{
  "best_metric": 11.920663833618164,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.030916679548616478,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003091667954861648,
      "grad_norm": 0.008824202232062817,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9332,
      "step": 1
    },
    {
      "epoch": 0.0003091667954861648,
      "eval_loss": 11.933963775634766,
      "eval_runtime": 0.2668,
      "eval_samples_per_second": 187.429,
      "eval_steps_per_second": 26.24,
      "step": 1
    },
    {
      "epoch": 0.0006183335909723295,
      "grad_norm": 0.008883276022970676,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9329,
      "step": 2
    },
    {
      "epoch": 0.0009275003864584944,
      "grad_norm": 0.011851401068270206,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.935,
      "step": 3
    },
    {
      "epoch": 0.001236667181944659,
      "grad_norm": 0.010448981076478958,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9331,
      "step": 4
    },
    {
      "epoch": 0.001545833977430824,
      "grad_norm": 0.009428169578313828,
      "learning_rate": 0.00015,
      "loss": 11.936,
      "step": 5
    },
    {
      "epoch": 0.0018550007729169888,
      "grad_norm": 0.011950953863561153,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9322,
      "step": 6
    },
    {
      "epoch": 0.0021641675684031534,
      "grad_norm": 0.007914911024272442,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9326,
      "step": 7
    },
    {
      "epoch": 0.002473334363889318,
      "grad_norm": 0.011372610926628113,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9325,
      "step": 8
    },
    {
      "epoch": 0.002782501159375483,
      "grad_norm": 0.00945382658392191,
      "learning_rate": 0.00027,
      "loss": 11.9319,
      "step": 9
    },
    {
      "epoch": 0.003091667954861648,
      "grad_norm": 0.009733719751238823,
      "learning_rate": 0.0003,
      "loss": 11.9337,
      "step": 10
    },
    {
      "epoch": 0.0034008347503478127,
      "grad_norm": 0.01105896383523941,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.9318,
      "step": 11
    },
    {
      "epoch": 0.0037100015458339775,
      "grad_norm": 0.012633428908884525,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9346,
      "step": 12
    },
    {
      "epoch": 0.004019168341320142,
      "grad_norm": 0.013770537450909615,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.9338,
      "step": 13
    },
    {
      "epoch": 0.004328335136806307,
      "grad_norm": 0.009807516820728779,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9331,
      "step": 14
    },
    {
      "epoch": 0.004637501932292472,
      "grad_norm": 0.014494593255221844,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9339,
      "step": 15
    },
    {
      "epoch": 0.004946668727778636,
      "grad_norm": 0.013395157642662525,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9337,
      "step": 16
    },
    {
      "epoch": 0.005255835523264802,
      "grad_norm": 0.018604109063744545,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9344,
      "step": 17
    },
    {
      "epoch": 0.005565002318750966,
      "grad_norm": 0.017795801162719727,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.9319,
      "step": 18
    },
    {
      "epoch": 0.005874169114237131,
      "grad_norm": 0.017611371353268623,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.934,
      "step": 19
    },
    {
      "epoch": 0.006183335909723296,
      "grad_norm": 0.016056658700108528,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9341,
      "step": 20
    },
    {
      "epoch": 0.00649250270520946,
      "grad_norm": 0.01700686477124691,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.933,
      "step": 21
    },
    {
      "epoch": 0.006801669500695625,
      "grad_norm": 0.020028963685035706,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9335,
      "step": 22
    },
    {
      "epoch": 0.00711083629618179,
      "grad_norm": 0.019611453637480736,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9312,
      "step": 23
    },
    {
      "epoch": 0.007420003091667955,
      "grad_norm": 0.023897267878055573,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9304,
      "step": 24
    },
    {
      "epoch": 0.007729169887154119,
      "grad_norm": 0.020800765603780746,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9328,
      "step": 25
    },
    {
      "epoch": 0.007729169887154119,
      "eval_loss": 11.932024955749512,
      "eval_runtime": 0.267,
      "eval_samples_per_second": 187.231,
      "eval_steps_per_second": 26.212,
      "step": 25
    },
    {
      "epoch": 0.008038336682640285,
      "grad_norm": 0.0328727588057518,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9322,
      "step": 26
    },
    {
      "epoch": 0.008347503478126449,
      "grad_norm": 0.023031141608953476,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9322,
      "step": 27
    },
    {
      "epoch": 0.008656670273612613,
      "grad_norm": 0.03310677036643028,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9303,
      "step": 28
    },
    {
      "epoch": 0.00896583706909878,
      "grad_norm": 0.02859288640320301,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9309,
      "step": 29
    },
    {
      "epoch": 0.009275003864584944,
      "grad_norm": 0.023054543882608414,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9306,
      "step": 30
    },
    {
      "epoch": 0.009584170660071108,
      "grad_norm": 0.034139908850193024,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9311,
      "step": 31
    },
    {
      "epoch": 0.009893337455557273,
      "grad_norm": 0.03088107891380787,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.9302,
      "step": 32
    },
    {
      "epoch": 0.010202504251043437,
      "grad_norm": 0.028771521523594856,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9313,
