{
  "best_metric": 0.7020787596702576,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.15055467511885895,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001584786053882726,
      "grad_norm": 2.344426393508911,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.1155,
      "step": 1
    },
    {
      "epoch": 0.001584786053882726,
      "eval_loss": 4.5734944343566895,
      "eval_runtime": 3.2337,
      "eval_samples_per_second": 15.462,
      "eval_steps_per_second": 4.02,
      "step": 1
    },
    {
      "epoch": 0.003169572107765452,
      "grad_norm": 1.989837884902954,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.0433,
      "step": 2
    },
    {
      "epoch": 0.004754358161648178,
      "grad_norm": 2.0686755180358887,
      "learning_rate": 0.0001,
      "loss": 3.0158,
      "step": 3
    },
    {
      "epoch": 0.006339144215530904,
      "grad_norm": 2.5443685054779053,
      "learning_rate": 9.997376600647783e-05,
      "loss": 2.9057,
      "step": 4
    },
    {
      "epoch": 0.00792393026941363,
      "grad_norm": 2.039285659790039,
      "learning_rate": 9.989509461357426e-05,
      "loss": 2.3574,
      "step": 5
    },
    {
      "epoch": 0.009508716323296355,
      "grad_norm": 2.248792886734009,
      "learning_rate": 9.976407754861426e-05,
      "loss": 2.1331,
      "step": 6
    },
    {
      "epoch": 0.011093502377179081,
      "grad_norm": 1.847161889076233,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.762,
      "step": 7
    },
    {
      "epoch": 0.012678288431061807,
      "grad_norm": 2.0366954803466797,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.6532,
      "step": 8
    },
    {
      "epoch": 0.014263074484944533,
      "grad_norm": 2.5140931606292725,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.4923,
      "step": 9
    },
    {
      "epoch": 0.01584786053882726,
      "grad_norm": 2.7745964527130127,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.0749,
      "step": 10
    },
    {
      "epoch": 0.017432646592709985,
      "grad_norm": 2.2155520915985107,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.9472,
      "step": 11
    },
    {
      "epoch": 0.01901743264659271,
      "grad_norm": 3.2750940322875977,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.2059,
      "step": 12
    },
    {
      "epoch": 0.020602218700475437,
      "grad_norm": 7.851731777191162,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.2002,
      "step": 13
    },
    {
      "epoch": 0.022187004754358162,
      "grad_norm": 2.0609889030456543,
      "learning_rate": 9.686252995020249e-05,
      "loss": 1.0557,
      "step": 14
    },
    {
      "epoch": 0.02377179080824089,
      "grad_norm": 1.621334433555603,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.8744,
      "step": 15
    },
    {
      "epoch": 0.025356576862123614,
      "grad_norm": 1.06352961063385,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.9567,
      "step": 16
    },
    {
      "epoch": 0.02694136291600634,
      "grad_norm": 1.0080907344818115,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.9841,
      "step": 17
    },
    {
      "epoch": 0.028526148969889066,
      "grad_norm": 1.0307260751724243,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.8911,
      "step": 18
    },
    {
      "epoch": 0.030110935023771792,
      "grad_norm": 0.9563176035881042,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.8358,
      "step": 19
    },
    {
      "epoch": 0.03169572107765452,
      "grad_norm": 0.9397155046463013,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.6939,
      "step": 20
    },
    {
      "epoch": 0.03328050713153724,
      "grad_norm": 0.9912440180778503,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.6091,
      "step": 21
    },
    {
      "epoch": 0.03486529318541997,
      "grad_norm": 0.9592384099960327,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.7451,
      "step": 22
    },
    {
      "epoch": 0.03645007923930269,
      "grad_norm": 1.3581793308258057,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.6801,
      "step": 23
    },
    {
      "epoch": 0.03803486529318542,
      "grad_norm": 1.7192140817642212,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.7422,
      "step": 24
    },
    {
      "epoch": 0.039619651347068144,
      "grad_norm": 1.995835304260254,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.8001,
      "step": 25
    },
    {
      "epoch": 0.039619651347068144,
      "eval_loss": 0.8743540048599243,
      "eval_runtime": 3.2909,
      "eval_samples_per_second": 15.193,
      "eval_steps_per_second": 3.95,
      "step": 25
    },
    {
      "epoch": 0.04120443740095087,
      "grad_norm": 0.7731386423110962,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.8463,
      "step": 26
    },
    {
      "epoch": 0.042789223454833596,
      "grad_norm": 0.6917439103126526,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.8448,
