{
  "best_metric": 11.925982475280762,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.05379007714629486,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005662113383820511,
      "grad_norm": 0.013953766785562038,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 11.9292,
      "step": 1
    },
    {
      "epoch": 0.0005662113383820511,
      "eval_loss": 11.930351257324219,
      "eval_runtime": 0.167,
      "eval_samples_per_second": 299.345,
      "eval_steps_per_second": 77.83,
      "step": 1
    },
    {
      "epoch": 0.0011324226767641021,
      "grad_norm": 0.013790151104331017,
      "learning_rate": 6.666666666666667e-05,
      "loss": 11.9302,
      "step": 2
    },
    {
      "epoch": 0.0016986340151461533,
      "grad_norm": 0.016090799123048782,
      "learning_rate": 0.0001,
      "loss": 11.9294,
      "step": 3
    },
    {
      "epoch": 0.0022648453535282042,
      "grad_norm": 0.01473537739366293,
      "learning_rate": 9.997376600647783e-05,
      "loss": 11.9304,
      "step": 4
    },
    {
      "epoch": 0.0028310566919102554,
      "grad_norm": 0.01676877774298191,
      "learning_rate": 9.989509461357426e-05,
      "loss": 11.9312,
      "step": 5
    },
    {
      "epoch": 0.0033972680302923066,
      "grad_norm": 0.016732048243284225,
      "learning_rate": 9.976407754861426e-05,
      "loss": 11.9308,
      "step": 6
    },
    {
      "epoch": 0.003963479368674357,
      "grad_norm": 0.018546266481280327,
      "learning_rate": 9.958086757163489e-05,
      "loss": 11.929,
      "step": 7
    },
    {
      "epoch": 0.0045296907070564085,
      "grad_norm": 0.020338336005806923,
      "learning_rate": 9.934567829727386e-05,
      "loss": 11.9303,
      "step": 8
    },
    {
      "epoch": 0.00509590204543846,
      "grad_norm": 0.01960534043610096,
      "learning_rate": 9.905878394570453e-05,
      "loss": 11.9315,
      "step": 9
    },
    {
      "epoch": 0.005662113383820511,
      "grad_norm": 0.020073408260941505,
      "learning_rate": 9.872051902290737e-05,
      "loss": 11.9293,
      "step": 10
    },
    {
      "epoch": 0.006228324722202562,
      "grad_norm": 0.02526913955807686,
      "learning_rate": 9.833127793065098e-05,
      "loss": 11.9297,
      "step": 11
    },
    {
      "epoch": 0.006794536060584613,
      "grad_norm": 0.024866905063390732,
      "learning_rate": 9.789151450663723e-05,
      "loss": 11.9327,
      "step": 12
    },
    {
      "epoch": 0.007360747398966664,
      "grad_norm": 0.01540751475840807,
      "learning_rate": 9.740174149534693e-05,
      "loss": 11.9287,
      "step": 13
    },
    {
      "epoch": 0.007926958737348715,
      "grad_norm": 0.012520595453679562,
      "learning_rate": 9.686252995020249e-05,
      "loss": 11.93,
      "step": 14
    },
    {
      "epoch": 0.008493170075730767,
      "grad_norm": 0.013276130892336369,
      "learning_rate": 9.627450856774539e-05,
      "loss": 11.9295,
      "step": 15
    },
    {
      "epoch": 0.009059381414112817,
      "grad_norm": 0.018443942070007324,
      "learning_rate": 9.563836295460398e-05,
      "loss": 11.93,
      "step": 16
    },
    {
      "epoch": 0.009625592752494869,
      "grad_norm": 0.016834240406751633,
      "learning_rate": 9.495483482810688e-05,
      "loss": 11.9297,
      "step": 17
    },
    {
      "epoch": 0.01019180409087692,
      "grad_norm": 0.018165774643421173,
      "learning_rate": 9.422472115147382e-05,
      "loss": 11.9287,
      "step": 18
    },
    {
      "epoch": 0.010758015429258971,
      "grad_norm": 0.022725488990545273,
      "learning_rate": 9.3448873204592e-05,
      "loss": 11.93,
      "step": 19
    },
    {
      "epoch": 0.011324226767641022,
      "grad_norm": 0.017869580537080765,
      "learning_rate": 9.2628195591462e-05,
      "loss": 11.9321,
      "step": 20
    },
    {
      "epoch": 0.011890438106023074,
      "grad_norm": 0.018510721623897552,
      "learning_rate": 9.176364518546989e-05,
      "loss": 11.9297,
      "step": 21
    },
    {
      "epoch": 0.012456649444405124,
      "grad_norm": 0.02430478297173977,
      "learning_rate": 9.08562300137157e-05,
      "loss": 11.9293,
      "step": 22
    },
    {
      "epoch": 0.013022860782787176,
      "grad_norm": 0.02443353272974491,
      "learning_rate": 8.990700808169889e-05,
      "loss": 11.929,
      "step": 23
    },
    {
