{
  "best_metric": 0.12861138582229614,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.7204301075268817,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017204301075268817,
      "grad_norm": 4.458132266998291,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 1
    },
    {
      "epoch": 0.017204301075268817,
      "eval_loss": 1.4783204793930054,
      "eval_runtime": 5.145,
      "eval_samples_per_second": 76.19,
      "eval_steps_per_second": 9.524,
      "step": 1
    },
    {
      "epoch": 0.034408602150537634,
      "grad_norm": 6.990025997161865,
      "learning_rate": 4e-05,
      "loss": 0.6626,
      "step": 2
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 7.760075092315674,
      "learning_rate": 6e-05,
      "loss": 0.6972,
      "step": 3
    },
    {
      "epoch": 0.06881720430107527,
      "grad_norm": 4.424337387084961,
      "learning_rate": 8e-05,
      "loss": 0.4081,
      "step": 4
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 3.306837797164917,
      "learning_rate": 0.0001,
      "loss": 0.3062,
      "step": 5
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 1.8788976669311523,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2261,
      "step": 6
    },
    {
      "epoch": 0.12043010752688173,
      "grad_norm": 1.6426763534545898,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2242,
      "step": 7
    },
    {
      "epoch": 0.13763440860215054,
      "grad_norm": 0.9566802978515625,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.155,
      "step": 8
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 0.9555782675743103,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1778,
      "step": 9
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.8017747402191162,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1825,
      "step": 10
    },
    {
      "epoch": 0.18924731182795698,
      "grad_norm": 0.958012044429779,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2193,
      "step": 11
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 0.8382191061973572,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2093,
      "step": 12
    },
    {
      "epoch": 0.22365591397849463,
      "grad_norm": 0.3560003638267517,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0776,
      "step": 13
    },
    {
      "epoch": 0.24086021505376345,
      "grad_norm": 0.4326319396495819,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0718,
      "step": 14
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.37284064292907715,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0865,
      "step": 15
    },
    {
      "epoch": 0.2752688172043011,
      "grad_norm": 0.5674258470535278,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1066,
      "step": 16
    },
    {
      "epoch": 0.2924731182795699,
      "grad_norm": 0.4691183269023895,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0984,
      "step": 17
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 0.4190113842487335,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1101,
      "step": 18
    },
    {
      "epoch": 0.32688172043010755,
      "grad_norm": 0.4916987419128418,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1126,
      "step": 19
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.5751784443855286,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1253,
      "step": 20
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 0.5716490149497986,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1295,
      "step": 21
    },
    {
      "epoch": 0.37849462365591396,
      "grad_norm": 0.5874112248420715,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1434,
      "step": 22
    },
    {
      "epoch": 0.3956989247311828,
      "grad_norm": 0.5886926054954529,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1337,
      "step": 23
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 0.7976363301277161,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1757,
      "step": 24
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.8777889609336853,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2267,
      "step": 25
    },
    {
      "epoch": 0.43010752688172044,
      "eval_loss": 0.1384161114692688,
      "eval_runtime": 5.1574,
      "eval_samples_per_second": 76.007,
      "eval_steps_per_second": 9.501,
      "step": 25
    },
    {
      "epoch": 0.44731182795698926,
      "grad_norm": 0.1694585084915161,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.045,
      "step": 26
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 0.2662329375743866,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0663,
      "step": 27
    },
    {
      "epoch": 0.4817204301075269,
      "grad_norm": 0.376115083694458,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0903,
      "step": 28
    },
    {
      "epoch": 0.4989247311827957,
      "grad_norm": 0.3713178336620331,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0913,
      "step": 29
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.35013172030448914,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0937,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.43744900822639465,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.104,
      "step": 31
    },
    {
      "epoch": 0.5505376344086022,
      "grad_norm": 0.4328308403491974,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1082,
      "step": 32
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 0.4831233322620392,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1199,
      "step": 33
    },
    {
      "epoch": 0.5849462365591398,
