": 1.3302,
      "step": 12
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 2.14997935295105,
      "learning_rate": 0.000299334294690462,
      "loss": 1.1676,
      "step": 13
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 2.865056037902832,
      "learning_rate": 0.0002988172051971717,
      "loss": 1.179,
      "step": 14
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 2.2772552967071533,
      "learning_rate": 0.00029815325108927063,
      "loss": 1.0101,
      "step": 15
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 1.7772722244262695,
      "learning_rate": 0.0002973430876093033,
      "loss": 0.924,
      "step": 16
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 1.6902390718460083,
      "learning_rate": 0.0002963875142908121,
      "loss": 0.8714,
      "step": 17
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 1.3245774507522583,
      "learning_rate": 0.00029528747416929463,
      "loss": 0.849,
      "step": 18
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 1.3994680643081665,
      "learning_rate": 0.0002940440528515414,
      "loss": 0.6922,
      "step": 19
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 1.3206199407577515,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.6246,
      "step": 20
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 1.5602670907974243,
      "learning_rate": 0.0002911321153431338,
      "loss": 0.4424,
      "step": 21
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 1.6248738765716553,
      "learning_rate": 0.00028946647288323766,
      "loss": 0.3231,
      "step": 22
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 2.217292547225952,
      "learning_rate": 0.00028766319385259713,
      "loss": 0.4047,
      "step": 23
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 1.8803366422653198,
      "learning_rate": 0.00028572405786990294,
      "loss": 0.2903,
      "step": 24
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 2.2177164554595947,
      "learning_rate": 0.00028365097862825513,
      "loss": 0.2043,
      "step": 25
    },
    {
      "epoch": 0.45662100456621,
      "eval_loss": 0.2833889126777649,
      "eval_runtime": 3.4109,
      "eval_samples_per_second": 14.659,
      "eval_steps_per_second": 2.052,
      "step": 25
    },
    {
      "epoch": 0.4748858447488584,
      "grad_norm": 2.0055646896362305,
      "learning_rate": 0.0002814460020065795,
      "loss": 0.1663,
      "step": 26
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 6.125588893890381,
      "learning_rate": 0.0002791113040505915,
      "loss": 0.4882,
      "step": 27
    },
    {
      "epoch": 0.5114155251141552,
      "grad_norm": 2.6787264347076416,
      "learning_rate": 0.00027664918882530225,
      "loss": 0.267,
      "step": 28
    },
    {
      "epoch": 0.5296803652968036,
      "grad_norm": 2.423906087875366,
      "learning_rate": 0.00027406208614118424,
      "loss": 0.2878,
      "step": 29
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 2.6322414875030518,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.3463,
      "step": 30
    },
    {
      "epoch": 0.5662100456621004,
      "grad_norm": 2.0104191303253174,
      "learning_rate": 0.00026852325185635354,
      "loss": 0.2524,
      "step": 31
    },
    {
      "epoch": 0.5844748858447488,
      "grad_norm": 1.3756883144378662,
      "learning_rate": 0.00026557698641636835,
      "loss": 0.1495,
      "step": 32
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 1.8245288133621216,
      "learning_rate": 0.0002625166604445689,
      "loss": 0.1895,
      "step": 33
    },
    {
      "epoch": 0.6210045662100456,
      "grad_norm": 1.0265326499938965,
      "learning_rate": 0.0002593452941132117,
      "loss": 0.0832,
      "step": 34
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.7454352378845215,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.06,
      "step": 35
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.8095255494117737,
      "learning_rate": 0.0002526820658893033,
      "loss": 0.064,
      "step": 36
    },
    {
      "epoch": 0.6757990867579908,
      "grad_norm": 0.7397829294204712,
      "learning_rate": 0.00024919677979854776,
      "loss": 0.0462,
      "step": 37
    },
    {
      "epoch": 0.6940639269406392,
