{
  "best_metric": 0.6224383115768433,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.14641288433382138,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014641288433382138,
      "grad_norm": 0.9750430583953857,
      "learning_rate": 4e-05,
      "loss": 1.0625,
      "step": 1
    },
    {
      "epoch": 0.0014641288433382138,
      "eval_loss": 1.124760389328003,
      "eval_runtime": 76.9259,
      "eval_samples_per_second": 3.744,
      "eval_steps_per_second": 1.872,
      "step": 1
    },
    {
      "epoch": 0.0029282576866764276,
      "grad_norm": 1.0913565158843994,
      "learning_rate": 8e-05,
      "loss": 1.0917,
      "step": 2
    },
    {
      "epoch": 0.004392386530014641,
      "grad_norm": 1.0702697038650513,
      "learning_rate": 0.00012,
      "loss": 1.0758,
      "step": 3
    },
    {
      "epoch": 0.005856515373352855,
      "grad_norm": 1.0503638982772827,
      "learning_rate": 0.00016,
      "loss": 1.0126,
      "step": 4
    },
    {
      "epoch": 0.007320644216691069,
      "grad_norm": 1.3807379007339478,
      "learning_rate": 0.0002,
      "loss": 0.9423,
      "step": 5
    },
    {
      "epoch": 0.008784773060029283,
      "grad_norm": 1.5241297483444214,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.9538,
      "step": 6
    },
    {
      "epoch": 0.010248901903367497,
      "grad_norm": 1.7318557500839233,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.8408,
      "step": 7
    },
    {
      "epoch": 0.01171303074670571,
      "grad_norm": 1.2110615968704224,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.8412,
      "step": 8
    },
    {
      "epoch": 0.013177159590043924,
      "grad_norm": 0.9903315901756287,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.8473,
      "step": 9
    },
    {
      "epoch": 0.014641288433382138,
      "grad_norm": 0.8798181414604187,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.8267,
      "step": 10
    },
    {
      "epoch": 0.016105417276720352,
      "grad_norm": 0.9941743016242981,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.8427,
      "step": 11
    },
    {
      "epoch": 0.017569546120058566,
      "grad_norm": 0.9219509959220886,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.7463,
      "step": 12
    },
    {
      "epoch": 0.01903367496339678,
      "grad_norm": 0.8963194489479065,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.8373,
      "step": 13
    },
    {
      "epoch": 0.020497803806734993,
      "grad_norm": 0.9019066691398621,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.754,
      "step": 14
    },
    {
      "epoch": 0.021961932650073207,
      "grad_norm": 1.0534106492996216,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.7813,
      "step": 15
    },
    {
      "epoch": 0.02342606149341142,
      "grad_norm": 0.8860576152801514,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.7497,
      "step": 16
    },
    {
      "epoch": 0.024890190336749635,
      "grad_norm": 0.9496033191680908,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.6888,
      "step": 17
    },
    {
      "epoch": 0.02635431918008785,
      "grad_norm": 0.9020019173622131,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.7641,
      "step": 18
    },
    {
      "epoch": 0.027818448023426062,
      "grad_norm": 0.8967961668968201,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.75,
      "step": 19
    },
    {
      "epoch": 0.029282576866764276,
      "grad_norm": 0.8483291268348694,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.6926,
      "step": 20
    },
    {
      "epoch": 0.03074670571010249,
      "grad_norm": 0.9041450023651123,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.7076,
      "step": 21
    },
    {
      "epoch": 0.032210834553440704,
      "grad_norm": 0.8793591260910034,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.6334,
      "step": 22
    },
    {
      "epoch": 0.03367496339677892,
      "grad_norm": 0.9118833541870117,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.7029,
      "step": 23
    },
    {
      "epoch": 0.03513909224011713,
      "grad_norm": 0.9427176117897034,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7891,
      "step": 24
    },
    {
      "epoch": 0.036603221083455345,
      "grad_norm": 0.9533204436302185,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.8176,
      "step": 25
    },
    {
      "epoch": 0.036603221083455345,
