{
  "best_metric": 1.0160294771194458,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.262044653349001,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01253427340383862,
      "grad_norm": 1.1170662641525269,
      "learning_rate": 2e-05,
      "loss": 1.4767,
      "step": 1
    },
    {
      "epoch": 0.01253427340383862,
      "eval_loss": 1.9253945350646973,
      "eval_runtime": 0.505,
      "eval_samples_per_second": 99.007,
      "eval_steps_per_second": 25.742,
      "step": 1
    },
    {
      "epoch": 0.02506854680767724,
      "grad_norm": 1.693622350692749,
      "learning_rate": 4e-05,
      "loss": 1.3994,
      "step": 2
    },
    {
      "epoch": 0.03760282021151586,
      "grad_norm": 1.2852354049682617,
      "learning_rate": 6e-05,
      "loss": 1.4144,
      "step": 3
    },
    {
      "epoch": 0.05013709361535448,
      "grad_norm": 0.7188471555709839,
      "learning_rate": 8e-05,
      "loss": 1.4402,
      "step": 4
    },
    {
      "epoch": 0.06267136701919311,
      "grad_norm": 0.8938153386116028,
      "learning_rate": 0.0001,
      "loss": 1.3592,
      "step": 5
    },
    {
      "epoch": 0.07520564042303172,
      "grad_norm": 1.0028204917907715,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.3106,
      "step": 6
    },
    {
      "epoch": 0.08773991382687035,
      "grad_norm": 0.8493397235870361,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.3208,
      "step": 7
    },
    {
      "epoch": 0.10027418723070897,
      "grad_norm": 0.9337547421455383,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.3671,
      "step": 8
    },
    {
      "epoch": 0.1128084606345476,
      "grad_norm": 1.223391056060791,
      "learning_rate": 9.96068831197139e-05,
      "loss": 1.5723,
      "step": 9
    },
    {
      "epoch": 0.12534273403838622,
      "grad_norm": 1.8942437171936035,
      "learning_rate": 9.938625865312251e-05,
      "loss": 1.639,
      "step": 10
    },
    {
      "epoch": 0.13787700744222484,
      "grad_norm": 2.1686646938323975,
      "learning_rate": 9.911709846436641e-05,
      "loss": 1.6882,
      "step": 11
    },
    {
      "epoch": 0.15041128084606345,
      "grad_norm": 3.026473045349121,
      "learning_rate": 9.879969687616027e-05,
      "loss": 1.7185,
      "step": 12
    },
    {
      "epoch": 0.16294555424990206,
      "grad_norm": 1.4735753536224365,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.8444,
      "step": 13
    },
    {
      "epoch": 0.1754798276537407,
      "grad_norm": 0.49902650713920593,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.2001,
      "step": 14
    },
    {
      "epoch": 0.18801410105757932,
      "grad_norm": 0.6777222156524658,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.2655,
      "step": 15
    },
    {
      "epoch": 0.20054837446141793,
      "grad_norm": 0.4127340614795685,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.1372,
      "step": 16
    },
    {
      "epoch": 0.21308264786525657,
      "grad_norm": 0.40515682101249695,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.1083,
      "step": 17
    },
    {
      "epoch": 0.2256169212690952,
      "grad_norm": 0.4739683270454407,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.0717,
      "step": 18
    },
    {
      "epoch": 0.2381511946729338,
      "grad_norm": 0.6458739042282104,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.0592,
      "step": 19
    },
    {
      "epoch": 0.25068546807677244,
      "grad_norm": 0.5222955346107483,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.0887,
      "step": 20
    },
    {
      "epoch": 0.26321974148061106,
      "grad_norm": 0.3751823306083679,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.1611,
      "step": 21
    },
    {
      "epoch": 0.27575401488444967,
      "grad_norm": 0.4577747583389282,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.1816,
      "step": 22
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.7088647484779358,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.3151,
      "step": 23
    },
    {
      "epoch": 0.3008225616921269,
      "grad_norm": 0.7640499472618103,
      "learning_rate": 9.140576474687264e-05,
      "loss": 1.3088,
      "step": 24
    },
    {
      "epoch": 0.3133568350959655,
      "grad_norm": 1.2768914699554443,
      "learning_rate": 9.051132292283771e-05,
      "loss": 1.5238,
      "step": 25
