{
  "best_metric": 1.517699122428894,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.04689331770222743,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004936138705497624,
      "grad_norm": 8.610563278198242,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.296,
      "step": 1
    },
    {
      "epoch": 0.0004936138705497624,
      "eval_loss": 3.618351697921753,
      "eval_runtime": 2.0991,
      "eval_samples_per_second": 23.82,
      "eval_steps_per_second": 6.193,
      "step": 1
    },
    {
      "epoch": 0.0009872277410995249,
      "grad_norm": 9.678094863891602,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.4229,
      "step": 2
    },
    {
      "epoch": 0.0014808416116492873,
      "grad_norm": 8.572405815124512,
      "learning_rate": 0.0001,
      "loss": 3.2758,
      "step": 3
    },
    {
      "epoch": 0.0019744554821990497,
      "grad_norm": 3.8493947982788086,
      "learning_rate": 9.997376600647783e-05,
      "loss": 2.3979,
      "step": 4
    },
    {
      "epoch": 0.002468069352748812,
      "grad_norm": 2.470167398452759,
      "learning_rate": 9.989509461357426e-05,
      "loss": 2.0289,
      "step": 5
    },
    {
      "epoch": 0.0029616832232985746,
      "grad_norm": 1.9393905401229858,
      "learning_rate": 9.976407754861426e-05,
      "loss": 2.2227,
      "step": 6
    },
    {
      "epoch": 0.003455297093848337,
      "grad_norm": 1.9276494979858398,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.9944,
      "step": 7
    },
    {
      "epoch": 0.0039489109643980995,
      "grad_norm": 1.5310888290405273,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.7675,
      "step": 8
    },
    {
      "epoch": 0.004442524834947862,
      "grad_norm": 1.3651423454284668,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.8709,
      "step": 9
    },
    {
      "epoch": 0.004936138705497624,
      "grad_norm": 1.3343584537506104,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.7253,
      "step": 10
    },
    {
      "epoch": 0.005429752576047387,
      "grad_norm": 1.2432461977005005,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.8579,
      "step": 11
    },
    {
      "epoch": 0.005923366446597149,
      "grad_norm": 1.0454318523406982,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.7956,
      "step": 12
    },
    {
      "epoch": 0.006416980317146912,
      "grad_norm": 1.0827058553695679,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.6771,
      "step": 13
    },
    {
      "epoch": 0.006910594187696674,
      "grad_norm": 0.9257851839065552,
      "learning_rate": 9.686252995020249e-05,
      "loss": 1.7253,
      "step": 14
    },
    {
      "epoch": 0.007404208058246437,
      "grad_norm": 1.018771767616272,
      "learning_rate": 9.627450856774539e-05,
      "loss": 1.708,
      "step": 15
    },
    {
      "epoch": 0.007897821928796199,
      "grad_norm": 0.8964956402778625,
      "learning_rate": 9.563836295460398e-05,
      "loss": 1.6949,
      "step": 16
    },
    {
      "epoch": 0.008391435799345962,
      "grad_norm": 0.9759191870689392,
      "learning_rate": 9.495483482810688e-05,
      "loss": 1.5602,
      "step": 17
    },
    {
      "epoch": 0.008885049669895725,
      "grad_norm": 1.0305898189544678,
      "learning_rate": 9.422472115147382e-05,
      "loss": 1.653,
      "step": 18
    },
    {
      "epoch": 0.009378663540445486,
      "grad_norm": 0.9951354265213013,
      "learning_rate": 9.3448873204592e-05,
      "loss": 1.787,
      "step": 19
    },
    {
      "epoch": 0.009872277410995249,
      "grad_norm": 0.8011742830276489,
      "learning_rate": 9.2628195591462e-05,
      "loss": 1.639,
      "step": 20
    },
    {
      "epoch": 0.010365891281545012,
      "grad_norm": 0.8728142976760864,
      "learning_rate": 9.176364518546989e-05,
      "loss": 1.6791,
      "step": 21
    },
    {
      "epoch": 0.010859505152094774,
      "grad_norm": 0.8905225396156311,
      "learning_rate": 9.08562300137157e-05,
      "loss": 1.5861,
      "step": 22
    },
    {
      "epoch": 0.011353119022644536,
      "grad_norm": 0.8705262541770935,
      "learning_rate": 8.990700808169889e-05,
      "loss": 1.4812,
      "step": 23
    },
    {
      "epoch": 0.011846732893194298,
