{
  "best_metric": 10.334551811218262,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 2.453591606133979,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0258272800645682,
      "grad_norm": 0.14458106458187103,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3967,
      "step": 1
    },
    {
      "epoch": 0.0258272800645682,
      "eval_loss": 10.38502311706543,
      "eval_runtime": 0.1482,
      "eval_samples_per_second": 337.285,
      "eval_steps_per_second": 87.694,
      "step": 1
    },
    {
      "epoch": 0.0516545601291364,
      "grad_norm": 0.19388781487941742,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.4055,
      "step": 2
    },
    {
      "epoch": 0.0774818401937046,
      "grad_norm": 0.13940967619419098,
      "learning_rate": 0.0001,
      "loss": 10.3947,
      "step": 3
    },
    {
      "epoch": 0.1033091202582728,
      "grad_norm": 0.12940029799938202,
      "learning_rate": 9.997376600647783e-05,
      "loss": 10.39,
      "step": 4
    },
    {
      "epoch": 0.129136400322841,
      "grad_norm": 0.12409521639347076,
      "learning_rate": 9.989509461357426e-05,
      "loss": 10.383,
      "step": 5
    },
    {
      "epoch": 0.1549636803874092,
      "grad_norm": 0.11843808740377426,
      "learning_rate": 9.976407754861426e-05,
      "loss": 10.3812,
      "step": 6
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 0.11526809632778168,
      "learning_rate": 9.958086757163489e-05,
      "loss": 10.3722,
      "step": 7
    },
    {
      "epoch": 0.2066182405165456,
      "grad_norm": 0.11756883561611176,
      "learning_rate": 9.934567829727386e-05,
      "loss": 10.3561,
      "step": 8
    },
    {
      "epoch": 0.2324455205811138,
      "grad_norm": 0.14288835227489471,
      "learning_rate": 9.905878394570453e-05,
      "loss": 10.3812,
      "step": 9
    },
    {
      "epoch": 0.258272800645682,
      "grad_norm": 0.1054273471236229,
      "learning_rate": 9.872051902290737e-05,
      "loss": 10.3776,
      "step": 10
    },
    {
      "epoch": 0.2841000807102502,
      "grad_norm": 0.21361760795116425,
      "learning_rate": 9.833127793065098e-05,
      "loss": 10.4013,
      "step": 11
    },
    {
      "epoch": 0.3099273607748184,
      "grad_norm": 0.13051673769950867,
      "learning_rate": 9.789151450663723e-05,
      "loss": 10.3836,
      "step": 12
    },
    {
      "epoch": 0.3357546408393866,
      "grad_norm": 0.13624922931194305,
      "learning_rate": 9.740174149534693e-05,
      "loss": 10.3847,
      "step": 13
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 0.13448677957057953,
      "learning_rate": 9.686252995020249e-05,
      "loss": 10.3821,
      "step": 14
    },
    {
      "epoch": 0.387409200968523,
      "grad_norm": 0.13489721715450287,
      "learning_rate": 9.627450856774539e-05,
      "loss": 10.3781,
      "step": 15
    },
    {
      "epoch": 0.4132364810330912,
      "grad_norm": 0.11860419064760208,
      "learning_rate": 9.563836295460398e-05,
      "loss": 10.3716,
      "step": 16
    },
    {
      "epoch": 0.4390637610976594,
      "grad_norm": 0.12369117885828018,
      "learning_rate": 9.495483482810688e-05,
      "loss": 10.357,
      "step": 17
    },
    {
      "epoch": 0.4648910411622276,
      "grad_norm": 0.12533077597618103,
      "learning_rate": 9.422472115147382e-05,
      "loss": 10.3728,
      "step": 18
    },
    {
      "epoch": 0.4907183212267958,
      "grad_norm": 0.1503569632768631,
      "learning_rate": 9.3448873204592e-05,
      "loss": 10.3781,
      "step": 19
    },
    {
      "epoch": 0.516545601291364,
      "grad_norm": 0.1492878496646881,
      "learning_rate": 9.2628195591462e-05,
      "loss": 10.3794,
      "step": 20
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.2185596376657486,
      "learning_rate": 9.176364518546989e-05,
      "loss": 10.3976,
      "step": 21
    },
    {
      "epoch": 0.5682001614205004,
      "grad_norm": 0.14859223365783691,
      "learning_rate": 9.08562300137157e-05,
      "loss": 10.3817,
      "step": 22
    },
    {
      "epoch": 0.5940274414850686,
      "grad_norm": 0.14766570925712585,
      "learning_rate": 8.990700808169889e-05,
      "loss": 10.376,
      "step": 23
    },
    {
      "epoch": 0.6198547215496368,
