{
  "best_metric": 0.01876358687877655,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.07654586771917235,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007654586771917235,
      "grad_norm": 15.716177940368652,
      "learning_rate": 2.5e-05,
      "loss": 0.6301,
      "step": 1
    },
    {
      "epoch": 0.0007654586771917235,
      "eval_loss": 0.9535714983940125,
      "eval_runtime": 1.8763,
      "eval_samples_per_second": 26.648,
      "eval_steps_per_second": 6.929,
      "step": 1
    },
    {
      "epoch": 0.001530917354383447,
      "grad_norm": 28.1146240234375,
      "learning_rate": 5e-05,
      "loss": 1.6204,
      "step": 2
    },
    {
      "epoch": 0.0022963760315751706,
      "grad_norm": 3.1468186378479004,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4088,
      "step": 3
    },
    {
      "epoch": 0.003061834708766894,
      "grad_norm": 2.8593838214874268,
      "learning_rate": 0.0001,
      "loss": 0.3243,
      "step": 4
    },
    {
      "epoch": 0.0038272933859586173,
      "grad_norm": 2.0387535095214844,
      "learning_rate": 9.997590643643647e-05,
      "loss": 0.1949,
      "step": 5
    },
    {
      "epoch": 0.004592752063150341,
      "grad_norm": 2.075502395629883,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.1607,
      "step": 6
    },
    {
      "epoch": 0.005358210740342064,
      "grad_norm": 2.105217695236206,
      "learning_rate": 9.978331270024886e-05,
      "loss": 0.108,
      "step": 7
    },
    {
      "epoch": 0.006123669417533788,
      "grad_norm": 1.4741127490997314,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0612,
      "step": 8
    },
    {
      "epoch": 0.006889128094725512,
      "grad_norm": 3.5471949577331543,
      "learning_rate": 9.939894994381957e-05,
      "loss": 0.0807,
      "step": 9
    },
    {
      "epoch": 0.007654586771917235,
      "grad_norm": 2.4321608543395996,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0468,
      "step": 10
    },
    {
      "epoch": 0.008420045449108958,
      "grad_norm": 2.2056820392608643,
      "learning_rate": 9.882446406748002e-05,
      "loss": 0.0375,
      "step": 11
    },
    {
      "epoch": 0.009185504126300682,
      "grad_norm": 1.6821849346160889,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0243,
      "step": 12
    },
    {
      "epoch": 0.009950962803492405,
      "grad_norm": 1.2000023126602173,
      "learning_rate": 9.80623151079494e-05,
      "loss": 0.3485,
      "step": 13
    },
    {
      "epoch": 0.010716421480684128,
      "grad_norm": 1.9993274211883545,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.4763,
      "step": 14
    },
    {
      "epoch": 0.011481880157875853,
      "grad_norm": 3.4421091079711914,
      "learning_rate": 9.711576670407965e-05,
      "loss": 0.8174,
      "step": 15
    },
    {
      "epoch": 0.012247338835067576,
      "grad_norm": 0.3677566945552826,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0088,
      "step": 16
    },
    {
      "epoch": 0.013012797512259299,
      "grad_norm": 0.11690377444028854,
      "learning_rate": 9.598887212145291e-05,
      "loss": 0.0054,
      "step": 17
    },
    {
      "epoch": 0.013778256189451023,
      "grad_norm": 0.09429043531417847,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0047,
      "step": 18
    },
    {
      "epoch": 0.014543714866642746,
      "grad_norm": 0.36489200592041016,
      "learning_rate": 9.468645689567598e-05,
      "loss": 0.0057,
      "step": 19
    },
    {
      "epoch": 0.01530917354383447,
      "grad_norm": 0.42153462767601013,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0062,
      "step": 20
    },
    {
      "epoch": 0.016074632221026192,
      "grad_norm": 0.28647613525390625,
      "learning_rate": 9.321409816869605e-05,
      "loss": 0.0051,
      "step": 21
    },
    {
      "epoch": 0.016840090898217915,
      "grad_norm": 0.0691399872303009,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0021,
      "step": 22
    },
    {
      "epoch": 0.01760554957540964,
      "grad_norm": 0.08754007518291473,
      "learning_rate": 9.157810080662269e-05,
      "loss": 0.0027,
      "step": 23
    },
    {
      "epoch": 0.018371008252601365,
      "grad_norm": 0.15579411387443542,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0033,
      "step": 24
    },
    {
      "epoch": 0.019136466929793088,
      "grad_norm": 0.08465871959924698,
      "learning_rate": 8.978547040132317e-05,
      "loss": 0.0018,
      "step": 25
    },
    {