      "grad_norm": 0.8652294874191284,
      "learning_rate": 8.891708613973126e-05,
      "loss": 1.5792,
      "step": 24
    },
    {
      "epoch": 0.012340346763744061,
      "grad_norm": 0.916961133480072,
      "learning_rate": 8.788761839251559e-05,
      "loss": 1.4967,
      "step": 25
    },
    {
      "epoch": 0.012340346763744061,
      "eval_loss": 1.6187465190887451,
      "eval_runtime": 2.171,
      "eval_samples_per_second": 23.03,
      "eval_steps_per_second": 5.988,
      "step": 25
    },
    {
      "epoch": 0.012833960634293824,
      "grad_norm": 0.9111001491546631,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.643,
      "step": 26
    },
    {
      "epoch": 0.013327574504843585,
      "grad_norm": 0.869102418422699,
      "learning_rate": 8.571489144483944e-05,
      "loss": 1.6734,
      "step": 27
    },
    {
      "epoch": 0.013821188375393348,
      "grad_norm": 0.842080295085907,
      "learning_rate": 8.457416554680877e-05,
      "loss": 1.476,
      "step": 28
    },
    {
      "epoch": 0.014314802245943111,
      "grad_norm": 0.835245668888092,
      "learning_rate": 8.339895749467238e-05,
      "loss": 1.6803,
      "step": 29
    },
    {
      "epoch": 0.014808416116492874,
      "grad_norm": 0.7700492739677429,
      "learning_rate": 8.219063752844926e-05,
      "loss": 1.4141,
      "step": 30
    },
    {
      "epoch": 0.015302029987042635,
      "grad_norm": 0.8414303064346313,
      "learning_rate": 8.095061449516903e-05,
      "loss": 1.5424,
      "step": 31
    },
    {
      "epoch": 0.015795643857592398,
      "grad_norm": 0.8434069752693176,
      "learning_rate": 7.968033420621935e-05,
      "loss": 1.5554,
      "step": 32
    },
    {
      "epoch": 0.01628925772814216,
      "grad_norm": 0.8102946877479553,
      "learning_rate": 7.838127775159452e-05,
      "loss": 1.5322,
      "step": 33
    },
    {
      "epoch": 0.016782871598691924,
      "grad_norm": 0.777534544467926,
      "learning_rate": 7.705495977301078e-05,
      "loss": 1.5407,
      "step": 34
    },
    {
      "epoch": 0.017276485469241685,
      "grad_norm": 0.8392916321754456,
      "learning_rate": 7.570292669790186e-05,
      "loss": 1.5694,
      "step": 35
    },
    {
      "epoch": 0.01777009933979145,
      "grad_norm": 0.8198193907737732,
      "learning_rate": 7.43267549363537e-05,
      "loss": 1.5633,
      "step": 36
    },
    {
      "epoch": 0.01826371321034121,
      "grad_norm": 0.8337418437004089,
      "learning_rate": 7.292804904308087e-05,
      "loss": 1.563,
      "step": 37
    },
    {
      "epoch": 0.01875732708089097,
      "grad_norm": 0.7560647130012512,
      "learning_rate": 7.150843984658754e-05,
      "loss": 1.4525,
      "step": 38
    },
    {
      "epoch": 0.019250940951440736,
      "grad_norm": 0.7717271447181702,
      "learning_rate": 7.006958254769438e-05,
      "loss": 1.5498,
      "step": 39
    },
    {
      "epoch": 0.019744554821990497,
      "grad_norm": 0.7649319767951965,
      "learning_rate": 6.861315478964841e-05,
      "loss": 1.529,
      "step": 40
    },
    {
      "epoch": 0.020238168692540262,
      "grad_norm": 0.747653067111969,
      "learning_rate": 6.714085470206609e-05,
      "loss": 1.388,
      "step": 41
    },
    {
      "epoch": 0.020731782563090023,
      "grad_norm": 0.7593997120857239,
      "learning_rate": 6.56543989209901e-05,
      "loss": 1.4656,
      "step": 42
    },
    {
      "epoch": 0.021225396433639784,
      "grad_norm": 0.7581989765167236,
      "learning_rate": 6.415552058736854e-05,
      "loss": 1.5301,
      "step": 43
    },
    {
      "epoch": 0.02171901030418955,
      "grad_norm": 0.8096319437026978,
      "learning_rate": 6.264596732629e-05,
      "loss": 1.5115,
      "step": 44
    },
    {
      "epoch": 0.02221262417473931,
      "grad_norm": 0.8088666200637817,
      "learning_rate": 6.112749920933111e-05,
      "loss": 1.5176,
      "step": 45
    },
    {
      "epoch": 0.02270623804528907,
      "grad_norm": 0.7563244700431824,
      "learning_rate": 5.960188670239154e-05,
      "loss": 1.3766,
      "step": 46
    },
    {
      "epoch": 0.023199851915838836,
      "grad_norm": 0.8245486617088318,
      "learning_rate": 5.80709086014102e-05,
      "loss": 1.4407,
      "step": 47
    },
    {