      "grad_norm": 0.14743873476982117,
      "learning_rate": 8.891708613973126e-05,
      "loss": 10.3707,
      "step": 24
    },
    {
      "epoch": 0.645682001614205,
      "grad_norm": 0.14462894201278687,
      "learning_rate": 8.788761839251559e-05,
      "loss": 10.3691,
      "step": 25
    },
    {
      "epoch": 0.645682001614205,
      "eval_loss": 10.3701753616333,
      "eval_runtime": 0.141,
      "eval_samples_per_second": 354.551,
      "eval_steps_per_second": 92.183,
      "step": 25
    },
    {
      "epoch": 0.6715092816787732,
      "grad_norm": 0.13384991884231567,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3578,
      "step": 26
    },
    {
      "epoch": 0.6973365617433414,
      "grad_norm": 0.12744058668613434,
      "learning_rate": 8.571489144483944e-05,
      "loss": 10.3495,
      "step": 27
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 0.1669607311487198,
      "learning_rate": 8.457416554680877e-05,
      "loss": 10.3762,
      "step": 28
    },
    {
      "epoch": 0.7489911218724778,
      "grad_norm": 0.12546218931674957,
      "learning_rate": 8.339895749467238e-05,
      "loss": 10.3638,
      "step": 29
    },
    {
      "epoch": 0.774818401937046,
      "grad_norm": 0.2545466721057892,
      "learning_rate": 8.219063752844926e-05,
      "loss": 10.3936,
      "step": 30
    },
    {
      "epoch": 0.8006456820016142,
      "grad_norm": 0.19755293428897858,
      "learning_rate": 8.095061449516903e-05,
      "loss": 10.3783,
      "step": 31
    },
    {
      "epoch": 0.8264729620661824,
      "grad_norm": 0.1928538680076599,
      "learning_rate": 7.968033420621935e-05,
      "loss": 10.372,
      "step": 32
    },
    {
      "epoch": 0.8523002421307506,
      "grad_norm": 0.18659983575344086,
      "learning_rate": 7.838127775159452e-05,
      "loss": 10.3674,
      "step": 33
    },
    {
      "epoch": 0.8781275221953188,
      "grad_norm": 0.1749713122844696,
      "learning_rate": 7.705495977301078e-05,
      "loss": 10.3609,
      "step": 34
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 0.1704954355955124,
      "learning_rate": 7.570292669790186e-05,
      "loss": 10.3566,
      "step": 35
    },
    {
      "epoch": 0.9297820823244553,
      "grad_norm": 0.16353993117809296,
      "learning_rate": 7.43267549363537e-05,
      "loss": 10.3469,
      "step": 36
    },
    {
      "epoch": 0.9556093623890234,
      "grad_norm": 0.13135264813899994,
      "learning_rate": 7.292804904308087e-05,
      "loss": 10.3572,
      "step": 37
    },
    {
      "epoch": 0.9814366424535916,
      "grad_norm": 0.1786571592092514,
      "learning_rate": 7.150843984658754e-05,
      "loss": 10.3632,
      "step": 38
    },
    {
      "epoch": 1.0072639225181599,
      "grad_norm": 0.24464179575443268,
      "learning_rate": 7.006958254769438e-05,
      "loss": 14.0365,
      "step": 39
    },
    {
      "epoch": 1.033091202582728,
      "grad_norm": 0.24344998598098755,
      "learning_rate": 6.861315478964841e-05,
      "loss": 8.8539,
      "step": 40
    },
    {
      "epoch": 1.0589184826472962,
      "grad_norm": 0.26347535848617554,
      "learning_rate": 6.714085470206609e-05,
      "loss": 11.0519,
      "step": 41
    },
    {
      "epoch": 1.0847457627118644,
      "grad_norm": 0.25414544343948364,
      "learning_rate": 6.56543989209901e-05,
      "loss": 10.6151,
      "step": 42
    },
    {
      "epoch": 1.1105730427764327,
      "grad_norm": 0.22299374639987946,
      "learning_rate": 6.415552058736854e-05,
      "loss": 10.2404,
      "step": 43
    },
    {
      "epoch": 1.136400322841001,
      "grad_norm": 0.21534107625484467,
      "learning_rate": 6.264596732629e-05,
      "loss": 10.2576,
      "step": 44
    },
    {
      "epoch": 1.162227602905569,
      "grad_norm": 0.20723971724510193,
      "learning_rate": 6.112749920933111e-05,
      "loss": 10.3462,
      "step": 45
    },
    {
      "epoch": 1.1880548829701372,
      "grad_norm": 0.1938544362783432,
      "learning_rate": 5.960188670239154e-05,
      "loss": 10.2931,
      "step": 46
    },
    {
      "epoch": 1.2138821630347054,
      "grad_norm": 0.15806801617145538,
      "learning_rate": 5.80709086014102e-05,
      "loss": 10.4001,
      "step": 47
