{
  "best_metric": 3.1820225715637207,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0014386263995137443,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4386263995137443e-05,
      "grad_norm": 3.251556158065796,
      "learning_rate": 4e-05,
      "loss": 3.8038,
      "step": 1
    },
    {
      "epoch": 1.4386263995137443e-05,
      "eval_loss": 7.7365922927856445,
      "eval_runtime": 10029.5031,
      "eval_samples_per_second": 2.918,
      "eval_steps_per_second": 1.459,
      "step": 1
    },
    {
      "epoch": 2.8772527990274885e-05,
      "grad_norm": 5.66372013092041,
      "learning_rate": 8e-05,
      "loss": 6.4359,
      "step": 2
    },
    {
      "epoch": 4.3158791985412326e-05,
      "grad_norm": 7.8616108894348145,
      "learning_rate": 0.00012,
      "loss": 6.1656,
      "step": 3
    },
    {
      "epoch": 5.754505598054977e-05,
      "grad_norm": 5.461581707000732,
      "learning_rate": 0.00016,
      "loss": 5.6581,
      "step": 4
    },
    {
      "epoch": 7.193131997568721e-05,
      "grad_norm": 6.099221229553223,
      "learning_rate": 0.0002,
      "loss": 5.1573,
      "step": 5
    },
    {
      "epoch": 8.631758397082465e-05,
      "grad_norm": 7.90977144241333,
      "learning_rate": 0.00019994532573409262,
      "loss": 5.2319,
      "step": 6
    },
    {
      "epoch": 0.0001007038479659621,
      "grad_norm": 6.142984390258789,
      "learning_rate": 0.00019978136272187747,
      "loss": 4.4226,
      "step": 7
    },
    {
      "epoch": 0.00011509011196109954,
      "grad_norm": 7.399872779846191,
      "learning_rate": 0.00019950829025450114,
      "loss": 5.3465,
      "step": 8
    },
    {
      "epoch": 0.00012947637595623699,
      "grad_norm": 6.89127254486084,
      "learning_rate": 0.00019912640693269752,
      "loss": 4.0349,
      "step": 9
    },
    {
      "epoch": 0.00014386263995137442,
      "grad_norm": 7.014307022094727,
      "learning_rate": 0.00019863613034027224,
      "loss": 4.8762,
      "step": 10
    },
    {
      "epoch": 0.00015824890394651187,
      "grad_norm": 6.281440734863281,
      "learning_rate": 0.00019803799658748094,
      "loss": 3.8366,
      "step": 11
    },
    {
      "epoch": 0.0001726351679416493,
      "grad_norm": 6.824883460998535,
      "learning_rate": 0.0001973326597248006,
      "loss": 3.7482,
      "step": 12
    },
    {
      "epoch": 0.00018702143193678676,
      "grad_norm": 6.548895359039307,
      "learning_rate": 0.00019652089102773488,
      "loss": 3.7988,
      "step": 13
    },
    {
      "epoch": 0.0002014076959319242,
      "grad_norm": 8.689468383789062,
      "learning_rate": 0.00019560357815343577,
      "loss": 5.0917,
      "step": 14
    },
    {
      "epoch": 0.00021579395992706165,
      "grad_norm": 9.284707069396973,
      "learning_rate": 0.00019458172417006347,
      "loss": 4.096,
      "step": 15
    },
    {
      "epoch": 0.00023018022392219908,
      "grad_norm": 9.370043754577637,
      "learning_rate": 0.0001934564464599461,
      "loss": 4.165,
      "step": 16
    },
    {
      "epoch": 0.0002445664879173365,
      "grad_norm": 7.626341819763184,
      "learning_rate": 0.00019222897549773848,
      "loss": 3.4382,
      "step": 17
    },
    {
      "epoch": 0.00025895275191247397,
      "grad_norm": 7.837584018707275,
      "learning_rate": 0.00019090065350491626,
      "loss": 4.7504,
      "step": 18
    },
    {
      "epoch": 0.00027333901590761143,
      "grad_norm": 9.203110694885254,
      "learning_rate": 0.00018947293298207635,
      "loss": 3.8969,
      "step": 19
    },
    {
      "epoch": 0.00028772527990274883,
      "grad_norm": 6.96456241607666,