      "epoch": 0.023693465786388597,
      "grad_norm": 0.8189464807510376,
      "learning_rate": 5.653634995836856e-05,
      "loss": 1.4207,
      "step": 48
    },
    {
      "epoch": 0.02418707965693836,
      "grad_norm": 0.86505126953125,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.5054,
      "step": 49
    },
    {
      "epoch": 0.024680693527488123,
      "grad_norm": 0.9769317507743835,
      "learning_rate": 5.346365004163145e-05,
      "loss": 1.505,
      "step": 50
    },
    {
      "epoch": 0.024680693527488123,
      "eval_loss": 1.558501124382019,
      "eval_runtime": 2.151,
      "eval_samples_per_second": 23.245,
      "eval_steps_per_second": 6.044,
      "step": 50
    },
    {
      "epoch": 0.025174307398037884,
      "grad_norm": 0.7213638424873352,
      "learning_rate": 5.192909139858981e-05,
      "loss": 1.411,
      "step": 51
    },
    {
      "epoch": 0.02566792126858765,
      "grad_norm": 0.7571468949317932,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 1.5454,
      "step": 52
    },
    {
      "epoch": 0.02616153513913741,
      "grad_norm": 0.717697024345398,
      "learning_rate": 4.887250079066892e-05,
      "loss": 1.4686,
      "step": 53
    },
    {
      "epoch": 0.02665514900968717,
      "grad_norm": 0.7320601344108582,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 1.4823,
      "step": 54
    },
    {
      "epoch": 0.027148762880236935,
      "grad_norm": 0.7738489508628845,
      "learning_rate": 4.584447941263149e-05,
      "loss": 1.4721,
      "step": 55
    },
    {
      "epoch": 0.027642376750786696,
      "grad_norm": 0.7395352721214294,
      "learning_rate": 4.43456010790099e-05,
      "loss": 1.5485,
      "step": 56
    },
    {
      "epoch": 0.02813599062133646,
      "grad_norm": 0.7061799764633179,
      "learning_rate": 4.285914529793391e-05,
      "loss": 1.4671,
      "step": 57
    },
    {
      "epoch": 0.028629604491886222,
      "grad_norm": 0.7371093034744263,
      "learning_rate": 4.13868452103516e-05,
      "loss": 1.5273,
      "step": 58
    },
    {
      "epoch": 0.029123218362435983,
      "grad_norm": 0.7502743005752563,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 1.5082,
      "step": 59
    },
    {
      "epoch": 0.029616832232985748,
      "grad_norm": 0.7478111982345581,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 1.4492,
      "step": 60
    },
    {
      "epoch": 0.03011044610353551,
      "grad_norm": 0.7804875373840332,
      "learning_rate": 3.707195095691913e-05,
      "loss": 1.5395,
      "step": 61
    },
    {
      "epoch": 0.03060405997408527,
      "grad_norm": 0.828667938709259,
      "learning_rate": 3.567324506364632e-05,
      "loss": 1.4686,
      "step": 62
    },
    {
      "epoch": 0.031097673844635035,
      "grad_norm": 0.7223063111305237,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 1.4567,
      "step": 63
    },
    {
      "epoch": 0.031591287715184796,
      "grad_norm": 0.8763315677642822,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 1.5132,
      "step": 64
    },
    {
      "epoch": 0.03208490158573456,
      "grad_norm": 0.8217432498931885,
      "learning_rate": 3.16187222484055e-05,
      "loss": 1.4729,
      "step": 65
    },
    {
      "epoch": 0.03257851545628432,
      "grad_norm": 0.7187386155128479,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 1.4075,
      "step": 66
    },
    {
      "epoch": 0.033072129326834086,
      "grad_norm": 0.7990232110023499,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 1.6426,
      "step": 67
    },
    {
      "epoch": 0.03356574319738385,
      "grad_norm": 0.7265430688858032,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 1.4177,
      "step": 68
    },
    {
      "epoch": 0.03405935706793361,
      "grad_norm": 0.7410502433776855,
      "learning_rate": 2.660104250532764e-05,
      "loss": 1.5169,
      "step": 69
    },
    {
      "epoch": 0.03455297093848337,
      "grad_norm": 0.8333743214607239,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 1.5395,
      "step": 70
    },
    {
      "epoch": 0.03504658480903313,
      "grad_norm": 0.7417758703231812,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 1.4021,
      "step": 71
    },
    {
      "epoch": 0.0355401986795829,
