{
  "best_metric": 1.0146315097808838,
  "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": 1.065430760383606,
      "learning_rate": 2e-05,
      "loss": 1.4767,
      "step": 1
    },
    {
      "epoch": 0.01253427340383862,
      "eval_loss": 1.9253945350646973,
      "eval_runtime": 0.5058,
      "eval_samples_per_second": 98.851,
      "eval_steps_per_second": 25.701,
      "step": 1
    },
    {
      "epoch": 0.02506854680767724,
      "grad_norm": 1.6225430965423584,
      "learning_rate": 4e-05,
      "loss": 1.3994,
      "step": 2
    },
    {
      "epoch": 0.03760282021151586,
      "grad_norm": 1.2386142015457153,
      "learning_rate": 6e-05,
      "loss": 1.415,
      "step": 3
    },
    {
      "epoch": 0.05013709361535448,
      "grad_norm": 0.6819537878036499,
      "learning_rate": 8e-05,
      "loss": 1.4403,
      "step": 4
    },
    {
      "epoch": 0.06267136701919311,
      "grad_norm": 0.8419666886329651,
      "learning_rate": 0.0001,
      "loss": 1.3604,
      "step": 5
    },
    {
      "epoch": 0.07520564042303172,
      "grad_norm": 0.9854099750518799,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.3129,
      "step": 6
    },
    {
      "epoch": 0.08773991382687035,
      "grad_norm": 0.8464058041572571,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.3227,
      "step": 7
    },
    {
      "epoch": 0.10027418723070897,
      "grad_norm": 0.902024507522583,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.3704,
      "step": 8
    },
    {
      "epoch": 0.1128084606345476,
      "grad_norm": 1.2437635660171509,
      "learning_rate": 9.96068831197139e-05,
      "loss": 1.5765,
      "step": 9
    },
    {
      "epoch": 0.12534273403838622,
      "grad_norm": 1.6130616664886475,
      "learning_rate": 9.938625865312251e-05,
      "loss": 1.6439,
      "step": 10
    },
    {
      "epoch": 0.13787700744222484,
      "grad_norm": 2.1686384677886963,
      "learning_rate": 9.911709846436641e-05,
      "loss": 1.688,
      "step": 11
    },
    {
      "epoch": 0.15041128084606345,
      "grad_norm": 2.926682472229004,
      "learning_rate": 9.879969687616027e-05,
      "loss": 1.7303,
      "step": 12
    },
    {
      "epoch": 0.16294555424990206,
      "grad_norm": 1.3535600900650024,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.8476,
      "step": 13
    },
    {
      "epoch": 0.1754798276537407,
      "grad_norm": 0.5178162455558777,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.2019,
      "step": 14
    },
    {
      "epoch": 0.18801410105757932,
      "grad_norm": 0.5845542550086975,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.2685,
      "step": 15
    },
    {
      "epoch": 0.20054837446141793,
      "grad_norm": 0.3702237606048584,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.1359,
      "step": 16
    },
    {
      "epoch": 0.21308264786525657,
      "grad_norm": 0.3851359486579895,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.1106,
      "step": 17
    },
    {
      "epoch": 0.2256169212690952,
      "grad_norm": 0.44309094548225403,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.0739,
      "step": 18
    },
    {
      "epoch": 0.2381511946729338,
      "grad_norm": 0.4140450060367584,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.0593,
      "step": 19
    },
    {
      "epoch": 0.25068546807677244,
      "grad_norm": 0.4120848476886749,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.0905,
      "step": 20
    },
    {
      "epoch": 0.26321974148061106,
      "grad_norm": 0.5593251585960388,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.164,
      "step": 21
    },
    {
      "epoch": 0.27575401488444967,
      "grad_norm": 0.47133612632751465,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.1828,
      "step": 22
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.8377242088317871,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.3158,
      "step": 23
    },
    {
      "epoch": 0.3008225616921269,
      "grad_norm": 0.758277416229248,
      "learning_rate": 9.140576474687264e-05,
      "loss": 1.3127,
      "step": 24
    },
    {
      "epoch": 0.3133568350959655,
      "grad_norm": 1.3909739255905151,
      "learning_rate": 9.051132292283771e-05,
      "loss": 1.5423,
      "step": 25
    },
    {
      "epoch": 0.3133568350959655,
      "eval_loss": 1.1302893161773682,
      "eval_runtime": 0.5032,
