{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06749915626054674,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006749915626054674,
      "grad_norm": 1.9157516362611204e-05,
      "learning_rate": 8.000000000000001e-06,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0006749915626054674,
      "eval_loss": 11.5,
      "eval_runtime": 11.0558,
      "eval_samples_per_second": 225.674,
      "eval_steps_per_second": 56.441,
      "step": 1
    },
    {
      "epoch": 0.0013499831252109348,
      "grad_norm": 2.201150346081704e-05,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0020249746878164025,
      "grad_norm": 1.953383798536379e-05,
      "learning_rate": 2.4e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0026999662504218697,
      "grad_norm": 1.975701525225304e-05,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0033749578130273373,
      "grad_norm": 2.441896685922984e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.004049949375632805,
      "grad_norm": 2.1600873878924176e-05,
      "learning_rate": 4.8e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.004724940938238272,
      "grad_norm": 2.630273229442537e-05,
      "learning_rate": 5.6e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.005399932500843739,
      "grad_norm": 2.1237785404082388e-05,
      "learning_rate": 6.400000000000001e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.006074924063449207,
      "grad_norm": 2.6038042051368393e-05,
      "learning_rate": 7.2e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 1.9523216906236485e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.007424907188660142,
      "grad_norm": 3.139385080430657e-05,
      "learning_rate": 7.999453219969877e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.00809989875126561,
      "grad_norm": 2.8158918212284334e-05,
      "learning_rate": 7.997813029363704e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.008774890313871077,
      "grad_norm": 1.8800117686623707e-05,
      "learning_rate": 7.99507987659322e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.009449881876476544,
      "grad_norm": 2.5126875698333606e-05,
      "learning_rate": 7.991254508875098e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.010124873439082012,
      "grad_norm": 2.2397709471988492e-05,
      "learning_rate": 7.98633797202668e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.010799865001687479,
      "grad_norm": 1.7211687008966692e-05,
      "learning_rate": 7.980331610180046e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.011474856564292946,
      "grad_norm": 2.2995038307271898e-05,
      "learning_rate": 7.973237065414553e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.012149848126898413,
      "grad_norm": 2.6865302061196417e-05,
      "learning_rate": 7.965056277307902e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.01282483968950388,
      "grad_norm": 3.483371983747929e-05,
      "learning_rate": 7.955791482405875e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.01349983125210935,
      "grad_norm": 3.103768176515587e-05,
      "learning_rate": 7.94544521361089e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.014174822814714817,
      "grad_norm": 4.7862751671345904e-05,
      "learning_rate": 7.93402029948953e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.014849814377320284,
      "grad_norm": 3.231195660191588e-05,
      "learning_rate": 7.921519863499239e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.015524805939925751,
      "grad_norm": 3.36208613589406e-05,
      "learning_rate": 7.907947323134398e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.01619979750253122,
      "grad_norm": 3.122496127616614e-05,
      "learning_rate": 7.893306388992023e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.016874789065136685,
      "grad_norm": 4.556611384032294e-05,
      "learning_rate": 7.877601063757323e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.017549780627742154,
      "grad_norm": 3.778899917961098e-05,
      "learning_rate": 7.860835641109395e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.01822477219034762,
      "grad_norm": 5.3873991419095546e-05,
      "learning_rate": 7.843014704547393e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.01889976375295309,
      "grad_norm": 4.7375739086419344e-05,
      "learning_rate": 7.824143126137431e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.019574755315558554,
      "grad_norm": 5.459750900627114e-05,
      "learning_rate": 7.804226065180615e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.020249746878164023,
      "grad_norm": 5.2733059419551864e-05,
      "learning_rate": 7.783268966802539e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.020924738440769492,
      "grad_norm": 6.106657383497804e-05,
      "learning_rate": 7.761277560464645e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.021599730003374958,
      "grad_norm": 5.731414785259403e-05,
      "learning_rate": 7.738257858397844e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.022274721565980427,
      "grad_norm": 5.25766663486138e-05,
      "learning_rate": 7.71421615395883e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.022949713128585892,
      "grad_norm": 6.520126044051722e-05,
      "learning_rate": 7.68915901990954e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.02362470469119136,