      "grad_norm": 0.5026971101760864,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1211,
      "step": 34
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.5438146591186523,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1419,
      "step": 35
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 0.5357680320739746,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1607,
      "step": 36
    },
    {
      "epoch": 0.6365591397849463,
      "grad_norm": 0.756168007850647,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1972,
      "step": 37
    },
    {
      "epoch": 0.6537634408602151,
      "grad_norm": 0.2554115355014801,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0644,
      "step": 38
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 0.20917977392673492,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0535,
      "step": 39
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 0.23978161811828613,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0679,
      "step": 40
    },
    {
      "epoch": 0.7053763440860215,
      "grad_norm": 0.27051109075546265,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0797,
      "step": 41
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 0.2598600387573242,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0822,
      "step": 42
    },
    {
      "epoch": 0.7397849462365591,
      "grad_norm": 0.35222598910331726,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0945,
      "step": 43
    },
    {
      "epoch": 0.7569892473118279,
      "grad_norm": 0.38500919938087463,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1059,
      "step": 44
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.3825439512729645,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1103,
      "step": 45
    },
    {
      "epoch": 0.7913978494623656,
      "grad_norm": 0.42811131477355957,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1171,
      "step": 46
    },
    {
      "epoch": 0.8086021505376344,
      "grad_norm": 0.5827885270118713,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1313,
      "step": 47
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 0.4837743937969208,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1533,
      "step": 48
    },
    {
      "epoch": 0.843010752688172,
      "grad_norm": 0.6008716225624084,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.1616,
      "step": 49
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.940000057220459,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2398,
      "step": 50
    },
    {
      "epoch": 0.8602150537634409,
      "eval_loss": 0.13495324552059174,
      "eval_runtime": 5.1573,
      "eval_samples_per_second": 76.008,
      "eval_steps_per_second": 9.501,
      "step": 50
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 0.17139974236488342,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0471,
      "step": 51
    },
    {
      "epoch": 0.8946236559139785,
      "grad_norm": 0.22964441776275635,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0711,
      "step": 52
    },
    {
      "epoch": 0.9118279569892473,
      "grad_norm": 0.2772515118122101,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0881,
      "step": 53
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 0.3522781431674957,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0997,
      "step": 54
    },
    {
      "epoch": 0.946236559139785,
      "grad_norm": 0.39684680104255676,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1097,
      "step": 55
    },
    {
      "epoch": 0.9634408602150538,
      "grad_norm": 0.4268311560153961,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1237,
      "step": 56
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 0.4827687740325928,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1565,
      "step": 57
    },
    {
      "epoch": 0.9978494623655914,
      "grad_norm": 0.6742030382156372,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1891,
      "step": 58
    },
    {
      "epoch": 1.0150537634408603,
      "grad_norm": 1.1234270334243774,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1136,
      "step": 59
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.18411989510059357,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0529,
      "step": 60
    },
    {
      "epoch": 1.049462365591398,
      "grad_norm": 0.2407916635274887,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0628,
      "step": 61
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.22990457713603973,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0707,
      "step": 62
    },
    {
      "epoch": 1.0838709677419356,
      "grad_norm": 0.2655136287212372,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.073,
      "step": 63
    },
    {
      "epoch": 1.1010752688172043,
      "grad_norm": 0.27105939388275146,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0723,
      "step": 64
    },
    {
      "epoch": 1.118279569892473,
      "grad_norm": 0.3270939290523529,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0787,
      "step": 65
    },
    {
      "epoch": 1.135483870967742,
      "grad_norm": 0.3238106369972229,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0795,
      "step": 66
    },
    {
      "epoch": 1.1526881720430107,
      "grad_norm": 0.3283810317516327,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.089,
      "step": 67
    },
    {
      "epoch": 1.1698924731182796,
      "grad_norm": 0.4149152636528015,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1118,
      "step": 68