      "eval_samples_per_second": 99.369,
      "eval_steps_per_second": 25.836,
      "step": 25
    },
    {
      "epoch": 0.3258911084998041,
      "grad_norm": 0.39622560143470764,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.2607,
      "step": 26
    },
    {
      "epoch": 0.3384253819036428,
      "grad_norm": 0.30300581455230713,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.158,
      "step": 27
    },
    {
      "epoch": 0.3509596553074814,
      "grad_norm": 0.2985769510269165,
      "learning_rate": 8.759913421559902e-05,
      "loss": 1.2553,
      "step": 28
    },
    {
      "epoch": 0.36349392871132,
      "grad_norm": 0.23289650678634644,
      "learning_rate": 8.655565529226198e-05,
      "loss": 1.0957,
      "step": 29
    },
    {
      "epoch": 0.37602820211515864,
      "grad_norm": 0.28858616948127747,
      "learning_rate": 8.547767072315835e-05,
      "loss": 1.0659,
      "step": 30
    },
    {
      "epoch": 0.38856247551899725,
      "grad_norm": 0.32212552428245544,
      "learning_rate": 8.436635926858759e-05,
      "loss": 1.0239,
      "step": 31
    },
    {
      "epoch": 0.40109674892283587,
      "grad_norm": 0.35565420985221863,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.9998,
      "step": 32
    },
    {
      "epoch": 0.4136310223266745,
      "grad_norm": 0.3142378628253937,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.0932,
      "step": 33
    },
    {
      "epoch": 0.42616529573051315,
      "grad_norm": 0.3126344382762909,
      "learning_rate": 8.084478982073247e-05,
      "loss": 1.0905,
      "step": 34
    },
    {
      "epoch": 0.43869956913435176,
      "grad_norm": 0.3326547145843506,
      "learning_rate": 7.961266711550922e-05,
      "loss": 1.1614,
      "step": 35
    },
    {
      "epoch": 0.4512338425381904,
      "grad_norm": 0.5252828001976013,
      "learning_rate": 7.835363082015468e-05,
      "loss": 1.2527,
      "step": 36
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 0.6218559741973877,
      "learning_rate": 7.706905767237288e-05,
      "loss": 1.2688,
      "step": 37
    },
    {
      "epoch": 0.4763023893458676,
      "grad_norm": 0.8121174573898315,
      "learning_rate": 7.576035233404096e-05,
      "loss": 1.4308,
      "step": 38
    },
    {
      "epoch": 0.4888366627497062,
      "grad_norm": 0.3257191479206085,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.1662,
      "step": 39
    },
    {
      "epoch": 0.5013709361535449,
      "grad_norm": 0.3431564271450043,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.1489,
      "step": 40
    },
    {
      "epoch": 0.5139052095573835,
      "grad_norm": 0.3011854290962219,
      "learning_rate": 7.170387620131993e-05,
      "loss": 1.1174,
      "step": 41
    },
    {
      "epoch": 0.5264394829612221,
      "grad_norm": 0.25172197818756104,
      "learning_rate": 7.031319284987394e-05,
      "loss": 1.0787,
      "step": 42
    },
    {
      "epoch": 0.5389737563650607,
      "grad_norm": 0.198319673538208,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.9878,
      "step": 43
    },
    {
      "epoch": 0.5515080297688993,
      "grad_norm": 0.2211153209209442,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.9592,
      "step": 44
    },
    {
      "epoch": 0.564042303172738,
      "grad_norm": 0.2352219521999359,
      "learning_rate": 6.604684692133597e-05,
      "loss": 1.0132,
      "step": 45
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.2619933485984802,
      "learning_rate": 6.459848338346861e-05,
      "loss": 1.0471,
      "step": 46
    },
    {
      "epoch": 0.5891108499804152,
      "grad_norm": 0.3275744616985321,
      "learning_rate": 6.313962404494496e-05,
      "loss": 1.1015,
      "step": 47
    },
    {
      "epoch": 0.6016451233842538,
      "grad_norm": 0.4369727075099945,
      "learning_rate": 6.167186414703289e-05,
      "loss": 1.1958,
      "step": 48
    },
    {
      "epoch": 0.6141793967880924,
      "grad_norm": 0.592064380645752,
      "learning_rate": 6.019680866363139e-05,
      "loss": 1.2309,
      "step": 49
    },
    {
      "epoch": 0.626713670191931,
      "grad_norm": 0.8621000051498413,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 1.2946,
      "step": 50
    },
    {
      "epoch": 0.626713670191931,
      "eval_loss": 1.0444798469543457,
      "eval_runtime": 0.5038,