      "epoch": 0.013589072121169226,
      "grad_norm": 0.02545754238963127,
      "learning_rate": 8.891708613973126e-05,
      "loss": 11.9323,
      "step": 24
    },
    {
      "epoch": 0.014155283459551277,
      "grad_norm": 0.03127404302358627,
      "learning_rate": 8.788761839251559e-05,
      "loss": 11.9303,
      "step": 25
    },
    {
      "epoch": 0.014155283459551277,
      "eval_loss": 11.929224967956543,
      "eval_runtime": 0.1802,
      "eval_samples_per_second": 277.538,
      "eval_steps_per_second": 72.16,
      "step": 25
    },
    {
      "epoch": 0.014721494797933329,
      "grad_norm": 0.012647237628698349,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9297,
      "step": 26
    },
    {
      "epoch": 0.015287706136315379,
      "grad_norm": 0.015734661370515823,
      "learning_rate": 8.571489144483944e-05,
      "loss": 11.9291,
      "step": 27
    },
    {
      "epoch": 0.01585391747469743,
      "grad_norm": 0.017150381579995155,
      "learning_rate": 8.457416554680877e-05,
      "loss": 11.9295,
      "step": 28
    },
    {
      "epoch": 0.01642012881307948,
      "grad_norm": 0.020637271925807,
      "learning_rate": 8.339895749467238e-05,
      "loss": 11.9292,
      "step": 29
    },
    {
      "epoch": 0.016986340151461533,
      "grad_norm": 0.018464168533682823,
      "learning_rate": 8.219063752844926e-05,
      "loss": 11.9282,
      "step": 30
    },
    {
      "epoch": 0.017552551489843585,
      "grad_norm": 0.020926039665937424,
      "learning_rate": 8.095061449516903e-05,
      "loss": 11.9294,
      "step": 31
    },
    {
      "epoch": 0.018118762828225634,
      "grad_norm": 0.02240375615656376,
      "learning_rate": 7.968033420621935e-05,
      "loss": 11.9286,
      "step": 32
    },
    {
      "epoch": 0.018684974166607686,
      "grad_norm": 0.02602965198457241,
      "learning_rate": 7.838127775159452e-05,
      "loss": 11.9302,
      "step": 33
    },
    {
      "epoch": 0.019251185504989738,
      "grad_norm": 0.024349767714738846,
      "learning_rate": 7.705495977301078e-05,
      "loss": 11.9309,
      "step": 34
    },
    {
      "epoch": 0.01981739684337179,
      "grad_norm": 0.028244735673069954,
      "learning_rate": 7.570292669790186e-05,
      "loss": 11.9283,
      "step": 35
    },
    {
      "epoch": 0.02038360818175384,
      "grad_norm": 0.030170924961566925,
      "learning_rate": 7.43267549363537e-05,
      "loss": 11.9298,
      "step": 36
    },
    {
      "epoch": 0.02094981952013589,
      "grad_norm": 0.03267698734998703,
      "learning_rate": 7.292804904308087e-05,
      "loss": 11.9284,
      "step": 37
    },
    {
      "epoch": 0.021516030858517943,
      "grad_norm": 0.020892078056931496,
      "learning_rate": 7.150843984658754e-05,
      "loss": 11.9295,
      "step": 38
    },
    {
      "epoch": 0.02208224219689999,
      "grad_norm": 0.021916329860687256,
      "learning_rate": 7.006958254769438e-05,
      "loss": 11.9294,
      "step": 39
    },
    {
      "epoch": 0.022648453535282043,
      "grad_norm": 0.020233944058418274,
      "learning_rate": 6.861315478964841e-05,
      "loss": 11.9292,
      "step": 40
    },
    {
      "epoch": 0.023214664873664095,
      "grad_norm": 0.019477376714348793,
      "learning_rate": 6.714085470206609e-05,
      "loss": 11.9283,
      "step": 41
    },
    {
      "epoch": 0.023780876212046147,
      "grad_norm": 0.02245022915303707,
      "learning_rate": 6.56543989209901e-05,
      "loss": 11.9279,
      "step": 42
    },
    {
      "epoch": 0.024347087550428196,
      "grad_norm": 0.025973478332161903,
      "learning_rate": 6.415552058736854e-05,
      "loss": 11.9285,
      "step": 43
    },
    {
      "epoch": 0.024913298888810248,
      "grad_norm": 0.027722090482711792,
      "learning_rate": 6.264596732629e-05,
      "loss": 11.9288,
      "step": 44
    },
    {
      "epoch": 0.0254795102271923,
      "grad_norm": 0.028943056240677834,
      "learning_rate": 6.112749920933111e-05,
      "loss": 11.9274,
      "step": 45
    },
    {
      "epoch": 0.026045721565574352,
      "grad_norm": 0.025688176974654198,
      "learning_rate": 5.960188670239154e-05,
      "loss": 11.9279,
      "step": 46
    },
    {
      "epoch": 0.0266119329039564,
      "grad_norm": 0.03459373489022255,
      "learning_rate": 5.80709086014102e-05,