    },
    {
      "epoch": 1.2397094430992737,
      "grad_norm": 0.19093284010887146,
      "learning_rate": 5.653634995836856e-05,
      "loss": 10.6704,
      "step": 48
    },
    {
      "epoch": 1.2655367231638417,
      "grad_norm": 0.21306897699832916,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.0519,
      "step": 49
    },
    {
      "epoch": 1.29136400322841,
      "grad_norm": 0.3307248055934906,
      "learning_rate": 5.346365004163145e-05,
      "loss": 9.1488,
      "step": 50
    },
    {
      "epoch": 1.29136400322841,
      "eval_loss": 10.350641250610352,
      "eval_runtime": 0.148,
      "eval_samples_per_second": 337.788,
      "eval_steps_per_second": 87.825,
      "step": 50
    },
    {
      "epoch": 1.3171912832929782,
      "grad_norm": 0.267697274684906,
      "learning_rate": 5.192909139858981e-05,
      "loss": 10.5383,
      "step": 51
    },
    {
      "epoch": 1.3430185633575464,
      "grad_norm": 0.26058173179626465,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 10.4676,
      "step": 52
    },
    {
      "epoch": 1.3688458434221147,
      "grad_norm": 0.2508196532726288,
      "learning_rate": 4.887250079066892e-05,
      "loss": 10.2719,
      "step": 53
    },
    {
      "epoch": 1.3946731234866827,
      "grad_norm": 0.25303545594215393,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 10.3154,
      "step": 54
    },
    {
      "epoch": 1.420500403551251,
      "grad_norm": 0.23569032549858093,
      "learning_rate": 4.584447941263149e-05,
      "loss": 10.3523,
      "step": 55
    },
    {
      "epoch": 1.4463276836158192,
      "grad_norm": 0.23108288645744324,
      "learning_rate": 4.43456010790099e-05,
      "loss": 10.0447,
      "step": 56
    },
    {
      "epoch": 1.4721549636803875,
      "grad_norm": 0.20212367177009583,
      "learning_rate": 4.285914529793391e-05,
      "loss": 10.7471,
      "step": 57
    },
    {
      "epoch": 1.4979822437449557,
      "grad_norm": 0.17680847644805908,
      "learning_rate": 4.13868452103516e-05,
      "loss": 10.8458,
      "step": 58
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.3306703269481659,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 9.1983,
      "step": 59
    },
    {
      "epoch": 1.549636803874092,
      "grad_norm": 0.3741892874240875,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 10.8048,
      "step": 60
    },
    {
      "epoch": 1.5754640839386602,
      "grad_norm": 0.30580583214759827,
      "learning_rate": 3.707195095691913e-05,
      "loss": 10.3987,
      "step": 61
    },
    {
      "epoch": 1.6012913640032282,
      "grad_norm": 0.3070525527000427,
      "learning_rate": 3.567324506364632e-05,
      "loss": 10.4791,
      "step": 62
    },
    {
      "epoch": 1.6271186440677967,
      "grad_norm": 0.29894793033599854,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 10.3912,
      "step": 63
    },
    {
      "epoch": 1.6529459241323647,
      "grad_norm": 0.2760533392429352,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 10.2197,
      "step": 64
    },
    {
      "epoch": 1.678773204196933,
      "grad_norm": 0.2583504617214203,
      "learning_rate": 3.16187222484055e-05,
      "loss": 10.3224,
      "step": 65
    },
    {
      "epoch": 1.7046004842615012,
      "grad_norm": 0.18513259291648865,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 10.3208,
      "step": 66
    },
    {
      "epoch": 1.7304277643260693,
      "grad_norm": 0.21538212895393372,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 10.6184,
      "step": 67
    },
    {
      "epoch": 1.7562550443906377,
      "grad_norm": 0.28359174728393555,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 11.2688,
      "step": 68
    },
    {
      "epoch": 1.7820823244552058,
      "grad_norm": 0.46082407236099243,
      "learning_rate": 2.660104250532764e-05,
      "loss": 8.871,
      "step": 69
    },
    {
      "epoch": 1.807909604519774,
      "grad_norm": 0.33902662992477417,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 10.7785,
      "step": 70
    },
    {
      "epoch": 1.8337368845843423,
      "grad_norm": 0.31501203775405884,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 10.1366,
      "step": 71
    },
    {