      "eval_loss": 0.7120001316070557,
      "eval_runtime": 77.4992,
      "eval_samples_per_second": 3.716,
      "eval_steps_per_second": 1.858,
      "step": 25
    },
    {
      "epoch": 0.03806734992679356,
      "grad_norm": 0.9075884819030762,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.7545,
      "step": 26
    },
    {
      "epoch": 0.03953147877013177,
      "grad_norm": 0.8508671522140503,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.6666,
      "step": 27
    },
    {
      "epoch": 0.040995607613469986,
      "grad_norm": 0.830573558807373,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.696,
      "step": 28
    },
    {
      "epoch": 0.0424597364568082,
      "grad_norm": 0.816193163394928,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.7688,
      "step": 29
    },
    {
      "epoch": 0.043923865300146414,
      "grad_norm": 0.9093814492225647,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.6717,
      "step": 30
    },
    {
      "epoch": 0.04538799414348463,
      "grad_norm": 0.8094978332519531,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.588,
      "step": 31
    },
    {
      "epoch": 0.04685212298682284,
      "grad_norm": 0.8796850442886353,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.7133,
      "step": 32
    },
    {
      "epoch": 0.048316251830161056,
      "grad_norm": 0.9510671496391296,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.6754,
      "step": 33
    },
    {
      "epoch": 0.04978038067349927,
      "grad_norm": 0.9171980023384094,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.665,
      "step": 34
    },
    {
      "epoch": 0.05124450951683748,
      "grad_norm": 0.9319704174995422,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.6215,
      "step": 35
    },
    {
      "epoch": 0.0527086383601757,
      "grad_norm": 0.9619579911231995,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.7145,
      "step": 36
    },
    {
      "epoch": 0.05417276720351391,
      "grad_norm": 0.8880752921104431,
      "learning_rate": 0.00014904235038305083,
      "loss": 0.6216,
      "step": 37
    },
    {
      "epoch": 0.055636896046852125,
      "grad_norm": 0.9341321587562561,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.7046,
      "step": 38
    },
    {
      "epoch": 0.05710102489019034,
      "grad_norm": 0.8551350235939026,
      "learning_rate": 0.00014317543523384928,
      "loss": 0.6551,
      "step": 39
    },
    {
      "epoch": 0.05856515373352855,
      "grad_norm": 0.9286485314369202,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.6471,
      "step": 40
    },
    {
      "epoch": 0.060029282576866766,
      "grad_norm": 0.8776522278785706,
      "learning_rate": 0.00013711972489182208,
      "loss": 0.6324,
      "step": 41
    },
    {
      "epoch": 0.06149341142020498,
      "grad_norm": 0.859512984752655,
      "learning_rate": 0.00013402931744416433,
      "loss": 0.6475,
      "step": 42
    },
    {
      "epoch": 0.0629575402635432,
      "grad_norm": 0.8624581694602966,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6477,
      "step": 43
    },
    {
      "epoch": 0.06442166910688141,
      "grad_norm": 0.8696426749229431,
      "learning_rate": 0.00012774029087618446,
      "loss": 0.6571,
      "step": 44
    },
    {
      "epoch": 0.06588579795021962,
      "grad_norm": 0.8606180548667908,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.6489,
      "step": 45
    },
    {
      "epoch": 0.06734992679355783,
      "grad_norm": 0.8928582668304443,
      "learning_rate": 0.0001213299630743747,
      "loss": 0.6775,
      "step": 46
    },
    {
      "epoch": 0.06881405563689605,
      "grad_norm": 0.9211382865905762,
      "learning_rate": 0.000118088053433211,
      "loss": 0.5962,
      "step": 47
    },
    {
      "epoch": 0.07027818448023426,
      "grad_norm": 0.9554921388626099,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.6437,
      "step": 48
    },
    {
      "epoch": 0.07174231332357248,
      "grad_norm": 0.9748461842536926,
      "learning_rate": 0.00011154846369695863,
      "loss": 0.6481,
      "step": 49
    },
    {
      "epoch": 0.07320644216691069,
      "grad_norm": 1.0362958908081055,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.6812,
      "step": 50
    },
    {
      "epoch": 0.07320644216691069,
      "eval_loss": 0.6729180812835693,
      "eval_runtime": 77.5069,
      "eval_samples_per_second": 3.716,