      "learning_rate": 0.0001879473751206489,
      "loss": 3.205,
      "step": 20
    },
    {
      "epoch": 0.0003021115438978863,
      "grad_norm": 7.325512886047363,
      "learning_rate": 0.00018632564809575742,
      "loss": 4.6357,
      "step": 21
    },
    {
      "epoch": 0.00031649780789302375,
      "grad_norm": 8.572059631347656,
      "learning_rate": 0.00018460952524209355,
      "loss": 3.5764,
      "step": 22
    },
    {
      "epoch": 0.0003308840718881612,
      "grad_norm": 10.509377479553223,
      "learning_rate": 0.00018280088311480201,
      "loss": 3.5955,
      "step": 23
    },
    {
      "epoch": 0.0003452703358832986,
      "grad_norm": 9.667518615722656,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.3657,
      "step": 24
    },
    {
      "epoch": 0.00035965659987843607,
      "grad_norm": 10.283529281616211,
      "learning_rate": 0.00017891405093963938,
      "loss": 3.2434,
      "step": 25
    },
    {
      "epoch": 0.00035965659987843607,
      "eval_loss": 3.63478946685791,
      "eval_runtime": 10117.2577,
      "eval_samples_per_second": 2.893,
      "eval_steps_per_second": 1.446,
      "step": 25
    },
    {
      "epoch": 0.0003740428638735735,
      "grad_norm": 7.642445087432861,
      "learning_rate": 0.00017684011108568592,
      "loss": 3.6013,
      "step": 26
    },
    {
      "epoch": 0.00038842912786871093,
      "grad_norm": 6.486288547515869,
      "learning_rate": 0.0001746821476984154,
      "loss": 3.2864,
      "step": 27
    },
    {
      "epoch": 0.0004028153918638484,
      "grad_norm": 9.71819019317627,
      "learning_rate": 0.00017244252047910892,
      "loss": 3.5647,
      "step": 28
    },
    {
      "epoch": 0.00041720165585898585,
      "grad_norm": 10.292891502380371,
      "learning_rate": 0.00017012367842724887,
      "loss": 3.8624,
      "step": 29
    },
    {
      "epoch": 0.0004315879198541233,
      "grad_norm": 8.131758689880371,
      "learning_rate": 0.00016772815716257412,
      "loss": 2.9685,
      "step": 30
    },
    {
      "epoch": 0.0004459741838492607,
      "grad_norm": 8.162099838256836,
      "learning_rate": 0.00016525857615241687,
      "loss": 2.1483,
      "step": 31
    },
    {
      "epoch": 0.00046036044784439817,
      "grad_norm": 8.644756317138672,
      "learning_rate": 0.0001627176358473537,
      "loss": 3.4542,
      "step": 32
    },
    {
      "epoch": 0.0004747467118395356,
      "grad_norm": 10.966817855834961,
      "learning_rate": 0.00016010811472830252,
      "loss": 3.3133,
      "step": 33
    },
    {
      "epoch": 0.000489132975834673,
      "grad_norm": 13.345026969909668,
      "learning_rate": 0.00015743286626829437,
      "loss": 3.5618,
      "step": 34
    },
    {
      "epoch": 0.0005035192398298105,
      "grad_norm": 8.088078498840332,
      "learning_rate": 0.00015469481581224272,
      "loss": 3.0519,
      "step": 35
    },
    {
      "epoch": 0.0005179055038249479,
      "grad_norm": 9.461556434631348,
      "learning_rate": 0.00015189695737812152,
      "loss": 3.9405,
      "step": 36
    },
    {
      "epoch": 0.0005322917678200853,
      "grad_norm": 8.484424591064453,
      "learning_rate": 0.00014904235038305083,
      "loss": 3.0565,
      "step": 37
    },
    {
      "epoch": 0.0005466780318152229,
      "grad_norm": 11.633894920349121,
      "learning_rate": 0.0001461341162978688,
      "loss": 3.368,
      "step": 38
    },
    {
      "epoch": 0.0005610642958103603,
      "grad_norm": 9.127283096313477,
      "learning_rate": 0.00014317543523384928,
      "loss": 3.241,
      "step": 39
    },
    {
      "epoch": 0.0005754505598054977,
      "grad_norm": 10.992538452148438,