      "epoch": 0.019136466929793088,
      "eval_loss": 0.08919362723827362,
      "eval_runtime": 1.0392,
      "eval_samples_per_second": 48.113,
      "eval_steps_per_second": 12.509,
      "step": 25
    },
    {
      "epoch": 0.01990192560698481,
      "grad_norm": 0.8272204995155334,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.2644,
      "step": 26
    },
    {
      "epoch": 0.020667384284176533,
      "grad_norm": 0.919032096862793,
      "learning_rate": 8.78438832714026e-05,
      "loss": 0.564,
      "step": 27
    },
    {
      "epoch": 0.021432842961368256,
      "grad_norm": 1.0027246475219727,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.1129,
      "step": 28
    },
    {
      "epoch": 0.02219830163855998,
      "grad_norm": 0.8935683369636536,
      "learning_rate": 8.57616535910292e-05,
      "loss": 0.017,
      "step": 29
    },
    {
      "epoch": 0.022963760315751706,
      "grad_norm": 0.1873510479927063,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0033,
      "step": 30
    },
    {
      "epoch": 0.02372921899294343,
      "grad_norm": 0.2691366970539093,
      "learning_rate": 8.354769778736406e-05,
      "loss": 0.0028,
      "step": 31
    },
    {
      "epoch": 0.02449467767013515,
      "grad_norm": 0.675572395324707,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0078,
      "step": 32
    },
    {
      "epoch": 0.025260136347326875,
      "grad_norm": 0.48143887519836426,
      "learning_rate": 8.12114963590511e-05,
      "loss": 0.0062,
      "step": 33
    },
    {
      "epoch": 0.026025595024518598,
      "grad_norm": 0.1117522120475769,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0016,
      "step": 34
    },
    {
      "epoch": 0.02679105370171032,
      "grad_norm": 0.5607677102088928,
      "learning_rate": 7.876305327926657e-05,
      "loss": 0.0062,
      "step": 35
    },
    {
      "epoch": 0.027556512378902047,
      "grad_norm": 0.13989481329917908,
      "learning_rate": 7.75e-05,
      "loss": 0.0013,
      "step": 36
    },
    {
      "epoch": 0.02832197105609377,
      "grad_norm": 0.00945358444005251,
      "learning_rate": 7.62128531571699e-05,
      "loss": 0.0003,
      "step": 37
    },
    {
      "epoch": 0.029087429733285493,
      "grad_norm": 0.3890470862388611,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.2334,
      "step": 38
    },
    {
      "epoch": 0.029852888410477216,
      "grad_norm": 0.9241925477981567,
      "learning_rate": 7.357181634119777e-05,
      "loss": 0.2837,
      "step": 39
    },
    {
      "epoch": 0.03061834708766894,
      "grad_norm": 0.7805806398391724,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.1911,
      "step": 40
    },
    {
      "epoch": 0.03138380576486066,
      "grad_norm": 0.13290484249591827,
      "learning_rate": 7.085125215645552e-05,
      "loss": 0.0025,
      "step": 41
    },
    {
      "epoch": 0.032149264442052385,
      "grad_norm": 0.6546358466148376,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0129,
      "step": 42
    },
    {
      "epoch": 0.03291472311924411,
      "grad_norm": 2.0483906269073486,
      "learning_rate": 6.80628104764508e-05,
      "loss": 0.0307,
      "step": 43
    },
    {
      "epoch": 0.03368018179643583,
      "grad_norm": 1.0244156122207642,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0139,
      "step": 44
    },
    {
      "epoch": 0.03444564047362755,
      "grad_norm": 0.13140460848808289,
      "learning_rate": 6.52184318365468e-05,
      "loss": 0.0022,
      "step": 45
    },
    {
      "epoch": 0.03521109915081928,
      "grad_norm": 0.0883515477180481,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0016,
      "step": 46
    },
    {
      "epoch": 0.035976557828011006,
      "grad_norm": 0.04970284551382065,
      "learning_rate": 6.23302963027565e-05,
      "loss": 0.0009,
      "step": 47
    },
    {
      "epoch": 0.03674201650520273,
      "grad_norm": 0.0229946281760931,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0005,
      "step": 48
    },
    {
      "epoch": 0.03750747518239445,
      "grad_norm": 0.010964008048176765,
      "learning_rate": 5.941077131483025e-05,
      "loss": 0.0003,
      "step": 49
    },
    {
      "epoch": 0.038272933859586175,
      "grad_norm": 0.009133069775998592,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0003,
      "step": 50
    },
    {
      "epoch": 0.038272933859586175,
      "eval_loss": 0.037851009517908096,
      "eval_runtime": 0.9779,
