{
  "best_metric": 1.62236487865448,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0017317741593318816,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7317741593318815e-05,
      "grad_norm": 1.3246665000915527,
      "learning_rate": 4e-05,
      "loss": 1.6209,
      "step": 1
    },
    {
      "epoch": 1.7317741593318815e-05,
      "eval_loss": 2.6184682846069336,
      "eval_runtime": 4891.6495,
      "eval_samples_per_second": 4.971,
      "eval_steps_per_second": 2.485,
      "step": 1
    },
    {
      "epoch": 3.463548318663763e-05,
      "grad_norm": 1.7559422254562378,
      "learning_rate": 8e-05,
      "loss": 2.6328,
      "step": 2
    },
    {
      "epoch": 5.1953224779956444e-05,
      "grad_norm": 1.3109291791915894,
      "learning_rate": 0.00012,
      "loss": 1.8847,
      "step": 3
    },
    {
      "epoch": 6.927096637327526e-05,
      "grad_norm": 1.6149224042892456,
      "learning_rate": 0.00016,
      "loss": 2.4206,
      "step": 4
    },
    {
      "epoch": 8.658870796659407e-05,
      "grad_norm": 1.6735433340072632,
      "learning_rate": 0.0002,
      "loss": 2.4259,
      "step": 5
    },
    {
      "epoch": 0.00010390644955991289,
      "grad_norm": 1.4547559022903442,
      "learning_rate": 0.00019994532573409262,
      "loss": 1.7482,
      "step": 6
    },
    {
      "epoch": 0.0001212241911532317,
      "grad_norm": 1.628714919090271,
      "learning_rate": 0.00019978136272187747,
      "loss": 2.2129,
      "step": 7
    },
    {
      "epoch": 0.00013854193274655052,
      "grad_norm": 1.8027219772338867,
      "learning_rate": 0.00019950829025450114,
      "loss": 1.8543,
      "step": 8
    },
    {
      "epoch": 0.00015585967433986934,
      "grad_norm": 2.021082639694214,
      "learning_rate": 0.00019912640693269752,
      "loss": 2.0592,
      "step": 9
    },
    {
      "epoch": 0.00017317741593318815,
      "grad_norm": 2.312199115753174,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.055,
      "step": 10
    },
    {
      "epoch": 0.00019049515752650697,
      "grad_norm": 1.8753467798233032,
      "learning_rate": 0.00019803799658748094,
      "loss": 1.7057,
      "step": 11
    },
    {
      "epoch": 0.00020781289911982577,
      "grad_norm": 3.184194803237915,
      "learning_rate": 0.0001973326597248006,
      "loss": 2.1195,
      "step": 12
    },
    {
      "epoch": 0.0002251306407131446,
      "grad_norm": 2.2157609462738037,
      "learning_rate": 0.00019652089102773488,
      "loss": 1.6142,
      "step": 13
    },
    {
      "epoch": 0.0002424483823064634,
      "grad_norm": 1.8846286535263062,
      "learning_rate": 0.00019560357815343577,
      "loss": 1.6909,
      "step": 14
    },
    {
      "epoch": 0.00025976612389978223,
      "grad_norm": 1.8501865863800049,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.5635,
      "step": 15
    },
    {
      "epoch": 0.00027708386549310103,
      "grad_norm": 1.9967668056488037,
      "learning_rate": 0.0001934564464599461,
      "loss": 1.7519,
      "step": 16
    },
    {
      "epoch": 0.00029440160708641983,
      "grad_norm": 1.8826665878295898,
      "learning_rate": 0.00019222897549773848,
      "loss": 1.6652,
      "step": 17
    },
    {
      "epoch": 0.0003117193486797387,
      "grad_norm": 2.2450180053710938,
      "learning_rate": 0.00019090065350491626,
      "loss": 1.8715,
      "step": 18
    },
    {
      "epoch": 0.0003290370902730575,
      "grad_norm": 2.0638725757598877,
      "learning_rate": 0.00018947293298207635,
      "loss": 1.7423,
      "step": 19
    },
    {
      "epoch": 0.0003463548318663763,
      "grad_norm": 3.073434829711914,
      "learning_rate": 0.0001879473751206489,