      "eval_steps_per_second": 1.858,
      "step": 50
    },
    {
      "epoch": 0.0746705710102489,
      "grad_norm": 1.0011053085327148,
      "learning_rate": 0.00010495837546732224,
      "loss": 0.6524,
      "step": 51
    },
    {
      "epoch": 0.07613469985358712,
      "grad_norm": 1.0353124141693115,
      "learning_rate": 0.00010165339447663587,
      "loss": 0.7559,
      "step": 52
    },
    {
      "epoch": 0.07759882869692533,
      "grad_norm": 0.8761913776397705,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.7059,
      "step": 53
    },
    {
      "epoch": 0.07906295754026355,
      "grad_norm": 0.8307029008865356,
      "learning_rate": 9.504162453267777e-05,
      "loss": 0.6997,
      "step": 54
    },
    {
      "epoch": 0.08052708638360176,
      "grad_norm": 0.7661670446395874,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.7013,
      "step": 55
    },
    {
      "epoch": 0.08199121522693997,
      "grad_norm": 0.7999428510665894,
      "learning_rate": 8.845153630304139e-05,
      "loss": 0.676,
      "step": 56
    },
    {
      "epoch": 0.08345534407027819,
      "grad_norm": 0.7628665566444397,
      "learning_rate": 8.517363522881579e-05,
      "loss": 0.655,
      "step": 57
    },
    {
      "epoch": 0.0849194729136164,
      "grad_norm": 0.7992427945137024,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.6059,
      "step": 58
    },
    {
      "epoch": 0.08638360175695461,
      "grad_norm": 0.7833818197250366,
      "learning_rate": 7.867003692562534e-05,
      "loss": 0.7034,
      "step": 59
    },
    {
      "epoch": 0.08784773060029283,
      "grad_norm": 0.7682210206985474,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.6838,
      "step": 60
    },
    {
      "epoch": 0.08931185944363104,
      "grad_norm": 0.7837997078895569,
      "learning_rate": 7.225970912381556e-05,
      "loss": 0.7132,
      "step": 61
    },
    {
      "epoch": 0.09077598828696926,
      "grad_norm": 0.7890181541442871,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.7043,
      "step": 62
    },
    {
      "epoch": 0.09224011713030747,
      "grad_norm": 0.7309653759002686,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.6575,
      "step": 63
    },
    {
      "epoch": 0.09370424597364568,
      "grad_norm": 0.73288893699646,
      "learning_rate": 6.28802751081779e-05,
      "loss": 0.6336,
      "step": 64
    },
    {
      "epoch": 0.0951683748169839,
      "grad_norm": 0.768713116645813,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.656,
      "step": 65
    },
    {
      "epoch": 0.09663250366032211,
      "grad_norm": 0.7750256061553955,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 0.5982,
      "step": 66
    },
    {
      "epoch": 0.09809663250366032,
      "grad_norm": 0.82322096824646,
      "learning_rate": 5.386588370213124e-05,
      "loss": 0.6943,
      "step": 67
    },
    {
      "epoch": 0.09956076134699854,
      "grad_norm": 0.7596611380577087,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.6716,
      "step": 68
    },
    {
      "epoch": 0.10102489019033675,
      "grad_norm": 0.7736366391181946,
      "learning_rate": 4.810304262187852e-05,
      "loss": 0.5755,
      "step": 69
    },
    {
      "epoch": 0.10248901903367497,
      "grad_norm": 0.7916914820671082,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.6694,
      "step": 70
    },
    {
      "epoch": 0.10395314787701318,
      "grad_norm": 0.8091153502464294,
      "learning_rate": 4.256713373170564e-05,
      "loss": 0.6588,
      "step": 71
    },
    {
      "epoch": 0.1054172767203514,
      "grad_norm": 0.801612138748169,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 0.6123,
      "step": 72
    },
    {
      "epoch": 0.10688140556368961,
      "grad_norm": 0.7758727073669434,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.594,
      "step": 73
    },
    {
      "epoch": 0.10834553440702782,
      "grad_norm": 0.7896532416343689,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 0.6035,
      "step": 74
    },
    {
      "epoch": 0.10980966325036604,
      "grad_norm": 0.7845363020896912,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.6064,
      "step": 75
    },
    {
      "epoch": 0.10980966325036604,
      "eval_loss": 0.6299811005592346,
      "eval_runtime": 77.5045,
      "eval_samples_per_second": 3.716,
      "eval_steps_per_second": 1.858,
      "step": 75