      "eval_samples_per_second": 51.128,
      "eval_steps_per_second": 13.293,
      "step": 50
    },
    {
      "epoch": 0.0390383925367779,
      "grad_norm": 0.3454943597316742,
      "learning_rate": 5.6472358726979935e-05,
      "loss": 0.2051,
      "step": 51
    },
    {
      "epoch": 0.03980385121396962,
      "grad_norm": 1.5023900270462036,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.3154,
      "step": 52
    },
    {
      "epoch": 0.040569309891161344,
      "grad_norm": 0.16861777007579803,
      "learning_rate": 5.352764127302008e-05,
      "loss": 0.024,
      "step": 53
    },
    {
      "epoch": 0.04133476856835307,
      "grad_norm": 0.01335059478878975,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0005,
      "step": 54
    },
    {
      "epoch": 0.04210022724554479,
      "grad_norm": 0.01417592540383339,
      "learning_rate": 5.058922868516978e-05,
      "loss": 0.0006,
      "step": 55
    },
    {
      "epoch": 0.04286568592273651,
      "grad_norm": 0.010599881410598755,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0004,
      "step": 56
    },
    {
      "epoch": 0.043631144599928236,
      "grad_norm": 0.010219581425189972,
      "learning_rate": 4.7669703697243516e-05,
      "loss": 0.0004,
      "step": 57
    },
    {
      "epoch": 0.04439660327711996,
      "grad_norm": 0.008394899778068066,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0004,
      "step": 58
    },
    {
      "epoch": 0.04516206195431169,
      "grad_norm": 0.010442732833325863,
      "learning_rate": 4.478156816345321e-05,
      "loss": 0.0004,
      "step": 59
    },
    {
      "epoch": 0.04592752063150341,
      "grad_norm": 0.01015259325504303,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0004,
      "step": 60
    },
    {
      "epoch": 0.046692979308695134,
      "grad_norm": 0.013029181398451328,
      "learning_rate": 4.19371895235492e-05,
      "loss": 0.0003,
      "step": 61
    },
    {
      "epoch": 0.04745843798588686,
      "grad_norm": 0.0073064109310507774,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0003,
      "step": 62
    },
    {
      "epoch": 0.04822389666307858,
      "grad_norm": 0.2842812240123749,
      "learning_rate": 3.9148747843544495e-05,
      "loss": 0.1657,
      "step": 63
    },
    {
      "epoch": 0.0489893553402703,
      "grad_norm": 0.26676300168037415,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.1517,
      "step": 64
    },
    {
      "epoch": 0.049754814017462026,
      "grad_norm": 0.5113205909729004,
      "learning_rate": 3.642818365880224e-05,
      "loss": 0.1416,
      "step": 65
    },
    {
      "epoch": 0.05052027269465375,
      "grad_norm": 0.19968412816524506,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0041,
      "step": 66
    },
    {
      "epoch": 0.05128573137184547,
      "grad_norm": 0.08529309928417206,
      "learning_rate": 3.378714684283011e-05,
      "loss": 0.0021,
      "step": 67
    },
    {
      "epoch": 0.052051190049037195,
      "grad_norm": 0.03840894624590874,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0011,
      "step": 68
    },
    {
      "epoch": 0.05281664872622892,
      "grad_norm": 0.02306171879172325,
      "learning_rate": 3.123694672073344e-05,
      "loss": 0.0006,
      "step": 69
    },
    {
      "epoch": 0.05358210740342064,
      "grad_norm": 0.012097193859517574,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0004,
      "step": 70
    },
    {
      "epoch": 0.054347566080612364,
      "grad_norm": 0.010973786003887653,
      "learning_rate": 2.8788503640948912e-05,
      "loss": 0.0004,
      "step": 71
    },
    {
      "epoch": 0.055113024757804094,
      "grad_norm": 0.01180847268551588,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0004,
      "step": 72
    },
    {
      "epoch": 0.05587848343499582,
      "grad_norm": 0.010331504046916962,
      "learning_rate": 2.645230221263596e-05,
      "loss": 0.0004,
      "step": 73
    },
    {
      "epoch": 0.05664394211218754,
      "grad_norm": 0.012231193482875824,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0004,
      "step": 74
    },
    {
      "epoch": 0.05740940078937926,
      "grad_norm": 0.009561908431351185,
      "learning_rate": 2.423834640897079e-05,
      "loss": 0.0003,
      "step": 75
    },
    {
      "epoch": 0.05740940078937926,
      "eval_loss": 0.021306684240698814,
      "eval_runtime": 1.043,
      "eval_samples_per_second": 47.938,
      "eval_steps_per_second": 12.464,
      "step": 75
    },