      "loss": 2.1458,
      "step": 20
    },
    {
      "epoch": 0.00036367257345969515,
      "grad_norm": 1.9750235080718994,
      "learning_rate": 0.00018632564809575742,
      "loss": 1.6923,
      "step": 21
    },
    {
      "epoch": 0.00038099031505301395,
      "grad_norm": 2.1666667461395264,
      "learning_rate": 0.00018460952524209355,
      "loss": 1.6162,
      "step": 22
    },
    {
      "epoch": 0.00039830805664633275,
      "grad_norm": 1.9802206754684448,
      "learning_rate": 0.00018280088311480201,
      "loss": 1.6125,
      "step": 23
    },
    {
      "epoch": 0.00041562579823965155,
      "grad_norm": 1.9258074760437012,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.6174,
      "step": 24
    },
    {
      "epoch": 0.0004329435398329704,
      "grad_norm": 2.670494556427002,
      "learning_rate": 0.00017891405093963938,
      "loss": 2.1219,
      "step": 25
    },
    {
      "epoch": 0.0004329435398329704,
      "eval_loss": 1.7579680681228638,
      "eval_runtime": 4921.5904,
      "eval_samples_per_second": 4.94,
      "eval_steps_per_second": 2.47,
      "step": 25
    },
    {
      "epoch": 0.0004502612814262892,
      "grad_norm": 2.315001964569092,
      "learning_rate": 0.00017684011108568592,
      "loss": 1.9471,
      "step": 26
    },
    {
      "epoch": 0.000467579023019608,
      "grad_norm": 4.8373613357543945,
      "learning_rate": 0.0001746821476984154,
      "loss": 1.4014,
      "step": 27
    },
    {
      "epoch": 0.0004848967646129268,
      "grad_norm": 2.2539186477661133,
      "learning_rate": 0.00017244252047910892,
      "loss": 1.8659,
      "step": 28
    },
    {
      "epoch": 0.0005022145062062456,
      "grad_norm": 2.21065616607666,
      "learning_rate": 0.00017012367842724887,
      "loss": 1.8552,
      "step": 29
    },
    {
      "epoch": 0.0005195322477995645,
      "grad_norm": 2.3214337825775146,
      "learning_rate": 0.00016772815716257412,
      "loss": 2.0893,
      "step": 30
    },
    {
      "epoch": 0.0005368499893928833,
      "grad_norm": 2.827920436859131,
      "learning_rate": 0.00016525857615241687,
      "loss": 1.7269,
      "step": 31
    },
    {
      "epoch": 0.0005541677309862021,
      "grad_norm": 2.3385794162750244,
      "learning_rate": 0.0001627176358473537,
      "loss": 1.4844,
      "step": 32
    },
    {
      "epoch": 0.0005714854725795209,
      "grad_norm": 2.1411702632904053,
      "learning_rate": 0.00016010811472830252,
      "loss": 1.6424,
      "step": 33
    },
    {
      "epoch": 0.0005888032141728397,
      "grad_norm": 1.8949635028839111,
      "learning_rate": 0.00015743286626829437,
      "loss": 1.8416,
      "step": 34
    },
    {
      "epoch": 0.0006061209557661585,
      "grad_norm": 2.325913667678833,
      "learning_rate": 0.00015469481581224272,
      "loss": 1.9681,
      "step": 35
    },
    {
      "epoch": 0.0006234386973594774,
      "grad_norm": 2.5775182247161865,
      "learning_rate": 0.00015189695737812152,
      "loss": 2.0605,
      "step": 36
    },
    {
      "epoch": 0.0006407564389527961,
      "grad_norm": 2.1500771045684814,
      "learning_rate": 0.00014904235038305083,
      "loss": 1.7005,
      "step": 37
    },
    {
      "epoch": 0.000658074180546115,
      "grad_norm": 1.9176790714263916,
      "learning_rate": 0.0001461341162978688,
      "loss": 1.544,
      "step": 38
    },
    {
      "epoch": 0.0006753919221394338,
      "grad_norm": 5.9821248054504395,
      "learning_rate": 0.00014317543523384928,
      "loss": 1.5349,
      "step": 39
    },
    {
      "epoch": 0.0006927096637327526,