      "step": 33
    },
    {
      "epoch": 0.010511671046529603,
      "grad_norm": 0.04325784742832184,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9298,
      "step": 34
    },
    {
      "epoch": 0.010820837842015768,
      "grad_norm": 0.036876387894153595,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9304,
      "step": 35
    },
    {
      "epoch": 0.011130004637501932,
      "grad_norm": 0.04493628442287445,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9292,
      "step": 36
    },
    {
      "epoch": 0.011439171432988096,
      "grad_norm": 0.04691850394010544,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.927,
      "step": 37
    },
    {
      "epoch": 0.011748338228474263,
      "grad_norm": 0.03808928281068802,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.928,
      "step": 38
    },
    {
      "epoch": 0.012057505023960427,
      "grad_norm": 0.045798517763614655,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.9259,
      "step": 39
    },
    {
      "epoch": 0.012366671819446591,
      "grad_norm": 0.04286628216505051,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9249,
      "step": 40
    },
    {
      "epoch": 0.012675838614932756,
      "grad_norm": 0.039922237396240234,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.926,
      "step": 41
    },
    {
      "epoch": 0.01298500541041892,
      "grad_norm": 0.03747300058603287,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9265,
      "step": 42
    },
    {
      "epoch": 0.013294172205905086,
      "grad_norm": 0.04846448451280594,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9258,
      "step": 43
    },
    {
      "epoch": 0.01360333900139125,
      "grad_norm": 0.041615940630435944,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9271,
      "step": 44
    },
    {
      "epoch": 0.013912505796877415,
      "grad_norm": 0.0515202097594738,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9257,
      "step": 45
    },
    {
      "epoch": 0.01422167259236358,
      "grad_norm": 0.05010367929935455,
      "learning_rate": 0.000274201324672203,
      "loss": 11.9246,
      "step": 46
    },
    {
      "epoch": 0.014530839387849746,
      "grad_norm": 0.04578734561800957,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9264,
      "step": 47
    },
    {
      "epoch": 0.01484000618333591,
      "grad_norm": 0.047156915068626404,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9238,
      "step": 48
    },
    {
      "epoch": 0.015149172978822074,
      "grad_norm": 0.04473588988184929,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.9252,
      "step": 49
    },
    {
      "epoch": 0.015458339774308239,
      "grad_norm": 0.054239559918642044,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.9263,
      "step": 50
    },
    {
      "epoch": 0.015458339774308239,
      "eval_loss": 11.923178672790527,
      "eval_runtime": 0.2655,
      "eval_samples_per_second": 188.289,
      "eval_steps_per_second": 26.36,
      "step": 50
    },
    {
      "epoch": 0.015767506569794403,
      "grad_norm": 0.033662110567092896,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.9267,
      "step": 51
    },
    {
      "epoch": 0.01607667336528057,
      "grad_norm": 0.03926435112953186,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.9234,
      "step": 52
    },
    {
      "epoch": 0.016385840160766732,
      "grad_norm": 0.034058280289173126,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.9223,
      "step": 53
    },
    {
      "epoch": 0.016695006956252898,
      "grad_norm": 0.0344548374414444,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.9222,
      "step": 54
    },
    {
      "epoch": 0.017004173751739064,
      "grad_norm": 0.0250602625310421,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.9228,
      "step": 55
    },
    {
      "epoch": 0.017313340547225227,
      "grad_norm": 0.025534184649586678,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.9211,
      "step": 56
    },
    {
      "epoch": 0.017622507342711393,
      "grad_norm": 0.02254529669880867,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.9221,
      "step": 57
    },
    {
      "epoch": 0.01793167413819756,
      "grad_norm": 0.028335142880678177,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.9228,
      "step": 58
    },
    {
      "epoch": 0.018240840933683722,
      "grad_norm": 0.01873270981013775,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.9224,
      "step": 59
    },
    {
      "epoch": 0.018550007729169888,
      "grad_norm": 0.02736358530819416,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.9202,
      "step": 60
    },
    {
      "epoch": 0.01885917452465605,
      "grad_norm": 0.0195369403809309,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.9215,
      "step": 61
    },
    {
      "epoch": 0.019168341320142217,
      "grad_norm": 0.01774240843951702,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.9209,
      "step": 62
    },
    {
      "epoch": 0.019477508115628383,
      "grad_norm": 0.01636182889342308,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.9215,
      "step": 63
    },
    {
      "epoch": 0.019786674911114546,
      "grad_norm": 0.027203379198908806,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.9226,
      "step": 64
    },
    {
      "epoch": 0.02009584170660071,
      "grad_norm": 0.02323518693447113,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.9235,
      "step": 65
    },
    {
      "epoch": 0.020405008502086874,
      "grad_norm": 0.02373749576508999,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.9209,
      "step": 66
    },
    {
      "epoch": 0.02071417529757304,
      "grad_norm": 0.011498493142426014,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.9197,
      "step": 67
    },
    {
      "epoch": 0.021023342093059207,