      "eval_samples_per_second": 99.243,
      "eval_steps_per_second": 25.803,
      "step": 50
    },
    {
      "epoch": 0.6392479435957696,
      "grad_norm": 0.5975894331932068,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.541,
      "step": 51
    },
    {
      "epoch": 0.6517822169996083,
      "grad_norm": 0.15483112633228302,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.1529,
      "step": 52
    },
    {
      "epoch": 0.664316490403447,
      "grad_norm": 0.18394102156162262,
      "learning_rate": 5.425597248551387e-05,
      "loss": 1.0972,
      "step": 53
    },
    {
      "epoch": 0.6768507638072856,
      "grad_norm": 0.19094309210777283,
      "learning_rate": 5.2768731039705e-05,
      "loss": 1.0735,
      "step": 54
    },
    {
      "epoch": 0.6893850372111242,
      "grad_norm": 0.20925824344158173,
      "learning_rate": 5.128392945374505e-05,
      "loss": 1.014,
      "step": 55
    },
    {
      "epoch": 0.7019193106149628,
      "grad_norm": 0.1995202600955963,
      "learning_rate": 4.980319133636863e-05,
      "loss": 0.9662,
      "step": 56
    },
    {
      "epoch": 0.7144535840188014,
      "grad_norm": 0.23315928876399994,
      "learning_rate": 4.83281358529671e-05,
      "loss": 0.9831,
      "step": 57
    },
    {
      "epoch": 0.72698785742264,
      "grad_norm": 0.24936404824256897,
      "learning_rate": 4.686037595505507e-05,
      "loss": 1.0317,
      "step": 58
    },
    {
      "epoch": 0.7395221308264787,
      "grad_norm": 0.3004598915576935,
      "learning_rate": 4.54015166165314e-05,
      "loss": 1.0879,
      "step": 59
    },
    {
      "epoch": 0.7520564042303173,
      "grad_norm": 0.3489072620868683,
      "learning_rate": 4.395315307866405e-05,
      "loss": 1.0994,
      "step": 60
    },
    {
      "epoch": 0.7645906776341559,
      "grad_norm": 0.4188476800918579,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 1.1941,
      "step": 61
    },
    {
      "epoch": 0.7771249510379945,
      "grad_norm": 0.589253306388855,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.2446,
      "step": 62
    },
    {
      "epoch": 0.7896592244418331,
      "grad_norm": 1.2236573696136475,
      "learning_rate": 3.968680715012606e-05,
      "loss": 1.8354,
      "step": 63
    },
    {
      "epoch": 0.8021934978456717,
      "grad_norm": 0.1607893407344818,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.1968,
      "step": 64
    },
    {
      "epoch": 0.8147277712495103,
      "grad_norm": 0.15359888970851898,
      "learning_rate": 3.692370589061639e-05,
      "loss": 1.15,
      "step": 65
    },
    {
      "epoch": 0.827262044653349,
      "grad_norm": 0.17053017020225525,
      "learning_rate": 3.557105414476782e-05,
      "loss": 1.0514,
      "step": 66
    },
    {
      "epoch": 0.8397963180571876,
      "grad_norm": 0.17347736656665802,
      "learning_rate": 3.423964766595906e-05,
      "loss": 1.0406,
      "step": 67
    },
    {
      "epoch": 0.8523305914610263,
      "grad_norm": 0.19352148473262787,
      "learning_rate": 3.293094232762715e-05,
      "loss": 0.9618,
      "step": 68
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.21194122731685638,
      "learning_rate": 3.164636917984534e-05,
      "loss": 0.9632,
      "step": 69
    },
    {
      "epoch": 0.8773991382687035,
      "grad_norm": 0.22881725430488586,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.9874,
      "step": 70
    },
    {
      "epoch": 0.8899334116725421,
      "grad_norm": 0.24773931503295898,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 1.0175,
      "step": 71
    },
    {
      "epoch": 0.9024676850763808,
      "grad_norm": 0.315243124961853,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 1.1039,
      "step": 72
    },
    {
      "epoch": 0.9150019584802194,
      "grad_norm": 0.3527504503726959,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.0922,
      "step": 73
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.5069158673286438,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.1989,
      "step": 74
    },
    {
      "epoch": 0.9400705052878966,
      "grad_norm": 0.89546799659729,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 1.2376,
      "step": 75
    },
    {
      "epoch": 0.9400705052878966,
      "eval_loss": 1.0211966037750244,
      "eval_runtime": 0.5041,
      "eval_samples_per_second": 99.195,