      "grad_norm": 1.723404049873352,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.4033,
      "step": 40
    },
    {
      "epoch": 0.0007100274053260714,
      "grad_norm": 2.131654739379883,
      "learning_rate": 0.00013711972489182208,
      "loss": 1.8816,
      "step": 41
    },
    {
      "epoch": 0.0007273451469193903,
      "grad_norm": 2.1149301528930664,
      "learning_rate": 0.00013402931744416433,
      "loss": 1.7547,
      "step": 42
    },
    {
      "epoch": 0.000744662888512709,
      "grad_norm": 2.1402599811553955,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4692,
      "step": 43
    },
    {
      "epoch": 0.0007619806301060279,
      "grad_norm": 2.189884662628174,
      "learning_rate": 0.00012774029087618446,
      "loss": 1.6887,
      "step": 44
    },
    {
      "epoch": 0.0007792983716993466,
      "grad_norm": 2.3986988067626953,
      "learning_rate": 0.00012454854871407994,
      "loss": 1.5637,
      "step": 45
    },
    {
      "epoch": 0.0007966161132926655,
      "grad_norm": 2.0756654739379883,
      "learning_rate": 0.0001213299630743747,
      "loss": 1.3412,
      "step": 46
    },
    {
      "epoch": 0.0008139338548859844,
      "grad_norm": 2.2220942974090576,
      "learning_rate": 0.000118088053433211,
      "loss": 1.9958,
      "step": 47
    },
    {
      "epoch": 0.0008312515964793031,
      "grad_norm": 2.2260262966156006,
      "learning_rate": 0.0001148263647711842,
      "loss": 1.8054,
      "step": 48
    },
    {
      "epoch": 0.000848569338072622,
      "grad_norm": 2.96877121925354,
      "learning_rate": 0.00011154846369695863,
      "loss": 1.7525,
      "step": 49
    },
    {
      "epoch": 0.0008658870796659408,
      "grad_norm": 2.6540238857269287,
      "learning_rate": 0.00010825793454723325,
      "loss": 1.731,
      "step": 50
    },
    {
      "epoch": 0.0008658870796659408,
      "eval_loss": 1.665256142616272,
      "eval_runtime": 4923.0054,
      "eval_samples_per_second": 4.939,
      "eval_steps_per_second": 2.469,
      "step": 50
    },
    {
      "epoch": 0.0008832048212592596,
      "grad_norm": 1.3105987310409546,
      "learning_rate": 0.00010495837546732224,
      "loss": 1.4402,
      "step": 51
    },
    {
      "epoch": 0.0009005225628525784,
      "grad_norm": 1.4101057052612305,
      "learning_rate": 0.00010165339447663587,
      "loss": 1.4313,
      "step": 52
    },
    {
      "epoch": 0.0009178403044458972,
      "grad_norm": 1.5237852334976196,
      "learning_rate": 9.834660552336415e-05,
      "loss": 1.7096,
      "step": 53
    },
    {
      "epoch": 0.000935158046039216,
      "grad_norm": 1.6052296161651611,
      "learning_rate": 9.504162453267777e-05,
      "loss": 1.4336,
      "step": 54
    },
    {
      "epoch": 0.0009524757876325349,
      "grad_norm": 1.7279136180877686,
      "learning_rate": 9.174206545276677e-05,
      "loss": 1.7388,
      "step": 55
    },
    {
      "epoch": 0.0009697935292258536,
      "grad_norm": 1.3830236196517944,
      "learning_rate": 8.845153630304139e-05,
      "loss": 1.2797,
      "step": 56
    },
    {
      "epoch": 0.0009871112708191726,
      "grad_norm": 2.031076669692993,
      "learning_rate": 8.517363522881579e-05,
      "loss": 1.9524,
      "step": 57
    },
    {
      "epoch": 0.0010044290124124912,
      "grad_norm": 1.437910556793213,
      "learning_rate": 8.191194656678904e-05,
      "loss": 1.4775,
      "step": 58
    },
    {
      "epoch": 0.00102174675400581,
      "grad_norm": 1.4608979225158691,
      "learning_rate": 7.867003692562534e-05,
      "loss": 1.4998,
      "step": 59
    },
    {
      "epoch": 0.001039064495599129,
      "grad_norm": 1.6951931715011597,