      "grad_norm": 6.199046765686944e-05,
      "learning_rate": 7.663093306620231e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.024299696253796826,
      "grad_norm": 6.82024983689189e-05,
      "learning_rate": 7.636026140196651e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.024974687816402295,
      "grad_norm": 5.999802306178026e-05,
      "learning_rate": 7.607964920531837e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.02564967937900776,
      "grad_norm": 6.861635483801365e-05,
      "learning_rate": 7.578917319283055e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.02632467094161323,
      "grad_norm": 6.790792394895107e-05,
      "learning_rate": 7.548891277774448e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.0269996625042187,
      "grad_norm": 5.505201261257753e-05,
      "learning_rate": 7.517895004825956e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.027674654066824164,
      "grad_norm": 0.00010721717990236357,
      "learning_rate": 7.48593697450911e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.028349645629429633,
      "grad_norm": 7.804264168953523e-05,
      "learning_rate": 7.453025923830296e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.0290246371920351,
      "grad_norm": 0.00016989179130177945,
      "learning_rate": 7.419170850342156e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.029699628754640568,
      "grad_norm": 0.00015660426288377494,
      "learning_rate": 7.384381009683742e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.030374620317246033,
      "grad_norm": 0.0001554411428514868,
      "learning_rate": 7.348665913050115e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.031049611879851502,
      "grad_norm": 9.427656186744571e-05,
      "learning_rate": 7.312035324592081e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.03172460344245697,
      "grad_norm": 0.00013080888311378658,
      "learning_rate": 7.274499258746771e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.03239959500506244,
      "grad_norm": 0.00012277769565116614,
      "learning_rate": 7.236067977499791e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.0330745865676679,
      "grad_norm": 0.0002552400401327759,
      "learning_rate": 7.196751987579699e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.03374957813027337,
      "grad_norm": 0.0002983387385029346,
      "learning_rate": 7.156562037585576e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.03374957813027337,
      "eval_loss": 11.5,
      "eval_runtime": 11.3501,
      "eval_samples_per_second": 219.821,
      "eval_steps_per_second": 54.977,
      "step": 50
    },
    {
      "epoch": 0.03442456969287884,
      "grad_norm": 5.4881169489817694e-05,
      "learning_rate": 7.11550911504845e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.03509956125548431,
      "grad_norm": 7.321939483517781e-05,
      "learning_rate": 7.073604443427437e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.03577455281808977,
      "grad_norm": 7.501189247705042e-05,
      "learning_rate": 7.03085947904134e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.03644954438069524,
      "grad_norm": 7.780554005876184e-05,
      "learning_rate": 6.987285907936617e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.03712453594330071,
      "grad_norm": 9.891616355162114e-05,
      "learning_rate": 6.942895642692527e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.03779952750590618,
      "grad_norm": 0.00010379558807471767,
      "learning_rate": 6.897700819164357e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.038474519068511646,
      "grad_norm": 6.376452802214772e-05,
      "learning_rate": 6.851713793165589e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.03914951063111711,
      "grad_norm": 0.00011976366658927873,
      "learning_rate": 6.804947137089955e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.03982450219372258,
      "grad_norm": 0.00011366497346898541,
      "learning_rate": 6.757413636474263e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.040499493756328046,
      "grad_norm": 0.00012407948088366538,
      "learning_rate": 6.709126286502965e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.041174485318933515,
      "grad_norm": 0.00011083694698754698,
      "learning_rate": 6.660098288455393e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.041849476881538984,
      "grad_norm": 0.00012434367090463638,
      "learning_rate": 6.610343046096674e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.042524468444144446,
      "grad_norm": 9.564027277519926e-05,
      "learning_rate": 6.559874162013267e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.043199460006749915,
      "grad_norm": 8.99869337445125e-05,
      "learning_rate": 6.508705433894149e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.043874451569355384,
      "grad_norm": 0.00011574227391975,
      "learning_rate": 6.456850850758673e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.04454944313196085,
      "grad_norm": 0.00011398899368941784,
      "learning_rate": 6.404324589132101e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.045224434694566315,
      "grad_norm": 8.823705138638616e-05,
      "learning_rate": 6.351141009169893e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.045899426257171784,
      "grad_norm": 0.0001269930216949433,
