{
  "best_metric": 0.33776161074638367,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.32118839706915586,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003211883970691559,
      "grad_norm": 20.16118621826172,
      "learning_rate": 2e-05,
      "loss": 10.5874,
      "step": 1
    },
    {
      "epoch": 0.003211883970691559,
      "eval_loss": 10.961771011352539,
      "eval_runtime": 0.5041,
      "eval_samples_per_second": 99.189,
      "eval_steps_per_second": 25.789,
      "step": 1
    },
    {
      "epoch": 0.006423767941383118,
      "grad_norm": 19.579418182373047,
      "learning_rate": 4e-05,
      "loss": 11.2853,
      "step": 2
    },
    {
      "epoch": 0.009635651912074676,
      "grad_norm": 19.505998611450195,
      "learning_rate": 6e-05,
      "loss": 11.473,
      "step": 3
    },
    {
      "epoch": 0.012847535882766235,
      "grad_norm": 19.151931762695312,
      "learning_rate": 8e-05,
      "loss": 10.7664,
      "step": 4
    },
    {
      "epoch": 0.016059419853457792,
      "grad_norm": 15.65612506866455,
      "learning_rate": 0.0001,
      "loss": 9.6991,
      "step": 5
    },
    {
      "epoch": 0.019271303824149353,
      "grad_norm": 15.794941902160645,
      "learning_rate": 9.997539658034168e-05,
      "loss": 8.4858,
      "step": 6
    },
    {
      "epoch": 0.02248318779484091,
      "grad_norm": 24.663986206054688,
      "learning_rate": 9.990161322484486e-05,
      "loss": 7.7278,
      "step": 7
    },
    {
      "epoch": 0.02569507176553247,
      "grad_norm": 32.05091857910156,
      "learning_rate": 9.977873061452552e-05,
      "loss": 5.7351,
      "step": 8
    },
    {
      "epoch": 0.028906955736224028,
      "grad_norm": 20.47426986694336,
      "learning_rate": 9.96068831197139e-05,
      "loss": 3.6171,
      "step": 9
    },
    {
      "epoch": 0.032118839706915585,
      "grad_norm": 16.713817596435547,
      "learning_rate": 9.938625865312251e-05,
      "loss": 2.2651,
      "step": 10
    },
    {
      "epoch": 0.035330723677607145,
      "grad_norm": 15.718864440917969,
      "learning_rate": 9.911709846436641e-05,
      "loss": 1.6319,
      "step": 11
    },
    {
      "epoch": 0.038542607648298706,
      "grad_norm": 8.562857627868652,
      "learning_rate": 9.879969687616027e-05,
      "loss": 1.043,
      "step": 12
    },
    {
      "epoch": 0.041754491618990267,
      "grad_norm": 7.533064842224121,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.4191,
      "step": 13
    },
    {
      "epoch": 0.04496637558968182,
      "grad_norm": 9.270398139953613,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.9694,
      "step": 14
    },
    {
      "epoch": 0.04817825956037338,
      "grad_norm": 6.436896324157715,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.4584,
      "step": 15
    },
    {
      "epoch": 0.05139014353106494,
      "grad_norm": 9.544507026672363,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.0719,
      "step": 16
    },
    {
      "epoch": 0.0546020275017565,
      "grad_norm": 12.543577194213867,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.2843,
      "step": 17
    },
    {
      "epoch": 0.057813911472448055,
      "grad_norm": 5.713746070861816,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.9745,
      "step": 18
    },
    {
      "epoch": 0.061025795443139616,
      "grad_norm": 3.9435653686523438,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.7748,
      "step": 19
    },
    {
      "epoch": 0.06423767941383117,
      "grad_norm": 12.931794166564941,
      "learning_rate": 9.4576318804292e-05,
      "loss": 2.0045,
      "step": 20
    },
    {
      "epoch": 0.06744956338452274,
      "grad_norm": 9.132307052612305,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.4456,
      "step": 21
    },
    {
      "epoch": 0.07066144735521429,
      "grad_norm": 4.245421886444092,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.8106,
      "step": 22
    },
    {
      "epoch": 0.07387333132590586,
      "grad_norm": 6.020063400268555,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.5633,
      "step": 23
    },
    {
      "epoch": 0.07708521529659741,
      "grad_norm": 5.152550220489502,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.6608,
      "step": 24
    },
    {
      "epoch": 0.08029709926728897,
      "grad_norm": 4.782017707824707,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.6502,
      "step": 25