      "loss": 11.9283,
      "step": 47
    },
    {
      "epoch": 0.027178144242338453,
      "grad_norm": 0.034123897552490234,
      "learning_rate": 5.653634995836856e-05,
      "loss": 11.9279,
      "step": 48
    },
    {
      "epoch": 0.027744355580720505,
      "grad_norm": 0.03610537573695183,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9265,
      "step": 49
    },
    {
      "epoch": 0.028310566919102553,
      "grad_norm": 0.043514493852853775,
      "learning_rate": 5.346365004163145e-05,
      "loss": 11.9264,
      "step": 50
    },
    {
      "epoch": 0.028310566919102553,
      "eval_loss": 11.927395820617676,
      "eval_runtime": 0.1723,
      "eval_samples_per_second": 290.181,
      "eval_steps_per_second": 75.447,
      "step": 50
    },
    {
      "epoch": 0.028876778257484605,
      "grad_norm": 0.019224930554628372,
      "learning_rate": 5.192909139858981e-05,
      "loss": 11.9278,
      "step": 51
    },
    {
      "epoch": 0.029442989595866657,
      "grad_norm": 0.025018585845828056,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 11.9295,
      "step": 52
    },
    {
      "epoch": 0.03000920093424871,
      "grad_norm": 0.02429080568253994,
      "learning_rate": 4.887250079066892e-05,
      "loss": 11.9275,
      "step": 53
    },
    {
      "epoch": 0.030575412272630758,
      "grad_norm": 0.024529896676540375,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 11.9274,
      "step": 54
    },
    {
      "epoch": 0.03114162361101281,
      "grad_norm": 0.027298960834741592,
      "learning_rate": 4.584447941263149e-05,
      "loss": 11.9275,
      "step": 55
    },
    {
      "epoch": 0.03170783494939486,
      "grad_norm": 0.028562380000948906,
      "learning_rate": 4.43456010790099e-05,
      "loss": 11.9283,
      "step": 56
    },
    {
      "epoch": 0.032274046287776914,
      "grad_norm": 0.03158874437212944,
      "learning_rate": 4.285914529793391e-05,
      "loss": 11.9261,
      "step": 57
    },
    {
      "epoch": 0.03284025762615896,
      "grad_norm": 0.027021652087569237,
      "learning_rate": 4.13868452103516e-05,
      "loss": 11.9292,
      "step": 58
    },
    {
      "epoch": 0.03340646896454102,
      "grad_norm": 0.030148476362228394,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 11.9276,
      "step": 59
    },
    {
      "epoch": 0.03397268030292307,
      "grad_norm": 0.03393995761871338,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 11.9276,
      "step": 60
    },
    {
      "epoch": 0.034538891641305115,
      "grad_norm": 0.03766351938247681,
      "learning_rate": 3.707195095691913e-05,
      "loss": 11.9288,
      "step": 61
    },
    {
      "epoch": 0.03510510297968717,
      "grad_norm": 0.04133583977818489,
      "learning_rate": 3.567324506364632e-05,
      "loss": 11.9268,
      "step": 62
    },
    {
      "epoch": 0.03567131431806922,
      "grad_norm": 0.027467934414744377,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 11.9259,
      "step": 63
    },
    {
      "epoch": 0.03623752565645127,
      "grad_norm": 0.027041316032409668,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 11.9287,
      "step": 64
    },
    {
      "epoch": 0.03680373699483332,
      "grad_norm": 0.0271934624761343,
      "learning_rate": 3.16187222484055e-05,
      "loss": 11.9281,
      "step": 65
    },
    {
      "epoch": 0.03736994833321537,
      "grad_norm": 0.027144378051161766,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 11.9272,
      "step": 66
    },
    {
      "epoch": 0.03793615967159742,
      "grad_norm": 0.03089400939643383,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 11.9273,
      "step": 67
    },
    {
      "epoch": 0.038502371009979476,
      "grad_norm": 0.03256877884268761,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 11.9265,
      "step": 68
    },
    {
      "epoch": 0.039068582348361525,
      "grad_norm": 0.037180133163928986,
      "learning_rate": 2.660104250532764e-05,
      "loss": 11.9273,
      "step": 69
    },
    {
      "epoch": 0.03963479368674358,
      "grad_norm": 0.03133248910307884,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 11.9266,
      "step": 70
    },
    {
      "epoch": 0.04020100502512563,
      "grad_norm": 0.036548782140016556,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 11.928,
      "step": 71