    },
    {
      "epoch": 0.11127379209370425,
      "grad_norm": 0.800595760345459,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 0.6418,
      "step": 76
    },
    {
      "epoch": 0.11273792093704246,
      "grad_norm": 0.8185175657272339,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 0.6344,
      "step": 77
    },
    {
      "epoch": 0.11420204978038068,
      "grad_norm": 0.8200536966323853,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.6307,
      "step": 78
    },
    {
      "epoch": 0.11566617862371889,
      "grad_norm": 0.8251193165779114,
      "learning_rate": 2.315988891431412e-05,
      "loss": 0.6243,
      "step": 79
    },
    {
      "epoch": 0.1171303074670571,
      "grad_norm": 0.7931867241859436,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.5778,
      "step": 80
    },
    {
      "epoch": 0.11859443631039532,
      "grad_norm": 0.8764688372612,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6503,
      "step": 81
    },
    {
      "epoch": 0.12005856515373353,
      "grad_norm": 0.8642603158950806,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 0.6904,
      "step": 82
    },
    {
      "epoch": 0.12152269399707175,
      "grad_norm": 0.7701883316040039,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.5929,
      "step": 83
    },
    {
      "epoch": 0.12298682284040996,
      "grad_norm": 0.813798725605011,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 0.6174,
      "step": 84
    },
    {
      "epoch": 0.12445095168374817,
      "grad_norm": 0.8495608568191528,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.6403,
      "step": 85
    },
    {
      "epoch": 0.1259150805270864,
      "grad_norm": 0.850382924079895,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 0.5469,
      "step": 86
    },
    {
      "epoch": 0.1273792093704246,
      "grad_norm": 0.8462463617324829,
      "learning_rate": 9.09934649508375e-06,
      "loss": 0.6733,
      "step": 87
    },
    {
      "epoch": 0.12884333821376281,
      "grad_norm": 0.8402328491210938,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.5709,
      "step": 88
    },
    {
      "epoch": 0.13030746705710103,
      "grad_norm": 0.9025482535362244,
      "learning_rate": 6.543553540053926e-06,
      "loss": 0.6922,
      "step": 89
    },
    {
      "epoch": 0.13177159590043924,
      "grad_norm": 0.7909383177757263,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.5907,
      "step": 90
    },
    {
      "epoch": 0.13323572474377746,
      "grad_norm": 0.7756696343421936,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 0.5443,
      "step": 91
    },
    {
      "epoch": 0.13469985358711567,
      "grad_norm": 0.837628185749054,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 0.6027,
      "step": 92
    },
    {
      "epoch": 0.13616398243045388,
      "grad_norm": 0.8768534660339355,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.6742,
      "step": 93
    },
    {
      "epoch": 0.1376281112737921,
      "grad_norm": 0.7963073253631592,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 0.5903,
      "step": 94
    },
    {
      "epoch": 0.1390922401171303,
      "grad_norm": 0.8839337229728699,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.6328,
      "step": 95
    },
    {
      "epoch": 0.14055636896046853,
      "grad_norm": 0.9011049270629883,
      "learning_rate": 8.735930673024806e-07,
      "loss": 0.6805,
      "step": 96
    },
    {
      "epoch": 0.14202049780380674,
      "grad_norm": 0.8585094213485718,
      "learning_rate": 4.917097454988584e-07,
      "loss": 0.5341,
      "step": 97
    },
    {
      "epoch": 0.14348462664714495,
      "grad_norm": 0.8849230408668518,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.6161,
      "step": 98
    },
    {
      "epoch": 0.14494875549048317,
      "grad_norm": 0.9133574366569519,
      "learning_rate": 5.467426590739511e-08,
      "loss": 0.6795,
      "step": 99
    },
    {
      "epoch": 0.14641288433382138,
      "grad_norm": 0.9264809489250183,
      "learning_rate": 0.0,
      "loss": 0.6004,
      "step": 100
    },
    {
      "epoch": 0.14641288433382138,
      "eval_loss": 0.6224383115768433,
      "eval_runtime": 77.4968,
      "eval_samples_per_second": 3.716,
      "eval_steps_per_second": 1.858,
      "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": 4.02119316209664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}