      "learning_rate": 7.54514512859201e-05,
      "loss": 1.8601,
      "step": 60
    },
    {
      "epoch": 0.0010563822371924478,
      "grad_norm": 1.654209852218628,
      "learning_rate": 7.225970912381556e-05,
      "loss": 1.8643,
      "step": 61
    },
    {
      "epoch": 0.0010736999787857666,
      "grad_norm": 1.837178349494934,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.7543,
      "step": 62
    },
    {
      "epoch": 0.0010910177203790853,
      "grad_norm": 1.8673418760299683,
      "learning_rate": 6.59706825558357e-05,
      "loss": 1.408,
      "step": 63
    },
    {
      "epoch": 0.0011083354619724041,
      "grad_norm": 1.660733938217163,
      "learning_rate": 6.28802751081779e-05,
      "loss": 1.6586,
      "step": 64
    },
    {
      "epoch": 0.001125653203565723,
      "grad_norm": 1.6716222763061523,
      "learning_rate": 5.983045753470308e-05,
      "loss": 1.7785,
      "step": 65
    },
    {
      "epoch": 0.0011429709451590418,
      "grad_norm": 1.4793193340301514,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 1.524,
      "step": 66
    },
    {
      "epoch": 0.0011602886867523607,
      "grad_norm": 1.4535232782363892,
      "learning_rate": 5.386588370213124e-05,
      "loss": 1.3191,
      "step": 67
    },
    {
      "epoch": 0.0011776064283456793,
      "grad_norm": 1.9624608755111694,
      "learning_rate": 5.095764961694922e-05,
      "loss": 1.5482,
      "step": 68
    },
    {
      "epoch": 0.0011949241699389982,
      "grad_norm": 1.7577117681503296,
      "learning_rate": 4.810304262187852e-05,
      "loss": 1.5874,
      "step": 69
    },
    {
      "epoch": 0.001212241911532317,
      "grad_norm": 1.5105639696121216,
      "learning_rate": 4.530518418775733e-05,
      "loss": 1.5703,
      "step": 70
    },
    {
      "epoch": 0.001229559653125636,
      "grad_norm": 1.529349446296692,
      "learning_rate": 4.256713373170564e-05,
      "loss": 1.1905,
      "step": 71
    },
    {
      "epoch": 0.0012468773947189548,
      "grad_norm": 1.8508775234222412,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 1.8208,
      "step": 72
    },
    {
      "epoch": 0.0012641951363122736,
      "grad_norm": 1.593199610710144,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 1.3999,
      "step": 73
    },
    {
      "epoch": 0.0012815128779055922,
      "grad_norm": 1.6738864183425903,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 1.4956,
      "step": 74
    },
    {
      "epoch": 0.001298830619498911,
      "grad_norm": 1.758865475654602,
      "learning_rate": 3.227184283742591e-05,
      "loss": 1.631,
      "step": 75
    },
    {
      "epoch": 0.001298830619498911,
      "eval_loss": 1.6363804340362549,
      "eval_runtime": 4921.7849,
      "eval_samples_per_second": 4.94,
      "eval_steps_per_second": 2.47,
      "step": 75
    },
    {
      "epoch": 0.00131614836109223,
      "grad_norm": 2.4752883911132812,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 2.0203,
      "step": 76
    },
    {
      "epoch": 0.0013334661026855488,
      "grad_norm": 2.1483538150787354,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 1.5806,
      "step": 77
    },
    {
      "epoch": 0.0013507838442788677,
      "grad_norm": 1.9293116331100464,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 2.0804,
      "step": 78
    },
    {
      "epoch": 0.0013681015858721863,
      "grad_norm": 1.519399881362915,
      "learning_rate": 2.315988891431412e-05,
      "loss": 1.4393,
      "step": 79
    },
    {
      "epoch": 0.0013854193274655052,
      "grad_norm": 1.9969561100006104,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 1.5912,
      "step": 80
    },