      "grad_norm": 0.965843915939331,
      "learning_rate": 0.0002456135984623034,
      "loss": 0.048,
      "step": 38
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": 0.4619573652744293,
      "learning_rate": 0.00024193605804794646,
      "loss": 0.02,
      "step": 39
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 1.6063387393951416,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.1591,
      "step": 40
    },
    {
      "epoch": 0.7488584474885844,
      "grad_norm": 1.861398696899414,
      "learning_rate": 0.00023431250667781958,
      "loss": 0.144,
      "step": 41
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 2.341588258743286,
      "learning_rate": 0.00023037401924684946,
      "loss": 0.1565,
      "step": 42
    },
    {
      "epoch": 0.7853881278538812,
      "grad_norm": 1.8141049146652222,
      "learning_rate": 0.00022635621236255567,
      "loss": 0.1546,
      "step": 43
    },
    {
      "epoch": 0.8036529680365296,
      "grad_norm": 2.6451475620269775,
      "learning_rate": 0.00022226305111525726,
      "loss": 0.1163,
      "step": 44
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.9599330425262451,
      "learning_rate": 0.00021809857496093199,
      "loss": 0.0565,
      "step": 45
    },
    {
      "epoch": 0.8401826484018264,
      "grad_norm": 0.49869561195373535,
      "learning_rate": 0.00021386689373476087,
      "loss": 0.0417,
      "step": 46
    },
    {
      "epoch": 0.8584474885844748,
      "grad_norm": 0.35756292939186096,
      "learning_rate": 0.00020957218359521706,
      "loss": 0.0231,
      "step": 47
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.629383385181427,
      "learning_rate": 0.0002052186829027017,
      "loss": 0.0203,
      "step": 48
    },
    {
      "epoch": 0.8949771689497716,
      "grad_norm": 0.6143040060997009,
      "learning_rate": 0.00020081068803679371,
      "loss": 0.0258,
      "step": 49
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.9527487754821777,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.0326,
      "step": 50
    },
    {
      "epoch": 0.91324200913242,
      "eval_loss": 0.03938543424010277,
      "eval_runtime": 3.9802,
      "eval_samples_per_second": 12.562,
      "eval_steps_per_second": 1.759,
      "step": 50
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": 0.7113423347473145,
      "learning_rate": 0.00019184866590588439,
      "loss": 0.0168,
      "step": 51
    },
    {
      "epoch": 0.9497716894977168,
      "grad_norm": 0.3350503742694855,
      "learning_rate": 0.00018730348307472824,
      "loss": 0.0141,
      "step": 52
    },
    {
      "epoch": 0.9680365296803652,
      "grad_norm": 0.6726917624473572,
      "learning_rate": 0.0001827214862094814,
      "loss": 0.0454,
      "step": 53
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.31374573707580566,
      "learning_rate": 0.0001781071971878587,
      "loss": 0.0138,
      "step": 54
    },
    {
      "epoch": 1.009132420091324,
      "grad_norm": 0.6686992049217224,
      "learning_rate": 0.00017346516975603462,
      "loss": 0.032,
      "step": 55
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 0.4239481985569,
      "learning_rate": 0.00016879998503464561,
      "loss": 0.0243,
      "step": 56
    },
    {
      "epoch": 1.045662100456621,
      "grad_norm": 0.2905505895614624,
      "learning_rate": 0.00016411624699777717,
      "loss": 0.0159,
      "step": 57
    },
    {
      "epoch": 1.0639269406392695,
      "grad_norm": 2.1741881370544434,
      "learning_rate": 0.000159418577929397,
      "loss": 0.0303,
      "step": 58
    },
    {
      "epoch": 1.0821917808219177,
      "grad_norm": 0.6694914102554321,
      "learning_rate": 0.00015471161386171922,
      "loss": 0.0176,
      "step": 59
    },
    {
      "epoch": 1.1004566210045663,
      "grad_norm": 0.4211752414703369,
      "learning_rate": 0.00015,
      "loss": 0.0112,
      "step": 60
    },
    {
      "epoch": 1.1187214611872145,
      "grad_norm": 1.0037997961044312,
      "learning_rate": 0.00014528838613828076,
      "loss": 0.0202,
      "step": 61
    },
    {
      "epoch": 1.1369863013698631,
      "grad_norm": 0.20127694308757782,
      "learning_rate": 0.000140581422070603,
      "loss": 0.0052,
      "step": 62
    },
    {