      "grad_norm": 0.757122814655304,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.5029,
      "step": 72
    },
    {
      "epoch": 0.03603381255013266,
      "grad_norm": 0.8034988045692444,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 1.5196,
      "step": 73
    },
    {
      "epoch": 0.03652742642068242,
      "grad_norm": 0.8066292405128479,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 1.4421,
      "step": 74
    },
    {
      "epoch": 0.03702104029123218,
      "grad_norm": 0.9166308045387268,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 1.5344,
      "step": 75
    },
    {
      "epoch": 0.03702104029123218,
      "eval_loss": 1.517699122428894,
      "eval_runtime": 2.1573,
      "eval_samples_per_second": 23.177,
      "eval_steps_per_second": 6.026,
      "step": 75
    },
    {
      "epoch": 0.03751465416178194,
      "grad_norm": 0.715366005897522,
      "learning_rate": 1.91437699862843e-05,
      "loss": 1.5203,
      "step": 76
    },
    {
      "epoch": 0.03800826803233171,
      "grad_norm": 0.7529436945915222,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 1.468,
      "step": 77
    },
    {
      "epoch": 0.03850188190288147,
      "grad_norm": 0.8566577434539795,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 1.5055,
      "step": 78
    },
    {
      "epoch": 0.038995495773431234,
      "grad_norm": 0.7840465307235718,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 1.525,
      "step": 79
    },
    {
      "epoch": 0.039489109643980995,
      "grad_norm": 0.7184439897537231,
      "learning_rate": 1.577527884852619e-05,
      "loss": 1.5049,
      "step": 80
    },
    {
      "epoch": 0.039982723514530756,
      "grad_norm": 0.7097110748291016,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 1.3389,
      "step": 81
    },
    {
      "epoch": 0.040476337385080524,
      "grad_norm": 0.7986069917678833,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 1.5583,
      "step": 82
    },
    {
      "epoch": 0.040969951255630285,
      "grad_norm": 0.8031150102615356,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 1.405,
      "step": 83
    },
    {
      "epoch": 0.041463565126180046,
      "grad_norm": 0.7863020896911621,
      "learning_rate": 1.313747004979751e-05,
      "loss": 1.4955,
      "step": 84
    },
    {
      "epoch": 0.04195717899672981,
      "grad_norm": 0.8263758420944214,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 1.4869,
      "step": 85
    },
    {
      "epoch": 0.04245079286727957,
      "grad_norm": 0.7383260726928711,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 1.4159,
      "step": 86
    },
    {
      "epoch": 0.04294440673782933,
      "grad_norm": 0.8411725759506226,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 1.3053,
      "step": 87
    },
    {
      "epoch": 0.0434380206083791,
      "grad_norm": 0.7437005639076233,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 1.4478,
      "step": 88
    },
    {
      "epoch": 0.04393163447892886,
      "grad_norm": 0.7593280673027039,
      "learning_rate": 1.094121605429547e-05,
      "loss": 1.5367,
      "step": 89
    },
    {
      "epoch": 0.04442524834947862,
      "grad_norm": 0.7815626859664917,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 1.4695,
      "step": 90
    },
    {
      "epoch": 0.04491886222002838,
      "grad_norm": 0.7754625678062439,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 1.4679,
      "step": 91
    },
    {
      "epoch": 0.04541247609057814,
      "grad_norm": 0.7283334136009216,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 1.4585,
      "step": 92
    },
    {
      "epoch": 0.04590608996112791,
      "grad_norm": 0.795418381690979,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 1.4876,
      "step": 93
    },
    {
      "epoch": 0.04639970383167767,
      "grad_norm": 0.7504608631134033,
      "learning_rate": 1.002623399352217e-05,
      "loss": 1.4626,
      "step": 94
    },
    {
      "epoch": 0.04689331770222743,
      "grad_norm": 0.7937198281288147,
      "learning_rate": 1e-05,
      "loss": 1.4679,
      "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": 3.087136995672064e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}