      "learning_rate": 0.00014016954246529696,
      "loss": 4.4219,
      "step": 40
    },
    {
      "epoch": 0.0005898368238006352,
      "grad_norm": 13.77578067779541,
      "learning_rate": 0.00013711972489182208,
      "loss": 3.6872,
      "step": 41
    },
    {
      "epoch": 0.0006042230877957726,
      "grad_norm": 8.236401557922363,
      "learning_rate": 0.00013402931744416433,
      "loss": 3.6752,
      "step": 42
    },
    {
      "epoch": 0.00061860935179091,
      "grad_norm": 6.068155288696289,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.6444,
      "step": 43
    },
    {
      "epoch": 0.0006329956157860475,
      "grad_norm": 8.862524032592773,
      "learning_rate": 0.00012774029087618446,
      "loss": 2.5672,
      "step": 44
    },
    {
      "epoch": 0.0006473818797811849,
      "grad_norm": 8.178911209106445,
      "learning_rate": 0.00012454854871407994,
      "loss": 3.0123,
      "step": 45
    },
    {
      "epoch": 0.0006617681437763224,
      "grad_norm": 8.450122833251953,
      "learning_rate": 0.0001213299630743747,
      "loss": 3.3182,
      "step": 46
    },
    {
      "epoch": 0.0006761544077714598,
      "grad_norm": 8.23652458190918,
      "learning_rate": 0.000118088053433211,
      "loss": 3.7808,
      "step": 47
    },
    {
      "epoch": 0.0006905406717665972,
      "grad_norm": 7.568443775177002,
      "learning_rate": 0.0001148263647711842,
      "loss": 3.0745,
      "step": 48
    },
    {
      "epoch": 0.0007049269357617347,
      "grad_norm": 10.986652374267578,
      "learning_rate": 0.00011154846369695863,
      "loss": 3.2082,
      "step": 49
    },
    {
      "epoch": 0.0007193131997568721,
      "grad_norm": 13.982491493225098,
      "learning_rate": 0.00010825793454723325,
      "loss": 3.8151,
      "step": 50
    },
    {
      "epoch": 0.0007193131997568721,
      "eval_loss": 3.4786899089813232,
      "eval_runtime": 10121.4453,
      "eval_samples_per_second": 2.892,
      "eval_steps_per_second": 1.446,
      "step": 50
    },
    {
      "epoch": 0.0007336994637520095,
      "grad_norm": 8.999927520751953,
      "learning_rate": 0.00010495837546732224,
      "loss": 2.9427,
      "step": 51
    },
    {
      "epoch": 0.000748085727747147,
      "grad_norm": 12.779885292053223,
      "learning_rate": 0.00010165339447663587,
      "loss": 3.1953,
      "step": 52
    },
    {
      "epoch": 0.0007624719917422845,
      "grad_norm": 7.076213836669922,
      "learning_rate": 9.834660552336415e-05,
      "loss": 3.3286,
      "step": 53
    },
    {
      "epoch": 0.0007768582557374219,
      "grad_norm": 8.078849792480469,
      "learning_rate": 9.504162453267777e-05,
      "loss": 3.7154,
      "step": 54
    },
    {
      "epoch": 0.0007912445197325594,
      "grad_norm": 12.962296485900879,
      "learning_rate": 9.174206545276677e-05,
      "loss": 3.3829,
      "step": 55
    },
    {
      "epoch": 0.0008056307837276968,
      "grad_norm": 6.32912015914917,
      "learning_rate": 8.845153630304139e-05,
      "loss": 2.8261,
      "step": 56
    },
    {
      "epoch": 0.0008200170477228343,
      "grad_norm": 6.619338035583496,
      "learning_rate": 8.517363522881579e-05,
      "loss": 3.0182,
      "step": 57
    },
    {
      "epoch": 0.0008344033117179717,
      "grad_norm": 6.766091346740723,
      "learning_rate": 8.191194656678904e-05,
      "loss": 3.5953,
      "step": 58
    },
    {
      "epoch": 0.0008487895757131091,
      "grad_norm": 5.642858505249023,
      "learning_rate": 7.867003692562534e-05,
      "loss": 2.6085,
      "step": 59
    },
    {
      "epoch": 0.0008631758397082466,
      "grad_norm": 5.088937759399414,
      "learning_rate": 7.54514512859201e-05,