      "epoch": 1.8595641646489103,
      "grad_norm": 0.33076632022857666,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3689,
      "step": 72
    },
    {
      "epoch": 1.8853914447134787,
      "grad_norm": 0.3075948655605316,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 10.381,
      "step": 73
    },
    {
      "epoch": 1.9112187247780468,
      "grad_norm": 0.2850956618785858,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 10.3407,
      "step": 74
    },
    {
      "epoch": 1.937046004842615,
      "grad_norm": 0.26673322916030884,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 10.0383,
      "step": 75
    },
    {
      "epoch": 1.937046004842615,
      "eval_loss": 10.334551811218262,
      "eval_runtime": 0.1424,
      "eval_samples_per_second": 351.006,
      "eval_steps_per_second": 91.262,
      "step": 75
    },
    {
      "epoch": 1.9628732849071833,
      "grad_norm": 0.20866307616233826,
      "learning_rate": 1.91437699862843e-05,
      "loss": 10.7531,
      "step": 76
    },
    {
      "epoch": 1.9887005649717513,
      "grad_norm": 0.20063051581382751,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 10.9387,
      "step": 77
    },
    {
      "epoch": 2.0145278450363198,
      "grad_norm": 0.3508239686489105,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 13.3289,
      "step": 78
    },
    {
      "epoch": 2.040355125100888,
      "grad_norm": 0.4250504672527313,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 8.3424,
      "step": 79
    },
    {
      "epoch": 2.066182405165456,
      "grad_norm": 0.39901620149612427,
      "learning_rate": 1.577527884852619e-05,
      "loss": 11.4688,
      "step": 80
    },
    {
      "epoch": 2.0920096852300243,
      "grad_norm": 0.3271302878856659,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 10.3724,
      "step": 81
    },
    {
      "epoch": 2.1178369652945923,
      "grad_norm": 0.336497038602829,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 10.2999,
      "step": 82
    },
    {
      "epoch": 2.143664245359161,
      "grad_norm": 0.3253435790538788,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 10.3855,
      "step": 83
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.29757609963417053,
      "learning_rate": 1.313747004979751e-05,
      "loss": 10.371,
      "step": 84
    },
    {
      "epoch": 2.195318805488297,
      "grad_norm": 0.2762691378593445,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 10.1709,
      "step": 85
    },
    {
      "epoch": 2.2211460855528653,
      "grad_norm": 0.19564643502235413,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 10.4328,
      "step": 86
    },
    {
      "epoch": 2.2469733656174333,
      "grad_norm": 0.24298599362373352,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 10.5657,
      "step": 87
    },
    {
      "epoch": 2.272800645682002,
      "grad_norm": 0.4188690781593323,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 10.8609,
      "step": 88
    },
    {
      "epoch": 2.29862792574657,
      "grad_norm": 0.4041149914264679,
      "learning_rate": 1.094121605429547e-05,
      "loss": 9.6247,
      "step": 89
    },
    {
      "epoch": 2.324455205811138,
      "grad_norm": 0.3442460298538208,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 10.1798,
      "step": 90
    },
    {
      "epoch": 2.3502824858757063,
      "grad_norm": 0.3444257974624634,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 10.4936,
      "step": 91
    },
    {
      "epoch": 2.3761097659402743,
      "grad_norm": 0.31269723176956177,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 10.264,
      "step": 92
    },
    {
      "epoch": 2.401937046004843,
      "grad_norm": 0.30598893761634827,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 10.3978,
      "step": 93
    },
    {
      "epoch": 2.427764326069411,
      "grad_norm": 0.29670581221580505,
      "learning_rate": 1.002623399352217e-05,
      "loss": 10.2726,
      "step": 94
    },
    {
      "epoch": 2.453591606133979,
      "grad_norm": 0.2217765897512436,
      "learning_rate": 1e-05,
      "loss": 10.093,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 94858219945984.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}