      "epoch": 1.1552511415525113,
      "grad_norm": 0.32008397579193115,
      "learning_rate": 0.00013588375300222283,
      "loss": 0.0052,
      "step": 63
    },
    {
      "epoch": 1.17351598173516,
      "grad_norm": 0.1412021666765213,
      "learning_rate": 0.00013120001496535433,
      "loss": 0.0028,
      "step": 64
    },
    {
      "epoch": 1.191780821917808,
      "grad_norm": 0.8715978860855103,
      "learning_rate": 0.00012653483024396533,
      "loss": 0.0081,
      "step": 65
    },
    {
      "epoch": 1.2100456621004567,
      "grad_norm": 0.14639712870121002,
      "learning_rate": 0.00012189280281214126,
      "loss": 0.0029,
      "step": 66
    },
    {
      "epoch": 1.228310502283105,
      "grad_norm": 0.020685512572526932,
      "learning_rate": 0.00011727851379051865,
      "loss": 0.001,
      "step": 67
    },
    {
      "epoch": 1.2465753424657535,
      "grad_norm": 0.3620803952217102,
      "learning_rate": 0.0001126965169252718,
      "loss": 0.0172,
      "step": 68
    },
    {
      "epoch": 1.2648401826484017,
      "grad_norm": 0.3493403494358063,
      "learning_rate": 0.00010815133409411562,
      "loss": 0.0116,
      "step": 69
    },
    {
      "epoch": 1.2831050228310503,
      "grad_norm": 0.19864076375961304,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.0067,
      "step": 70
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 0.4525580406188965,
      "learning_rate": 9.918931196320629e-05,
      "loss": 0.0112,
      "step": 71
    },
    {
      "epoch": 1.3196347031963471,
      "grad_norm": 0.36928990483283997,
      "learning_rate": 9.47813170972983e-05,
      "loss": 0.0154,
      "step": 72
    },
    {
      "epoch": 1.3378995433789953,
      "grad_norm": 0.3303503394126892,
      "learning_rate": 9.042781640478291e-05,
      "loss": 0.0088,
      "step": 73
    },
    {
      "epoch": 1.356164383561644,
      "grad_norm": 0.1237182691693306,
      "learning_rate": 8.613310626523909e-05,
      "loss": 0.0046,
      "step": 74
    },
    {
      "epoch": 1.374429223744292,
      "grad_norm": 0.10325484722852707,
      "learning_rate": 8.190142503906798e-05,
      "loss": 0.0028,
      "step": 75
    },
    {
      "epoch": 1.374429223744292,
      "eval_loss": 0.006142734084278345,
      "eval_runtime": 3.4169,
      "eval_samples_per_second": 14.633,
      "eval_steps_per_second": 2.049,
      "step": 75
    },
    {
      "epoch": 1.3926940639269407,
      "grad_norm": 0.2936699688434601,
      "learning_rate": 7.773694888474267e-05,
      "loss": 0.0047,
      "step": 76
    },
    {
      "epoch": 1.410958904109589,
      "grad_norm": 0.04170661419630051,
      "learning_rate": 7.364378763744429e-05,
      "loss": 0.0015,
      "step": 77
    },
    {
      "epoch": 1.4292237442922375,
      "grad_norm": 0.04328185319900513,
      "learning_rate": 6.962598075315046e-05,
      "loss": 0.0011,
      "step": 78
    },
    {
      "epoch": 1.4474885844748857,
      "grad_norm": 0.11742109060287476,
      "learning_rate": 6.568749332218044e-05,
      "loss": 0.0015,
      "step": 79
    },
    {
      "epoch": 1.4657534246575343,
      "grad_norm": 0.029690410941839218,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.0009,
      "step": 80
    },
    {
      "epoch": 1.4840182648401825,
      "grad_norm": 0.5141183733940125,
      "learning_rate": 5.806394195205356e-05,
      "loss": 0.0079,
      "step": 81
    },
    {
      "epoch": 1.5022831050228311,
      "grad_norm": 0.0738927498459816,
      "learning_rate": 5.4386401537696536e-05,
      "loss": 0.0036,
      "step": 82
    },
    {
      "epoch": 1.5205479452054793,
      "grad_norm": 0.3400103747844696,
      "learning_rate": 5.080322020145224e-05,
      "loss": 0.0093,
      "step": 83
    },
    {
      "epoch": 1.538812785388128,
      "grad_norm": 0.16344979405403137,
      "learning_rate": 4.7317934110696685e-05,
      "loss": 0.005,
      "step": 84
    },
    {
      "epoch": 1.5570776255707761,
      "grad_norm": 0.17904306948184967,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.0033,
      "step": 85
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 0.0942436158657074,
      "learning_rate": 4.06547058867883e-05,
      "loss": 0.0069,
      "step": 86
    },
    {
      "epoch": 1.593607305936073,