    {
      "epoch": 0.058174859466570986,
      "grad_norm": 0.18385003507137299,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.17,
      "step": 76
    },
    {
      "epoch": 0.05894031814376271,
      "grad_norm": 0.40027400851249695,
      "learning_rate": 2.215611672859741e-05,
      "loss": 0.1423,
      "step": 77
    },
    {
      "epoch": 0.05970577682095443,
      "grad_norm": 0.142598494887352,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0031,
      "step": 78
    },
    {
      "epoch": 0.060471235498146154,
      "grad_norm": 0.06515596807003021,
      "learning_rate": 2.0214529598676836e-05,
      "loss": 0.0014,
      "step": 79
    },
    {
      "epoch": 0.06123669417533788,
      "grad_norm": 0.05153204873204231,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0014,
      "step": 80
    },
    {
      "epoch": 0.0620021528525296,
      "grad_norm": 0.014992534182965755,
      "learning_rate": 1.842189919337732e-05,
      "loss": 0.0005,
      "step": 81
    },
    {
      "epoch": 0.06276761152972132,
      "grad_norm": 0.013885805383324623,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0004,
      "step": 82
    },
    {
      "epoch": 0.06353307020691305,
      "grad_norm": 0.010251723229885101,
      "learning_rate": 1.6785901831303956e-05,
      "loss": 0.0003,
      "step": 83
    },
    {
      "epoch": 0.06429852888410477,
      "grad_norm": 0.0075831301510334015,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0003,
      "step": 84
    },
    {
      "epoch": 0.0650639875612965,
      "grad_norm": 0.0066162901930511,
      "learning_rate": 1.531354310432403e-05,
      "loss": 0.0003,
      "step": 85
    },
    {
      "epoch": 0.06582944623848822,
      "grad_norm": 0.006637216545641422,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0002,
      "step": 86
    },
    {
      "epoch": 0.06659490491567994,
      "grad_norm": 0.011600018478929996,
      "learning_rate": 1.4011127878547087e-05,
      "loss": 0.0003,
      "step": 87
    },
    {
      "epoch": 0.06736036359287166,
      "grad_norm": 0.14439114928245544,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.1791,
      "step": 88
    },
    {
      "epoch": 0.06812582227006339,
      "grad_norm": 0.1987999677658081,
      "learning_rate": 1.2884233295920353e-05,
      "loss": 0.1352,
      "step": 89
    },
    {
      "epoch": 0.0688912809472551,
      "grad_norm": 0.19108176231384277,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.066,
      "step": 90
    },
    {
      "epoch": 0.06965673962444684,
      "grad_norm": 0.07157070934772491,
      "learning_rate": 1.1937684892050604e-05,
      "loss": 0.0013,
      "step": 91
    },
    {
      "epoch": 0.07042219830163857,
      "grad_norm": 0.04157419875264168,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0009,
      "step": 92
    },
    {
      "epoch": 0.07118765697883028,
      "grad_norm": 0.02740364894270897,
      "learning_rate": 1.1175535932519987e-05,
      "loss": 0.0007,
      "step": 93
    },
    {
      "epoch": 0.07195311565602201,
      "grad_norm": 0.013225646689534187,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0004,
      "step": 94
    },
    {
      "epoch": 0.07271857433321373,
      "grad_norm": 0.00674827815964818,
      "learning_rate": 1.0601050056180447e-05,
      "loss": 0.0002,
      "step": 95
    },
    {
      "epoch": 0.07348403301040546,
      "grad_norm": 0.005964465904980898,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0002,
      "step": 96
    },
    {
      "epoch": 0.07424949168759717,
      "grad_norm": 0.005700402893126011,
      "learning_rate": 1.0216687299751144e-05,
      "loss": 0.0002,
      "step": 97
    },
    {
      "epoch": 0.0750149503647889,
      "grad_norm": 0.005580263212323189,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0002,
      "step": 98
    },
    {
      "epoch": 0.07578040904198062,
      "grad_norm": 0.009917444549500942,
      "learning_rate": 1.0024093563563546e-05,
      "loss": 0.0002,
      "step": 99
    },
    {
      "epoch": 0.07654586771917235,
      "grad_norm": 0.0060340710915625095,
      "learning_rate": 1e-05,
      "loss": 0.0002,
      "step": 100
    },
    {
      "epoch": 0.07654586771917235,
      "eval_loss": 0.01876358687877655,
      "eval_runtime": 1.0439,
      "eval_samples_per_second": 47.897,
      "eval_steps_per_second": 12.453,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 5.965949609128755e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}