    },
    {
      "epoch": 0.3133568350959655,
      "eval_loss": 1.1197373867034912,
      "eval_runtime": 0.5165,
      "eval_samples_per_second": 96.799,
      "eval_steps_per_second": 25.168,
      "step": 25
    },
    {
      "epoch": 0.3258911084998041,
      "grad_norm": 0.40855640172958374,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.2607,
      "step": 26
    },
    {
      "epoch": 0.3384253819036428,
      "grad_norm": 0.30009791254997253,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.1573,
      "step": 27
    },
    {
      "epoch": 0.3509596553074814,
      "grad_norm": 0.291363388299942,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.2557,
      "step": 28
    },
    {
      "epoch": 0.36349392871132,
      "grad_norm": 0.30838480591773987,
      "learning_rate": 8.655565529226198e-05,
      "loss": 1.0956,
      "step": 29
    },
    {
      "epoch": 0.37602820211515864,
      "grad_norm": 0.2992044687271118,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.0659,
      "step": 30
    },
    {
      "epoch": 0.38856247551899725,
      "grad_norm": 0.34686920046806335,
      "learning_rate": 8.436635926858759e-05,
      "loss": 1.0239,
      "step": 31
    },
    {
      "epoch": 0.40109674892283587,
      "grad_norm": 0.3565788269042969,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.998,
      "step": 32
    },
    {
      "epoch": 0.4136310223266745,
      "grad_norm": 0.35293048620224,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.0887,
      "step": 33
    },
    {
      "epoch": 0.42616529573051315,
      "grad_norm": 0.45323696732521057,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.0885,
      "step": 34
    },
    {
      "epoch": 0.43869956913435176,
      "grad_norm": 0.3370770215988159,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.1596,
      "step": 35
    },
    {
      "epoch": 0.4512338425381904,
      "grad_norm": 0.4662862718105316,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.253,
      "step": 36
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 0.6272767782211304,
      "learning_rate": 7.706905767237288e-05,
      "loss": 1.2657,
      "step": 37
    },
    {
      "epoch": 0.4763023893458676,
      "grad_norm": 0.8257837295532227,
      "learning_rate": 7.576035233404096e-05,
      "loss": 1.4337,
      "step": 38
    },
    {
      "epoch": 0.4888366627497062,
      "grad_norm": 0.30664369463920593,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.1647,
      "step": 39
    },
    {
      "epoch": 0.5013709361535449,
      "grad_norm": 0.3234965205192566,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.1474,
      "step": 40
    },
    {
      "epoch": 0.5139052095573835,
      "grad_norm": 0.285153329372406,
      "learning_rate": 7.170387620131993e-05,
      "loss": 1.1143,
      "step": 41
    },
    {
      "epoch": 0.5264394829612221,
      "grad_norm": 0.2415602058172226,
      "learning_rate": 7.031319284987394e-05,
      "loss": 1.0752,
      "step": 42
    },
    {
      "epoch": 0.5389737563650607,
      "grad_norm": 0.2069091945886612,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.9871,
      "step": 43
    },
    {
      "epoch": 0.5515080297688993,
      "grad_norm": 0.23944531381130219,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.96,
      "step": 44
    },
    {
      "epoch": 0.564042303172738,
      "grad_norm": 0.2600782811641693,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.0151,
      "step": 45
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.2677628993988037,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.0476,
      "step": 46
    },
    {
      "epoch": 0.5891108499804152,
      "grad_norm": 0.33392930030822754,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.0985,
      "step": 47
    },
    {
      "epoch": 0.6016451233842538,
      "grad_norm": 0.45021188259124756,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.1938,
      "step": 48
    },
    {
      "epoch": 0.6141793967880924,
      "grad_norm": 0.5526214838027954,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.2237,
      "step": 49
    },
    {
      "epoch": 0.626713670191931,
      "grad_norm": 0.8567461967468262,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 1.2901,
      "step": 50
    },
    {
      "epoch": 0.626713670191931,
      "eval_loss": 1.0427753925323486,
      "eval_runtime": 0.5038,