    },
    {
      "epoch": 0.04076721636350768,
      "grad_norm": 0.04202922433614731,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.929,
      "step": 72
    },
    {
      "epoch": 0.04133342770188973,
      "grad_norm": 0.03880568593740463,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 11.9272,
      "step": 73
    },
    {
      "epoch": 0.04189963904027178,
      "grad_norm": 0.04478525370359421,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 11.9271,
      "step": 74
    },
    {
      "epoch": 0.04246585037865383,
      "grad_norm": 0.05667252466082573,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 11.9239,
      "step": 75
    },
    {
      "epoch": 0.04246585037865383,
      "eval_loss": 11.925982475280762,
      "eval_runtime": 0.174,
      "eval_samples_per_second": 287.402,
      "eval_steps_per_second": 74.725,
      "step": 75
    },
    {
      "epoch": 0.043032061717035885,
      "grad_norm": 0.019447388127446175,
      "learning_rate": 1.91437699862843e-05,
      "loss": 11.9267,
      "step": 76
    },
    {
      "epoch": 0.043598273055417934,
      "grad_norm": 0.024625686928629875,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 11.9275,
      "step": 77
    },
    {
      "epoch": 0.04416448439379998,
      "grad_norm": 0.024972781538963318,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 11.9273,
      "step": 78
    },
    {
      "epoch": 0.04473069573218204,
      "grad_norm": 0.028384722769260406,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 11.9259,
      "step": 79
    },
    {
      "epoch": 0.04529690707056409,
      "grad_norm": 0.031045373529195786,
      "learning_rate": 1.577527884852619e-05,
      "loss": 11.926,
      "step": 80
    },
    {
      "epoch": 0.04586311840894614,
      "grad_norm": 0.03209468722343445,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 11.9275,
      "step": 81
    },
    {
      "epoch": 0.04642932974732819,
      "grad_norm": 0.03293868526816368,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 11.9275,
      "step": 82
    },
    {
      "epoch": 0.04699554108571024,
      "grad_norm": 0.03368574380874634,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 11.9272,
      "step": 83
    },
    {
      "epoch": 0.047561752424092295,
      "grad_norm": 0.03013777732849121,
      "learning_rate": 1.313747004979751e-05,
      "loss": 11.9262,
      "step": 84
    },
    {
      "epoch": 0.04812796376247434,
      "grad_norm": 0.03828248009085655,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 11.924,
      "step": 85
    },
    {
      "epoch": 0.04869417510085639,
      "grad_norm": 0.04111775755882263,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 11.9271,
      "step": 86
    },
    {
      "epoch": 0.04926038643923845,
      "grad_norm": 0.04474611580371857,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 11.9244,
      "step": 87
    },
    {
      "epoch": 0.049826597777620496,
      "grad_norm": 0.027258913964033127,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 11.9264,
      "step": 88
    },
    {
      "epoch": 0.050392809116002545,
      "grad_norm": 0.022543244063854218,
      "learning_rate": 1.094121605429547e-05,
      "loss": 11.9276,
      "step": 89
    },
    {
      "epoch": 0.0509590204543846,
      "grad_norm": 0.027043450623750687,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 11.9276,
      "step": 90
    },
    {
      "epoch": 0.05152523179276665,
      "grad_norm": 0.027559487149119377,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 11.9274,
      "step": 91
    },
    {
      "epoch": 0.052091443131148704,
      "grad_norm": 0.029342046007514,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 11.9271,
      "step": 92
    },
    {
      "epoch": 0.05265765446953075,
      "grad_norm": 0.03043309599161148,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 11.9261,
      "step": 93
    },
    {
      "epoch": 0.0532238658079128,
      "grad_norm": 0.032014548778533936,
      "learning_rate": 1.002623399352217e-05,
      "loss": 11.9264,
      "step": 94
    },
    {
      "epoch": 0.05379007714629486,
      "grad_norm": 0.033974312245845795,
      "learning_rate": 1e-05,
      "loss": 11.9274,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 1980739092480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}