    },
    {
      "epoch": 1.1870967741935483,
      "grad_norm": 0.39082080125808716,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1163,
      "step": 69
    },
    {
      "epoch": 1.2043010752688172,
      "grad_norm": 0.45351719856262207,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1187,
      "step": 70
    },
    {
      "epoch": 1.221505376344086,
      "grad_norm": 0.24564394354820251,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0572,
      "step": 71
    },
    {
      "epoch": 1.238709677419355,
      "grad_norm": 0.1709287464618683,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0471,
      "step": 72
    },
    {
      "epoch": 1.2559139784946236,
      "grad_norm": 0.21685582399368286,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0593,
      "step": 73
    },
    {
      "epoch": 1.2731182795698925,
      "grad_norm": 0.2916705310344696,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0674,
      "step": 74
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.2436515837907791,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0669,
      "step": 75
    },
    {
      "epoch": 1.2903225806451613,
      "eval_loss": 0.12913550436496735,
      "eval_runtime": 5.1492,
      "eval_samples_per_second": 76.128,
      "eval_steps_per_second": 9.516,
      "step": 75
    },
    {
      "epoch": 1.3075268817204302,
      "grad_norm": 0.28724661469459534,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0693,
      "step": 76
    },
    {
      "epoch": 1.324731182795699,
      "grad_norm": 0.30966466665267944,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0818,
      "step": 77
    },
    {
      "epoch": 1.3419354838709676,
      "grad_norm": 0.30045086145401,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0787,
      "step": 78
    },
    {
      "epoch": 1.3591397849462366,
      "grad_norm": 0.32244807481765747,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0848,
      "step": 79
    },
    {
      "epoch": 1.3763440860215055,
      "grad_norm": 0.314584881067276,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0883,
      "step": 80
    },
    {
      "epoch": 1.3935483870967742,
      "grad_norm": 0.34502357244491577,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0882,
      "step": 81
    },
    {
      "epoch": 1.410752688172043,
      "grad_norm": 0.43789923191070557,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1093,
      "step": 82
    },
    {
      "epoch": 1.4279569892473118,
      "grad_norm": 0.5525321364402771,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1309,
      "step": 83
    },
    {
      "epoch": 1.4451612903225808,
      "grad_norm": 0.28792673349380493,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0488,
      "step": 84
    },
    {
      "epoch": 1.4623655913978495,
      "grad_norm": 0.20269066095352173,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0516,
      "step": 85
    },
    {
      "epoch": 1.4795698924731182,
      "grad_norm": 0.2444780319929123,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0632,
      "step": 86
    },
    {
      "epoch": 1.4967741935483871,
      "grad_norm": 0.27078327536582947,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0694,
      "step": 87
    },
    {
      "epoch": 1.513978494623656,
      "grad_norm": 0.2688973844051361,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0732,
      "step": 88
    },
    {
      "epoch": 1.5311827956989248,
      "grad_norm": 0.29662248492240906,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0768,
      "step": 89
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.34857553243637085,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0868,
      "step": 90
    },
    {
      "epoch": 1.5655913978494622,
      "grad_norm": 0.3253614008426666,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0789,
      "step": 91
    },
    {
      "epoch": 1.5827956989247312,
      "grad_norm": 0.3459737002849579,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.085,
      "step": 92
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3518889248371124,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.095,
      "step": 93
    },
    {
      "epoch": 1.6172043010752688,
      "grad_norm": 0.44837722182273865,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1058,
      "step": 94
    },
    {
      "epoch": 1.6344086021505375,
      "grad_norm": 0.4785314202308655,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.113,
      "step": 95
    },
    {
      "epoch": 1.6516129032258065,
      "grad_norm": 0.21725249290466309,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0481,
      "step": 96
    },
    {
      "epoch": 1.6688172043010754,
      "grad_norm": 0.16432440280914307,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0433,
      "step": 97
    },
    {
      "epoch": 1.686021505376344,
      "grad_norm": 0.21126870810985565,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0511,
      "step": 98
    },
    {
      "epoch": 1.7032258064516128,
      "grad_norm": 0.2568517327308655,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.069,
      "step": 99
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.3253111243247986,
      "learning_rate": 0.0,
      "loss": 0.0793,
      "step": 100
    },
    {
      "epoch": 1.7204301075268817,
      "eval_loss": 0.12861138582229614,
      "eval_runtime": 5.1532,
      "eval_samples_per_second": 76.069,
      "eval_steps_per_second": 9.509,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.178927560327168e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}