      "loss": 3.0031,
      "step": 60
    },
    {
      "epoch": 0.000877562103703384,
      "grad_norm": 6.179854869842529,
      "learning_rate": 7.225970912381556e-05,
      "loss": 3.0115,
      "step": 61
    },
    {
      "epoch": 0.0008919483676985214,
      "grad_norm": 6.379157543182373,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.9728,
      "step": 62
    },
    {
      "epoch": 0.0009063346316936589,
      "grad_norm": 6.963946342468262,
      "learning_rate": 6.59706825558357e-05,
      "loss": 3.1727,
      "step": 63
    },
    {
      "epoch": 0.0009207208956887963,
      "grad_norm": 5.228279113769531,
      "learning_rate": 6.28802751081779e-05,
      "loss": 3.2701,
      "step": 64
    },
    {
      "epoch": 0.0009351071596839337,
      "grad_norm": 6.0718488693237305,
      "learning_rate": 5.983045753470308e-05,
      "loss": 3.1534,
      "step": 65
    },
    {
      "epoch": 0.0009494934236790712,
      "grad_norm": 5.688898086547852,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 3.2423,
      "step": 66
    },
    {
      "epoch": 0.0009638796876742087,
      "grad_norm": 6.626285076141357,
      "learning_rate": 5.386588370213124e-05,
      "loss": 2.8435,
      "step": 67
    },
    {
      "epoch": 0.000978265951669346,
      "grad_norm": 5.733967304229736,
      "learning_rate": 5.095764961694922e-05,
      "loss": 3.2189,
      "step": 68
    },
    {
      "epoch": 0.0009926522156644836,
      "grad_norm": 8.272422790527344,
      "learning_rate": 4.810304262187852e-05,
      "loss": 4.0563,
      "step": 69
    },
    {
      "epoch": 0.001007038479659621,
      "grad_norm": 5.926618576049805,
      "learning_rate": 4.530518418775733e-05,
      "loss": 3.0186,
      "step": 70
    },
    {
      "epoch": 0.0010214247436547584,
      "grad_norm": 5.379611015319824,
      "learning_rate": 4.256713373170564e-05,
      "loss": 3.0911,
      "step": 71
    },
    {
      "epoch": 0.0010358110076498959,
      "grad_norm": 6.168915748596191,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 2.9903,
      "step": 72
    },
    {
      "epoch": 0.0010501972716450334,
      "grad_norm": 8.017834663391113,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 3.4968,
      "step": 73
    },
    {
      "epoch": 0.0010645835356401707,
      "grad_norm": 6.804283142089844,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 3.0869,
      "step": 74
    },
    {
      "epoch": 0.0010789697996353082,
      "grad_norm": 5.8104658126831055,
      "learning_rate": 3.227184283742591e-05,
      "loss": 3.1871,
      "step": 75
    },
    {
      "epoch": 0.0010789697996353082,
      "eval_loss": 3.277400493621826,
      "eval_runtime": 10118.7756,
      "eval_samples_per_second": 2.892,
      "eval_steps_per_second": 1.446,
      "step": 75
    },
    {
      "epoch": 0.0010933560636304457,
      "grad_norm": 5.396302223205566,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 2.4818,
      "step": 76
    },
    {
      "epoch": 0.001107742327625583,
      "grad_norm": 4.9067301750183105,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 2.6765,
      "step": 77
    },
    {
      "epoch": 0.0011221285916207205,
      "grad_norm": 5.162796497344971,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 2.6254,
      "step": 78
    },
    {
      "epoch": 0.001136514855615858,
      "grad_norm": 5.922882556915283,
      "learning_rate": 2.315988891431412e-05,
      "loss": 3.3523,
      "step": 79
    },
    {
      "epoch": 0.0011509011196109953,
      "grad_norm": 5.30287504196167,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 3.2716,
      "step": 80
    },
    {