    },
    {
      "epoch": 0.08029709926728897,
      "eval_loss": 0.6939069628715515,
      "eval_runtime": 0.5032,
      "eval_samples_per_second": 99.361,
      "eval_steps_per_second": 25.834,
      "step": 25
    },
    {
      "epoch": 0.08350898323798053,
      "grad_norm": 13.219664573669434,
      "learning_rate": 8.957804998855866e-05,
      "loss": 1.18,
      "step": 26
    },
    {
      "epoch": 0.08672086720867209,
      "grad_norm": 3.907947301864624,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.8817,
      "step": 27
    },
    {
      "epoch": 0.08993275117936364,
      "grad_norm": 2.1503279209136963,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.6689,
      "step": 28
    },
    {
      "epoch": 0.09314463515005521,
      "grad_norm": 1.8644012212753296,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.5879,
      "step": 29
    },
    {
      "epoch": 0.09635651912074676,
      "grad_norm": 5.081637859344482,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.6628,
      "step": 30
    },
    {
      "epoch": 0.09956840309143832,
      "grad_norm": 1.9498679637908936,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.4971,
      "step": 31
    },
    {
      "epoch": 0.10278028706212988,
      "grad_norm": 1.7911735773086548,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.5756,
      "step": 32
    },
    {
      "epoch": 0.10599217103282144,
      "grad_norm": 5.527887344360352,
      "learning_rate": 8.204865162773613e-05,
      "loss": 1.094,
      "step": 33
    },
    {
      "epoch": 0.109204055003513,
      "grad_norm": 1.6801953315734863,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.4828,
      "step": 34
    },
    {
      "epoch": 0.11241593897420456,
      "grad_norm": 2.1924173831939697,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.3928,
      "step": 35
    },
    {
      "epoch": 0.11562782294489611,
      "grad_norm": 2.8271541595458984,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.3965,
      "step": 36
    },
    {
      "epoch": 0.11883970691558768,
      "grad_norm": 1.9707531929016113,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.3363,
      "step": 37
    },
    {
      "epoch": 0.12205159088627923,
      "grad_norm": 2.6084580421447754,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.5723,
      "step": 38
    },
    {
      "epoch": 0.12526347485697079,
      "grad_norm": 2.948139190673828,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.7208,
      "step": 39
    },
    {
      "epoch": 0.12847535882766234,
      "grad_norm": 3.0574727058410645,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.5781,
      "step": 40
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 2.222038984298706,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.466,
      "step": 41
    },
    {
      "epoch": 0.13489912676904547,
      "grad_norm": 1.6518263816833496,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.3927,
      "step": 42
    },
    {
      "epoch": 0.13811101073973703,
      "grad_norm": 2.6922054290771484,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.5703,
      "step": 43
    },
    {
      "epoch": 0.14132289471042858,
      "grad_norm": 2.6648433208465576,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.5503,
      "step": 44
    },
    {
      "epoch": 0.14453477868112014,
      "grad_norm": 2.1673121452331543,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.7952,
      "step": 45
    },
    {
      "epoch": 0.14774666265181172,
      "grad_norm": 3.4408926963806152,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.6431,
      "step": 46
    },
    {
      "epoch": 0.15095854662250327,
      "grad_norm": 2.1872146129608154,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.4239,
      "step": 47
    },
    {
      "epoch": 0.15417043059319482,
      "grad_norm": 1.5436232089996338,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.4114,
      "step": 48
    },
    {
      "epoch": 0.15738231456388638,
      "grad_norm": 1.8399603366851807,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.3185,
      "step": 49
    },
    {
      "epoch": 0.16059419853457793,
      "grad_norm": 2.190896987915039,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.2297,
      "step": 50
    },
    {
      "epoch": 0.16059419853457793,
      "eval_loss": 0.5405478477478027,
      "eval_runtime": 0.5041,
      "eval_samples_per_second": 99.187,