      "learning_rate": 6.297314650731775e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.04657441781977725,
      "grad_norm": 0.0001396976731484756,
      "learning_rate": 6.242860229406692e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.04724940938238272,
      "grad_norm": 0.0001476786273997277,
      "learning_rate": 6.18779263248971e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.04792440094498819,
      "grad_norm": 0.0001579802919877693,
      "learning_rate": 6.132126914911976e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.04859939250759365,
      "grad_norm": 0.00014366269169840962,
      "learning_rate": 6.075878295124861e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.04927438407019912,
      "grad_norm": 0.00015545522910542786,
      "learning_rate": 6.019062150939376e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.04994937563280459,
      "grad_norm": 0.00011848592112073675,
      "learning_rate": 5.9616940153220336e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.05062436719541006,
      "grad_norm": 0.00015544149209745228,
      "learning_rate": 5.903789572148295e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.05129935875801552,
      "grad_norm": 0.00016012511332519352,
      "learning_rate": 5.845364651914752e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.05197435032062099,
      "grad_norm": 0.00024290069995913655,
      "learning_rate": 5.786435227411227e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.05264934188322646,
      "grad_norm": 0.00016308229533024132,
      "learning_rate": 5.727017409353971e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.05332433344583193,
      "grad_norm": 0.0001312433450948447,
      "learning_rate": 5.667127441981162e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.0539993250084374,
      "grad_norm": 0.00020814283925574273,
      "learning_rate": 5.606781698611879e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.05467431657104286,
      "grad_norm": 0.00017544587899465114,
      "learning_rate": 5.5459966771698096e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.05534930813364833,
      "grad_norm": 0.00021598087914753705,
      "learning_rate": 5.4847889956728834e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.0560242996962538,
      "grad_norm": 0.00022435332357417792,
      "learning_rate": 5.423175387690067e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.056699291258859266,
      "grad_norm": 0.00025759119307622313,
      "learning_rate": 5.361172697766573e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.05737428282146473,
      "grad_norm": 0.00027369000599719584,
      "learning_rate": 5.298797876818735e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.0580492743840702,
      "grad_norm": 0.00021083872707094997,
      "learning_rate": 5.23606797749979e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.058724265946675666,
      "grad_norm": 0.00017781296628527343,
      "learning_rate": 5.17300014953786e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.059399257509281135,
      "grad_norm": 0.0002701023768167943,
      "learning_rate": 5.109611635047379e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.060074249071886604,
      "grad_norm": 0.00020761927589774132,
      "learning_rate": 5.04591976381528e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.060749240634492066,
      "grad_norm": 0.0002119742421200499,
      "learning_rate": 4.981941948563197e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.061424232197097535,
      "grad_norm": 0.0003119312459602952,
      "learning_rate": 4.9176956801870065e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.062099223759703004,
      "grad_norm": 0.00029339047614485025,
      "learning_rate": 4.853198522974988e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.06277421532230847,
      "grad_norm": 0.00024452415527775884,
      "learning_rate": 4.788468109805921e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.06344920688491394,
      "grad_norm": 0.00024892069632187486,
      "learning_rate": 4.7235221373284407e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.0641241984475194,
      "grad_norm": 0.00032684431062079966,
      "learning_rate": 4.658378361122936e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.06479919001012488,
      "grad_norm": 0.00033167307265102863,
      "learning_rate": 4.593054590847368e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.06547418157273034,
      "grad_norm": 0.00021435694361571223,
      "learning_rate": 4.5275686853682765e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.0661491731353358,
      "grad_norm": 0.00033286900725215673,
      "learning_rate": 4.4619385478783456e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.06682416469794128,
      "grad_norm": 0.0003271261812187731,
      "learning_rate": 4.396182121001852e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.06749915626054674,
      "grad_norm": 0.0008189138607122004,
      "learning_rate": 4.33031738188933e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.06749915626054674,
      "eval_loss": 11.5,
      "eval_runtime": 11.1305,
      "eval_samples_per_second": 224.16,
      "eval_steps_per_second": 56.062,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 16079231385600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}