      "grad_norm": 0.01602911949157715,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.9212,
      "step": 68
    },
    {
      "epoch": 0.02133250888854537,
      "grad_norm": 0.020656874403357506,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.9203,
      "step": 69
    },
    {
      "epoch": 0.021641675684031535,
      "grad_norm": 0.01209651492536068,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.9207,
      "step": 70
    },
    {
      "epoch": 0.0219508424795177,
      "grad_norm": 0.017884377390146255,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.9222,
      "step": 71
    },
    {
      "epoch": 0.022260009275003864,
      "grad_norm": 0.0167262963950634,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.9219,
      "step": 72
    },
    {
      "epoch": 0.02256917607049003,
      "grad_norm": 0.030773084610700607,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.9203,
      "step": 73
    },
    {
      "epoch": 0.022878342865976193,
      "grad_norm": 0.01883070357143879,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.9234,
      "step": 74
    },
    {
      "epoch": 0.02318750966146236,
      "grad_norm": 0.016938529908657074,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.9208,
      "step": 75
    },
    {
      "epoch": 0.02318750966146236,
      "eval_loss": 11.921051979064941,
      "eval_runtime": 0.2655,
      "eval_samples_per_second": 188.335,
      "eval_steps_per_second": 26.367,
      "step": 75
    },
    {
      "epoch": 0.023496676456948525,
      "grad_norm": 0.01503379549831152,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.9233,
      "step": 76
    },
    {
      "epoch": 0.023805843252434688,
      "grad_norm": 0.01360781118273735,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.923,
      "step": 77
    },
    {
      "epoch": 0.024115010047920854,
      "grad_norm": 0.021511739119887352,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.9222,
      "step": 78
    },
    {
      "epoch": 0.024424176843407017,
      "grad_norm": 0.015243256464600563,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.9213,
      "step": 79
    },
    {
      "epoch": 0.024733343638893183,
      "grad_norm": 0.027415020391345024,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.9243,
      "step": 80
    },
    {
      "epoch": 0.02504251043437935,
      "grad_norm": 0.01201211754232645,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.9195,
      "step": 81
    },
    {
      "epoch": 0.02535167722986551,
      "grad_norm": 0.021786803379654884,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.9217,
      "step": 82
    },
    {
      "epoch": 0.025660844025351678,
      "grad_norm": 0.018142500892281532,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.9205,
      "step": 83
    },
    {
      "epoch": 0.02597001082083784,
      "grad_norm": 0.01087669376283884,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.9206,
      "step": 84
    },
    {
      "epoch": 0.026279177616324007,
      "grad_norm": 0.013356782495975494,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.9217,
      "step": 85
    },
    {
      "epoch": 0.026588344411810173,
      "grad_norm": 0.015523252077400684,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.9209,
      "step": 86
    },
    {
      "epoch": 0.026897511207296335,
      "grad_norm": 0.015875937417149544,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.9208,
      "step": 87
    },
    {
      "epoch": 0.0272066780027825,
      "grad_norm": 0.015149236656725407,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.9215,
      "step": 88
    },
    {
      "epoch": 0.027515844798268668,
      "grad_norm": 0.020532429218292236,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.9228,
      "step": 89
    },
    {
      "epoch": 0.02782501159375483,
      "grad_norm": 0.015903906896710396,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.9202,
      "step": 90
    },
    {
      "epoch": 0.028134178389240996,
      "grad_norm": 0.014392823912203312,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.921,
      "step": 91
    },
    {
      "epoch": 0.02844334518472716,
      "grad_norm": 0.018338419497013092,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.9189,
      "step": 92
    },
    {
      "epoch": 0.028752511980213325,
      "grad_norm": 0.014712207019329071,
      "learning_rate": 0.000179567554117722,
      "loss": 11.9197,
      "step": 93
    },
    {
      "epoch": 0.02906167877569949,
      "grad_norm": 0.022185087203979492,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.9208,
      "step": 94
    },
    {
      "epoch": 0.029370845571185654,
      "grad_norm": 0.022651012986898422,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.9208,
      "step": 95
    },
    {
      "epoch": 0.02968001236667182,
      "grad_norm": 0.015332295559346676,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.9201,
      "step": 96
    },
    {
      "epoch": 0.029989179162157983,
      "grad_norm": 0.02605201117694378,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.9201,
      "step": 97
    },
    {
      "epoch": 0.03029834595764415,
      "grad_norm": 0.019824691116809845,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.9193,
      "step": 98
    },
    {
      "epoch": 0.030607512753130315,
      "grad_norm": 0.01884804666042328,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.9215,
      "step": 99
    },
    {
      "epoch": 0.030916679548616478,
      "grad_norm": 0.033876944333314896,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.9219,
      "step": 100
    },
    {
      "epoch": 0.030916679548616478,
      "eval_loss": 11.920663833618164,
      "eval_runtime": 0.2665,
      "eval_samples_per_second": 187.636,
      "eval_steps_per_second": 26.269,
      "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 159262310400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}