      "grad_norm": 0.144642174243927,
      "learning_rate": 3.7483339555431055e-05,
      "loss": 0.0046,
      "step": 87
    },
    {
      "epoch": 1.6118721461187215,
      "grad_norm": 0.27809712290763855,
      "learning_rate": 3.442301358363163e-05,
      "loss": 0.003,
      "step": 88
    },
    {
      "epoch": 1.6301369863013697,
      "grad_norm": 0.021354489028453827,
      "learning_rate": 3.1476748143646435e-05,
      "loss": 0.0012,
      "step": 89
    },
    {
      "epoch": 1.6484018264840183,
      "grad_norm": 0.019089965149760246,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.001,
      "step": 90
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0716283917427063,
      "learning_rate": 2.5937913858815708e-05,
      "loss": 0.0012,
      "step": 91
    },
    {
      "epoch": 1.6849315068493151,
      "grad_norm": 0.012859423644840717,
      "learning_rate": 2.335081117469777e-05,
      "loss": 0.0007,
      "step": 92
    },
    {
      "epoch": 1.7031963470319633,
      "grad_norm": 0.07900480180978775,
      "learning_rate": 2.0888695949408468e-05,
      "loss": 0.0011,
      "step": 93
    },
    {
      "epoch": 1.721461187214612,
      "grad_norm": 0.06209683418273926,
      "learning_rate": 1.8553997993420495e-05,
      "loss": 0.0023,
      "step": 94
    },
    {
      "epoch": 1.7397260273972601,
      "grad_norm": 0.08779767155647278,
      "learning_rate": 1.634902137174483e-05,
      "loss": 0.0038,
      "step": 95
    },
    {
      "epoch": 1.7579908675799087,
      "grad_norm": 0.10400469601154327,
      "learning_rate": 1.4275942130097096e-05,
      "loss": 0.0042,
      "step": 96
    },
    {
      "epoch": 1.776255707762557,
      "grad_norm": 0.06363116204738617,
      "learning_rate": 1.2336806147402828e-05,
      "loss": 0.0019,
      "step": 97
    },
    {
      "epoch": 1.7945205479452055,
      "grad_norm": 0.08082360029220581,
      "learning_rate": 1.0533527116762296e-05,
      "loss": 0.0018,
      "step": 98
    },
    {
      "epoch": 1.8127853881278537,
      "grad_norm": 0.060259874910116196,
      "learning_rate": 8.867884656866181e-06,
      "loss": 0.0024,
      "step": 99
    },
    {
      "epoch": 1.8310502283105023,
      "grad_norm": 0.08836295455694199,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 1.8310502283105023,
      "eval_loss": 0.004337400663644075,
      "eval_runtime": 3.4882,
      "eval_samples_per_second": 14.334,
      "eval_steps_per_second": 2.007,
      "step": 100
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 0.026043424382805824,
      "learning_rate": 5.95594714845854e-06,
      "loss": 0.0015,
      "step": 101
    },
    {
      "epoch": 1.8675799086757991,
      "grad_norm": 0.05837749317288399,
      "learning_rate": 4.712525830705338e-06,
      "loss": 0.0033,
      "step": 102
    },
    {
      "epoch": 1.8858447488584473,
      "grad_norm": 1.0614242553710938,
      "learning_rate": 3.6124857091878845e-06,
      "loss": 0.0117,
      "step": 103
    },
    {
      "epoch": 1.904109589041096,
      "grad_norm": 0.020967742428183556,
      "learning_rate": 2.656912390696708e-06,
      "loss": 0.001,
      "step": 104
    },
    {
      "epoch": 1.9223744292237441,
      "grad_norm": 0.08478910475969315,
      "learning_rate": 1.8467489107293509e-06,
      "loss": 0.0009,
      "step": 105
    },
    {
      "epoch": 1.9406392694063928,
      "grad_norm": 0.028337517753243446,
      "learning_rate": 1.1827948028283352e-06,
      "loss": 0.0007,
      "step": 106
    },
    {
      "epoch": 1.958904109589041,
      "grad_norm": 1.1033185720443726,
      "learning_rate": 6.657053095380005e-07,
      "loss": 0.0129,
      "step": 107
    },
    {
      "epoch": 1.9771689497716896,
      "grad_norm": 0.06699586659669876,
      "learning_rate": 2.959907357592661e-07,
      "loss": 0.0026,
      "step": 108
    },
    {
      "epoch": 1.9954337899543377,
      "grad_norm": 0.02767285704612732,
      "learning_rate": 7.401594514025999e-08,
      "loss": 0.0019,
      "step": 109
    },
    {
      "epoch": 2.018264840182648,
      "grad_norm": 0.1497020125389099,
      "learning_rate": 0.0,
      "loss": 0.0052,
      "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": 2.878974644453376e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}