      "epoch": 0.0011652873836061328,
      "grad_norm": 5.643162250518799,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.5917,
      "step": 81
    },
    {
      "epoch": 0.0011796736476012704,
      "grad_norm": 9.638242721557617,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 3.8924,
      "step": 82
    },
    {
      "epoch": 0.0011940599115964077,
      "grad_norm": 7.516237735748291,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 3.5587,
      "step": 83
    },
    {
      "epoch": 0.0012084461755915452,
      "grad_norm": 7.148532867431641,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 2.6055,
      "step": 84
    },
    {
      "epoch": 0.0012228324395866827,
      "grad_norm": 6.535606384277344,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 2.5346,
      "step": 85
    },
    {
      "epoch": 0.00123721870358182,
      "grad_norm": 7.571803569793701,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 2.7083,
      "step": 86
    },
    {
      "epoch": 0.0012516049675769575,
      "grad_norm": 7.3511881828308105,
      "learning_rate": 9.09934649508375e-06,
      "loss": 3.5115,
      "step": 87
    },
    {
      "epoch": 0.001265991231572095,
      "grad_norm": 6.102956771850586,
      "learning_rate": 7.771024502261526e-06,
      "loss": 3.0957,
      "step": 88
    },
    {
      "epoch": 0.0012803774955672325,
      "grad_norm": 7.065240859985352,
      "learning_rate": 6.543553540053926e-06,
      "loss": 2.9476,
      "step": 89
    },
    {
      "epoch": 0.0012947637595623698,
      "grad_norm": 10.024836540222168,
      "learning_rate": 5.418275829936537e-06,
      "loss": 4.0562,
      "step": 90
    },
    {
      "epoch": 0.0013091500235575073,
      "grad_norm": 6.252835750579834,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 3.0513,
      "step": 91
    },
    {
      "epoch": 0.0013235362875526448,
      "grad_norm": 8.234208106994629,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 3.3823,
      "step": 92
    },
    {
      "epoch": 0.0013379225515477821,
      "grad_norm": 8.580864906311035,
      "learning_rate": 2.667340275199426e-06,
      "loss": 3.2553,
      "step": 93
    },
    {
      "epoch": 0.0013523088155429196,
      "grad_norm": 9.852059364318848,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 4.1037,
      "step": 94
    },
    {
      "epoch": 0.0013666950795380571,
      "grad_norm": 15.760644912719727,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 2.7196,
      "step": 95
    },
    {
      "epoch": 0.0013810813435331944,
      "grad_norm": 8.547517776489258,
      "learning_rate": 8.735930673024806e-07,
      "loss": 3.8778,
      "step": 96
    },
    {
      "epoch": 0.001395467607528332,
      "grad_norm": 9.558707237243652,
      "learning_rate": 4.917097454988584e-07,
      "loss": 3.362,
      "step": 97
    },
    {
      "epoch": 0.0014098538715234695,
      "grad_norm": 6.9549455642700195,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 2.8635,
      "step": 98
    },
    {
      "epoch": 0.0014242401355186068,
      "grad_norm": 11.047368049621582,
      "learning_rate": 5.467426590739511e-08,
      "loss": 3.9017,
      "step": 99
    },
    {
      "epoch": 0.0014386263995137443,
      "grad_norm": 10.734683990478516,
      "learning_rate": 0.0,
      "loss": 3.2839,
      "step": 100
    },
    {
      "epoch": 0.0014386263995137443,
      "eval_loss": 3.1820225715637207,
      "eval_runtime": 10123.1923,
      "eval_samples_per_second": 2.891,
      "eval_steps_per_second": 1.446,
      "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": 1.403578937769984e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}