      "eval_steps_per_second": 25.791,
      "step": 75
    },
    {
      "epoch": 0.9526047786917352,
      "grad_norm": 0.4782760441303253,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 1.4443,
      "step": 76
    },
    {
      "epoch": 0.9651390520955738,
      "grad_norm": 0.17578525841236115,
      "learning_rate": 2.2400865784401e-05,
      "loss": 1.0353,
      "step": 77
    },
    {
      "epoch": 0.9776733254994124,
      "grad_norm": 0.19925934076309204,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 0.9825,
      "step": 78
    },
    {
      "epoch": 0.990207598903251,
      "grad_norm": 0.321463018655777,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 1.1059,
      "step": 79
    },
    {
      "epoch": 1.0113591852722288,
      "grad_norm": 1.0701099634170532,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 2.3199,
      "step": 80
    },
    {
      "epoch": 1.0238934586760673,
      "grad_norm": 0.20064501464366913,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.193,
      "step": 81
    },
    {
      "epoch": 1.036427732079906,
      "grad_norm": 0.16497324407100677,
      "learning_rate": 1.77396025983391e-05,
      "loss": 1.0823,
      "step": 82
    },
    {
      "epoch": 1.0489620054837445,
      "grad_norm": 0.1805717796087265,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 1.0458,
      "step": 83
    },
    {
      "epoch": 1.0614962788875832,
      "grad_norm": 0.17193178832530975,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 0.9725,
      "step": 84
    },
    {
      "epoch": 1.074030552291422,
      "grad_norm": 0.18326754868030548,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.9722,
      "step": 85
    },
    {
      "epoch": 1.0865648256952605,
      "grad_norm": 0.20325006544589996,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 0.9446,
      "step": 86
    },
    {
      "epoch": 1.0990990990990992,
      "grad_norm": 0.23397134244441986,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 0.9672,
      "step": 87
    },
    {
      "epoch": 1.1116333725029377,
      "grad_norm": 0.2701351046562195,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 1.0053,
      "step": 88
    },
    {
      "epoch": 1.1241676459067764,
      "grad_norm": 0.3563973307609558,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 1.1253,
      "step": 89
    },
    {
      "epoch": 1.136701919310615,
      "grad_norm": 0.3762572705745697,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 1.1212,
      "step": 90
    },
    {
      "epoch": 1.1492361927144537,
      "grad_norm": 0.4805110991001129,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 1.1656,
      "step": 91
    },
    {
      "epoch": 1.1617704661182922,
      "grad_norm": 0.9201070070266724,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 1.5552,
      "step": 92
    },
    {
      "epoch": 1.1743047395221309,
      "grad_norm": 0.24048174917697906,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 1.2953,
      "step": 93
    },
    {
      "epoch": 1.1868390129259694,
      "grad_norm": 0.159620463848114,
      "learning_rate": 1.088290153563358e-05,
      "loss": 1.1379,
      "step": 94
    },
    {
      "epoch": 1.199373286329808,
      "grad_norm": 0.17821361124515533,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 1.0653,
      "step": 95
    },
    {
      "epoch": 1.2119075597336466,
      "grad_norm": 0.18576368689537048,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 0.9979,
      "step": 96
    },
    {
      "epoch": 1.2244418331374853,
      "grad_norm": 0.17474296689033508,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 0.95,
      "step": 97
    },
    {
      "epoch": 1.2369761065413238,
      "grad_norm": 0.18885326385498047,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 0.9432,
      "step": 98
    },
    {
      "epoch": 1.2495103799451626,
      "grad_norm": 0.21814164519309998,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 0.9849,
      "step": 99
    },
    {
      "epoch": 1.262044653349001,
      "grad_norm": 0.2603691816329956,
      "learning_rate": 1e-05,
      "loss": 1.0749,
      "step": 100
    },
    {
      "epoch": 1.262044653349001,
      "eval_loss": 1.0146315097808838,
      "eval_runtime": 0.5028,
      "eval_samples_per_second": 99.449,
      "eval_steps_per_second": 25.857,
      "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
}