      "step": 27
    },
    {
      "epoch": 0.044374009508716325,
      "grad_norm": 0.6431922316551208,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.7683,
      "step": 28
    },
    {
      "epoch": 0.04595879556259905,
      "grad_norm": 0.7308835387229919,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.9075,
      "step": 29
    },
    {
      "epoch": 0.04754358161648178,
      "grad_norm": 1.5559896230697632,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.7099,
      "step": 30
    },
    {
      "epoch": 0.0491283676703645,
      "grad_norm": 0.7101494669914246,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.7386,
      "step": 31
    },
    {
      "epoch": 0.05071315372424723,
      "grad_norm": 0.7161931991577148,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.6076,
      "step": 32
    },
    {
      "epoch": 0.05229793977812995,
      "grad_norm": 0.7691206336021423,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.6235,
      "step": 33
    },
    {
      "epoch": 0.05388272583201268,
      "grad_norm": 0.9122820496559143,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.7181,
      "step": 34
    },
    {
      "epoch": 0.0554675118858954,
      "grad_norm": 1.6549066305160522,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.7327,
      "step": 35
    },
    {
      "epoch": 0.05705229793977813,
      "grad_norm": 2.5280091762542725,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.5369,
      "step": 36
    },
    {
      "epoch": 0.058637083993660855,
      "grad_norm": 1.9925541877746582,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.5835,
      "step": 37
    },
    {
      "epoch": 0.060221870047543584,
      "grad_norm": 1.2063634395599365,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.8154,
      "step": 38
    },
    {
      "epoch": 0.061806656101426306,
      "grad_norm": 0.6842193603515625,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.8401,
      "step": 39
    },
    {
      "epoch": 0.06339144215530904,
      "grad_norm": 0.6004986763000488,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.6677,
      "step": 40
    },
    {
      "epoch": 0.06497622820919176,
      "grad_norm": 0.5825014710426331,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.7524,
      "step": 41
    },
    {
      "epoch": 0.06656101426307448,
      "grad_norm": 0.966681182384491,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.8021,
      "step": 42
    },
    {
      "epoch": 0.06814580031695722,
      "grad_norm": 0.6058341860771179,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.6558,
      "step": 43
    },
    {
      "epoch": 0.06973058637083994,
      "grad_norm": 0.730965256690979,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.5955,
      "step": 44
    },
    {
      "epoch": 0.07131537242472266,
      "grad_norm": 0.8394338488578796,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.6537,
      "step": 45
    },
    {
      "epoch": 0.07290015847860538,
      "grad_norm": 0.7698927521705627,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.7215,
      "step": 46
    },
    {
      "epoch": 0.07448494453248812,
      "grad_norm": 1.0021368265151978,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.5779,
      "step": 47
    },
    {
      "epoch": 0.07606973058637084,
      "grad_norm": 0.9064629077911377,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.4996,
      "step": 48
    },
    {
      "epoch": 0.07765451664025357,
      "grad_norm": 1.479453682899475,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.5706,
      "step": 49
    },
    {
      "epoch": 0.07923930269413629,
      "grad_norm": 1.81675124168396,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.6822,
      "step": 50
    },
    {
      "epoch": 0.07923930269413629,
      "eval_loss": 0.7424139976501465,
      "eval_runtime": 3.2822,
      "eval_samples_per_second": 15.234,
      "eval_steps_per_second": 3.961,
      "step": 50
    },
    {
      "epoch": 0.08082408874801902,
      "grad_norm": 0.706727921962738,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.9714,
      "step": 51
    },
    {
      "epoch": 0.08240887480190175,
      "grad_norm": 0.6248128414154053,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.7904,
      "step": 52
    },
    {
      "epoch": 0.08399366085578447,
      "grad_norm": 0.6073558330535889,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.7816,
      "step": 53
    },
    {
      "epoch": 0.08557844690966719,
      "grad_norm": 0.5754700899124146,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.7652,
      "step": 54
    },
    {
      "epoch": 0.08716323296354993,
      "grad_norm": 0.5993666052818298,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.7248,
      "step": 55
    },
    {
      "epoch": 0.08874801901743265,
      "grad_norm": 0.645228922367096,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.8138,