      "eval_samples_per_second": 99.253,
      "eval_steps_per_second": 25.806,
      "step": 50
    },
    {
      "epoch": 0.6392479435957696,
      "grad_norm": 0.6127623915672302,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.5449,
      "step": 51
    },
    {
      "epoch": 0.6517822169996083,
      "grad_norm": 0.15788757801055908,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.1523,
      "step": 52
    },
    {
      "epoch": 0.664316490403447,
      "grad_norm": 0.19719970226287842,
      "learning_rate": 5.425597248551387e-05,
      "loss": 1.0965,
      "step": 53
    },
    {
      "epoch": 0.6768507638072856,
      "grad_norm": 0.20220746099948883,
      "learning_rate": 5.2768731039705e-05,
      "loss": 1.0729,
      "step": 54
    },
    {
      "epoch": 0.6893850372111242,
      "grad_norm": 0.21883238852024078,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.0133,
      "step": 55
    },
    {
      "epoch": 0.7019193106149628,
      "grad_norm": 0.20048078894615173,
      "learning_rate": 4.980319133636863e-05,
      "loss": 0.9661,
      "step": 56
    },
    {
      "epoch": 0.7144535840188014,
      "grad_norm": 0.23357737064361572,
      "learning_rate": 4.83281358529671e-05,
      "loss": 0.983,
      "step": 57
    },
    {
      "epoch": 0.72698785742264,
      "grad_norm": 0.24839633703231812,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.0299,
      "step": 58
    },
    {
      "epoch": 0.7395221308264787,
      "grad_norm": 0.2856897711753845,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.083,
      "step": 59
    },
    {
      "epoch": 0.7520564042303173,
      "grad_norm": 0.3443909287452698,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.0942,
      "step": 60
    },
    {
      "epoch": 0.7645906776341559,
      "grad_norm": 0.3818349242210388,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.1876,
      "step": 61
    },
    {
      "epoch": 0.7771249510379945,
      "grad_norm": 0.5584022998809814,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.2389,
      "step": 62
    },
    {
      "epoch": 0.7896592244418331,
      "grad_norm": 1.83659029006958,
      "learning_rate": 3.968680715012606e-05,
      "loss": 1.8469,
      "step": 63
    },
    {
      "epoch": 0.8021934978456717,
      "grad_norm": 0.15524441003799438,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.1955,
      "step": 64
    },
    {
      "epoch": 0.8147277712495103,
      "grad_norm": 0.15641632676124573,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.1487,
      "step": 65
    },
    {
      "epoch": 0.827262044653349,
      "grad_norm": 0.1683935523033142,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.0506,
      "step": 66
    },
    {
      "epoch": 0.8397963180571876,
      "grad_norm": 0.17298902571201324,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.0407,
      "step": 67
    },
    {
      "epoch": 0.8523305914610263,
      "grad_norm": 0.19782142341136932,
      "learning_rate": 3.293094232762715e-05,
      "loss": 0.9614,
      "step": 68
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.2152557373046875,
      "learning_rate": 3.164636917984534e-05,
      "loss": 0.9624,
      "step": 69
    },
    {
      "epoch": 0.8773991382687035,
      "grad_norm": 0.2377156764268875,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.9853,
      "step": 70
    },
    {
      "epoch": 0.8899334116725421,
      "grad_norm": 0.24591700732707977,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.0166,
      "step": 71
    },
    {
      "epoch": 0.9024676850763808,
      "grad_norm": 0.32400262355804443,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.0993,
      "step": 72
    },
    {
      "epoch": 0.9150019584802194,
      "grad_norm": 0.3385933041572571,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.0851,
      "step": 73
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.4308682382106781,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.1932,
      "step": 74
    },
    {
      "epoch": 0.9400705052878966,
      "grad_norm": 0.8425101041793823,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 1.2269,
      "step": 75
    },
    {
      "epoch": 0.9400705052878966,
      "eval_loss": 1.0223414897918701,
      "eval_runtime": 0.5047,
      "eval_samples_per_second": 99.066,
      "eval_steps_per_second": 25.757,
      "step": 75
    },