      "eval_steps_per_second": 25.789,
      "step": 50
    },
    {
      "epoch": 0.16380608250526948,
      "grad_norm": 4.038471698760986,
      "learning_rate": 5.7231268960295e-05,
      "loss": 0.8339,
      "step": 51
    },
    {
      "epoch": 0.16701796647596107,
      "grad_norm": 2.3349921703338623,
      "learning_rate": 5.574402751448614e-05,
      "loss": 0.4534,
      "step": 52
    },
    {
      "epoch": 0.17022985044665262,
      "grad_norm": 1.8736135959625244,
      "learning_rate": 5.425597248551387e-05,
      "loss": 0.4491,
      "step": 53
    },
    {
      "epoch": 0.17344173441734417,
      "grad_norm": 2.2482573986053467,
      "learning_rate": 5.2768731039705e-05,
      "loss": 0.403,
      "step": 54
    },
    {
      "epoch": 0.17665361838803573,
      "grad_norm": 1.4259393215179443,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.3789,
      "step": 55
    },
    {
      "epoch": 0.17986550235872728,
      "grad_norm": 1.762160301208496,
      "learning_rate": 4.980319133636863e-05,
      "loss": 0.4335,
      "step": 56
    },
    {
      "epoch": 0.18307738632941886,
      "grad_norm": 1.4867217540740967,
      "learning_rate": 4.83281358529671e-05,
      "loss": 0.42,
      "step": 57
    },
    {
      "epoch": 0.18628927030011042,
      "grad_norm": 1.774482250213623,
      "learning_rate": 4.686037595505507e-05,
      "loss": 0.7633,
      "step": 58
    },
    {
      "epoch": 0.18950115427080197,
      "grad_norm": 1.6524527072906494,
      "learning_rate": 4.54015166165314e-05,
      "loss": 0.3312,
      "step": 59
    },
    {
      "epoch": 0.19271303824149352,
      "grad_norm": 1.7809213399887085,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.3048,
      "step": 60
    },
    {
      "epoch": 0.19592492221218508,
      "grad_norm": 0.9493484497070312,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 0.2782,
      "step": 61
    },
    {
      "epoch": 0.19913680618287663,
      "grad_norm": 1.6046050786972046,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.2086,
      "step": 62
    },
    {
      "epoch": 0.2023486901535682,
      "grad_norm": 4.323451042175293,
      "learning_rate": 3.968680715012606e-05,
      "loss": 0.5269,
      "step": 63
    },
    {
      "epoch": 0.20556057412425977,
      "grad_norm": 3.2167468070983887,
      "learning_rate": 3.829612379868006e-05,
      "loss": 0.5914,
      "step": 64
    },
    {
      "epoch": 0.20877245809495132,
      "grad_norm": 2.5836000442504883,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.3979,
      "step": 65
    },
    {
      "epoch": 0.21198434206564287,
      "grad_norm": 1.6577327251434326,
      "learning_rate": 3.557105414476782e-05,
      "loss": 0.2982,
      "step": 66
    },
    {
      "epoch": 0.21519622603633443,
      "grad_norm": 1.7948780059814453,
      "learning_rate": 3.423964766595906e-05,
      "loss": 0.353,
      "step": 67
    },
    {
      "epoch": 0.218408110007026,
      "grad_norm": 2.2538440227508545,
      "learning_rate": 3.293094232762715e-05,
      "loss": 0.4393,
      "step": 68
    },
    {
      "epoch": 0.22161999397771756,
      "grad_norm": 1.4487870931625366,
      "learning_rate": 3.164636917984534e-05,
      "loss": 0.3644,
      "step": 69
    },
    {
      "epoch": 0.22483187794840911,
      "grad_norm": 1.4857341051101685,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.5984,
      "step": 70
    },
    {
      "epoch": 0.22804376191910067,
      "grad_norm": 1.458071231842041,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 0.4983,
      "step": 71
    },
    {
      "epoch": 0.23125564588979222,
      "grad_norm": 1.4762952327728271,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 0.247,
      "step": 72
    },
    {
      "epoch": 0.2344675298604838,
      "grad_norm": 1.1881077289581299,
      "learning_rate": 2.677706386869083e-05,
      "loss": 0.2679,
      "step": 73
    },
    {
      "epoch": 0.23767941383117536,
      "grad_norm": 0.9410943984985352,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 0.1891,
      "step": 74
    },
    {
      "epoch": 0.2408912978018669,
      "grad_norm": 1.873358964920044,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.2224,
      "step": 75
    },
    {
      "epoch": 0.2408912978018669,
      "eval_loss": 0.3565179407596588,
      "eval_runtime": 0.503,
      "eval_samples_per_second": 99.395,
      "eval_steps_per_second": 25.843,