    {
      "epoch": 0.001402737069058824,
      "grad_norm": 1.9334006309509277,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.5095,
      "step": 81
    },
    {
      "epoch": 0.0014200548106521429,
      "grad_norm": 1.8917192220687866,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 1.8712,
      "step": 82
    },
    {
      "epoch": 0.0014373725522454617,
      "grad_norm": 1.6807430982589722,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 1.6938,
      "step": 83
    },
    {
      "epoch": 0.0014546902938387806,
      "grad_norm": 1.641627550125122,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 1.5532,
      "step": 84
    },
    {
      "epoch": 0.0014720080354320992,
      "grad_norm": 2.6051013469696045,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 1.8125,
      "step": 85
    },
    {
      "epoch": 0.001489325777025418,
      "grad_norm": 1.6829463243484497,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 1.5045,
      "step": 86
    },
    {
      "epoch": 0.001506643518618737,
      "grad_norm": 1.6704628467559814,
      "learning_rate": 9.09934649508375e-06,
      "loss": 1.5594,
      "step": 87
    },
    {
      "epoch": 0.0015239612602120558,
      "grad_norm": 2.3541147708892822,
      "learning_rate": 7.771024502261526e-06,
      "loss": 2.2284,
      "step": 88
    },
    {
      "epoch": 0.0015412790018053746,
      "grad_norm": 2.744718074798584,
      "learning_rate": 6.543553540053926e-06,
      "loss": 1.2474,
      "step": 89
    },
    {
      "epoch": 0.0015585967433986933,
      "grad_norm": 2.3282785415649414,
      "learning_rate": 5.418275829936537e-06,
      "loss": 1.9081,
      "step": 90
    },
    {
      "epoch": 0.0015759144849920121,
      "grad_norm": 1.7221317291259766,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 1.5467,
      "step": 91
    },
    {
      "epoch": 0.001593232226585331,
      "grad_norm": 2.2455320358276367,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 1.8693,
      "step": 92
    },
    {
      "epoch": 0.0016105499681786498,
      "grad_norm": 1.896304726600647,
      "learning_rate": 2.667340275199426e-06,
      "loss": 1.3848,
      "step": 93
    },
    {
      "epoch": 0.0016278677097719687,
      "grad_norm": 2.8605098724365234,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 1.6698,
      "step": 94
    },
    {
      "epoch": 0.0016451854513652876,
      "grad_norm": 1.6910480260849,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 1.4249,
      "step": 95
    },
    {
      "epoch": 0.0016625031929586062,
      "grad_norm": 3.1670644283294678,
      "learning_rate": 8.735930673024806e-07,
      "loss": 1.7864,
      "step": 96
    },
    {
      "epoch": 0.001679820934551925,
      "grad_norm": 2.209742784500122,
      "learning_rate": 4.917097454988584e-07,
      "loss": 1.7708,
      "step": 97
    },
    {
      "epoch": 0.001697138676145244,
      "grad_norm": 2.015029191970825,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 1.471,
      "step": 98
    },
    {
      "epoch": 0.0017144564177385628,
      "grad_norm": 2.405651569366455,
      "learning_rate": 5.467426590739511e-08,
      "loss": 1.6094,
      "step": 99
    },
    {
      "epoch": 0.0017317741593318816,
      "grad_norm": 4.6894025802612305,
      "learning_rate": 0.0,
      "loss": 2.0444,
      "step": 100
    },
    {
      "epoch": 0.0017317741593318816,
      "eval_loss": 1.62236487865448,
      "eval_runtime": 4922.5195,
      "eval_samples_per_second": 4.939,
      "eval_steps_per_second": 2.47,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 5.51427898343424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}