    {
      "epoch": 0.9526047786917352,
      "grad_norm": 0.49434900283813477,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 1.4486,
      "step": 76
    },
    {
      "epoch": 0.9651390520955738,
      "grad_norm": 0.17201216518878937,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.0346,
      "step": 77
    },
    {
      "epoch": 0.9776733254994124,
      "grad_norm": 0.20286938548088074,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 0.9808,
      "step": 78
    },
    {
      "epoch": 0.990207598903251,
      "grad_norm": 0.32843250036239624,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.1024,
      "step": 79
    },
    {
      "epoch": 1.0113591852722288,
      "grad_norm": 1.1532492637634277,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 2.3248,
      "step": 80
    },
    {
      "epoch": 1.0238934586760673,
      "grad_norm": 0.1928626447916031,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.1929,
      "step": 81
    },
    {
      "epoch": 1.036427732079906,
      "grad_norm": 0.16608740389347076,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.0818,
      "step": 82
    },
    {
      "epoch": 1.0489620054837445,
      "grad_norm": 0.17658193409442902,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.0452,
      "step": 83
    },
    {
      "epoch": 1.0614962788875832,
      "grad_norm": 0.17382438480854034,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 0.9723,
      "step": 84
    },
    {
      "epoch": 1.074030552291422,
      "grad_norm": 0.18274889886379242,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.972,
      "step": 85
    },
    {
      "epoch": 1.0865648256952605,
      "grad_norm": 0.19719198346138,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 0.9441,
      "step": 86
    },
    {
      "epoch": 1.0990990990990992,
      "grad_norm": 0.23278285562992096,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 0.9647,
      "step": 87
    },
    {
      "epoch": 1.1116333725029377,
      "grad_norm": 0.26890018582344055,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.0008,
      "step": 88
    },
    {
      "epoch": 1.1241676459067764,
      "grad_norm": 0.34293997287750244,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.1211,
      "step": 89
    },
    {
      "epoch": 1.136701919310615,
      "grad_norm": 0.36756041646003723,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.1147,
      "step": 90
    },
    {
      "epoch": 1.1492361927144537,
      "grad_norm": 0.47754383087158203,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.1506,
      "step": 91
    },
    {
      "epoch": 1.1617704661182922,
      "grad_norm": 0.9767032265663147,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.5687,
      "step": 92
    },
    {
      "epoch": 1.1743047395221309,
      "grad_norm": 0.27648741006851196,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.2947,
      "step": 93
    },
    {
      "epoch": 1.1868390129259694,
      "grad_norm": 0.16597148776054382,
      "learning_rate": 1.088290153563358e-05,
      "loss": 1.1376,
      "step": 94
    },
    {
      "epoch": 1.199373286329808,
      "grad_norm": 0.18325175344944,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 1.0643,
      "step": 95
    },
    {
      "epoch": 1.2119075597336466,
      "grad_norm": 0.17501665651798248,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 0.9975,
      "step": 96
    },
    {
      "epoch": 1.2244418331374853,
      "grad_norm": 0.1747180074453354,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 0.9486,
      "step": 97
    },
    {
      "epoch": 1.2369761065413238,
      "grad_norm": 0.18863636255264282,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 0.9441,
      "step": 98
    },
    {
      "epoch": 1.2495103799451626,
      "grad_norm": 0.21438157558441162,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 0.9852,
      "step": 99
    },
    {
      "epoch": 1.262044653349001,
      "grad_norm": 0.2572687864303589,
      "learning_rate": 1e-05,
      "loss": 1.0719,
      "step": 100
    },
    {
      "epoch": 1.262044653349001,
      "eval_loss": 1.0160294771194458,
      "eval_runtime": 0.504,
      "eval_samples_per_second": 99.214,
      "eval_steps_per_second": 25.796,
      "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": 1.6898819529847603e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}