      "step": 75
    },
    {
      "epoch": 0.24410318177255846,
      "grad_norm": 2.8982174396514893,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 0.6377,
      "step": 76
    },
    {
      "epoch": 0.24731506574325002,
      "grad_norm": 2.408865451812744,
      "learning_rate": 2.2400865784401e-05,
      "loss": 0.4874,
      "step": 77
    },
    {
      "epoch": 0.25052694971394157,
      "grad_norm": 2.227947473526001,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 0.3836,
      "step": 78
    },
    {
      "epoch": 0.2537388336846331,
      "grad_norm": 1.9388247728347778,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 0.2834,
      "step": 79
    },
    {
      "epoch": 0.2569507176553247,
      "grad_norm": 1.9769359827041626,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.3367,
      "step": 80
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 2.0125112533569336,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.3863,
      "step": 81
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 1.9390735626220703,
      "learning_rate": 1.77396025983391e-05,
      "loss": 0.393,
      "step": 82
    },
    {
      "epoch": 0.2665863695673994,
      "grad_norm": 1.5394026041030884,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 0.6196,
      "step": 83
    },
    {
      "epoch": 0.26979825353809095,
      "grad_norm": 2.0069022178649902,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 0.3049,
      "step": 84
    },
    {
      "epoch": 0.2730101375087825,
      "grad_norm": 1.0801819562911987,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.2012,
      "step": 85
    },
    {
      "epoch": 0.27622202147947406,
      "grad_norm": 1.3949787616729736,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 0.2644,
      "step": 86
    },
    {
      "epoch": 0.2794339054501656,
      "grad_norm": 1.527002215385437,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 0.2278,
      "step": 87
    },
    {
      "epoch": 0.28264578942085716,
      "grad_norm": 1.6759589910507202,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 0.3889,
      "step": 88
    },
    {
      "epoch": 0.2858576733915487,
      "grad_norm": 2.828400135040283,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 0.5727,
      "step": 89
    },
    {
      "epoch": 0.28906955736224027,
      "grad_norm": 2.203261375427246,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.3116,
      "step": 90
    },
    {
      "epoch": 0.2922814413329318,
      "grad_norm": 1.2678191661834717,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 0.232,
      "step": 91
    },
    {
      "epoch": 0.29549332530362343,
      "grad_norm": 1.533488154411316,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 0.3384,
      "step": 92
    },
    {
      "epoch": 0.298705209274315,
      "grad_norm": 1.5737160444259644,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 0.3892,
      "step": 93
    },
    {
      "epoch": 0.30191709324500654,
      "grad_norm": 2.21943998336792,
      "learning_rate": 1.088290153563358e-05,
      "loss": 0.4123,
      "step": 94
    },
    {
      "epoch": 0.3051289772156981,
      "grad_norm": 1.0407116413116455,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.4279,
      "step": 95
    },
    {
      "epoch": 0.30834086118638965,
      "grad_norm": 1.2876520156860352,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 0.4044,
      "step": 96
    },
    {
      "epoch": 0.3115527451570812,
      "grad_norm": 1.4480308294296265,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 0.1674,
      "step": 97
    },
    {
      "epoch": 0.31476462912777275,
      "grad_norm": 0.8228076100349426,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 0.2878,
      "step": 98
    },
    {
      "epoch": 0.3179765130984643,
      "grad_norm": 1.4703351259231567,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 0.2122,
      "step": 99
    },
    {
      "epoch": 0.32118839706915586,
      "grad_norm": 0.9804506897926331,
      "learning_rate": 1e-05,
      "loss": 0.1397,
      "step": 100
    },
    {
      "epoch": 0.32118839706915586,
      "eval_loss": 0.33776161074638367,
      "eval_runtime": 0.5035,
      "eval_samples_per_second": 99.308,
      "eval_steps_per_second": 25.82,
      "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": 1.666832784162816e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}