      "step": 56
    },
    {
      "epoch": 0.09033280507131537,
      "grad_norm": 0.825614869594574,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.5822,
      "step": 57
    },
    {
      "epoch": 0.0919175911251981,
      "grad_norm": 0.6977015733718872,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.6557,
      "step": 58
    },
    {
      "epoch": 0.09350237717908082,
      "grad_norm": 0.8051120638847351,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.6739,
      "step": 59
    },
    {
      "epoch": 0.09508716323296355,
      "grad_norm": 0.9124981164932251,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.6184,
      "step": 60
    },
    {
      "epoch": 0.09667194928684628,
      "grad_norm": 1.1939939260482788,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.6686,
      "step": 61
    },
    {
      "epoch": 0.098256735340729,
      "grad_norm": 1.1615188121795654,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.5636,
      "step": 62
    },
    {
      "epoch": 0.09984152139461172,
      "grad_norm": 0.9352508187294006,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.6433,
      "step": 63
    },
    {
      "epoch": 0.10142630744849446,
      "grad_norm": 0.5545775890350342,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.8057,
      "step": 64
    },
    {
      "epoch": 0.10301109350237718,
      "grad_norm": 0.6947957873344421,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.7252,
      "step": 65
    },
    {
      "epoch": 0.1045958795562599,
      "grad_norm": 0.5455904603004456,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.6677,
      "step": 66
    },
    {
      "epoch": 0.10618066561014262,
      "grad_norm": 0.6412747502326965,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.7173,
      "step": 67
    },
    {
      "epoch": 0.10776545166402536,
      "grad_norm": 0.5318034887313843,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.5931,
      "step": 68
    },
    {
      "epoch": 0.10935023771790808,
      "grad_norm": 0.6276905536651611,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.7394,
      "step": 69
    },
    {
      "epoch": 0.1109350237717908,
      "grad_norm": 0.6510589122772217,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.6478,
      "step": 70
    },
    {
      "epoch": 0.11251980982567353,
      "grad_norm": 0.6245140433311462,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.5465,
      "step": 71
    },
    {
      "epoch": 0.11410459587955626,
      "grad_norm": 0.7210938334465027,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.5694,
      "step": 72
    },
    {
      "epoch": 0.11568938193343899,
      "grad_norm": 0.6950007677078247,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.5108,
      "step": 73
    },
    {
      "epoch": 0.11727416798732171,
      "grad_norm": 0.887366771697998,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.4886,
      "step": 74
    },
    {
      "epoch": 0.11885895404120443,
      "grad_norm": 1.3450919389724731,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.5812,
      "step": 75
    },
    {
      "epoch": 0.11885895404120443,
      "eval_loss": 0.7020787596702576,
      "eval_runtime": 3.311,
      "eval_samples_per_second": 15.101,
      "eval_steps_per_second": 3.926,
      "step": 75
    },
    {
      "epoch": 0.12044374009508717,
      "grad_norm": 0.557953953742981,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.7917,
      "step": 76
    },
    {
      "epoch": 0.12202852614896989,
      "grad_norm": 0.5222028493881226,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.7734,
      "step": 77
    },
    {
      "epoch": 0.12361331220285261,
      "grad_norm": 0.5229513645172119,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.7783,
      "step": 78
    },
    {
      "epoch": 0.12519809825673534,
      "grad_norm": 0.5746840238571167,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.7599,
      "step": 79
    },
    {
      "epoch": 0.12678288431061807,
      "grad_norm": 0.523705244064331,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.6275,
      "step": 80
    },
    {
      "epoch": 0.12836767036450078,
      "grad_norm": 0.5565693974494934,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.701,
      "step": 81
    },
    {
      "epoch": 0.12995245641838352,
      "grad_norm": 0.5287532210350037,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.5081,
      "step": 82
    },
    {
      "epoch": 0.13153724247226625,
      "grad_norm": 0.594470739364624,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.5422,
      "step": 83
    },
    {
      "epoch": 0.13312202852614896,
      "grad_norm": 0.6673708558082581,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.5362,
      "step": 84
    },
    {
      "epoch": 0.1347068145800317,
      "grad_norm": 0.9278484582901001,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.6325,
      "step": 85
    },
    {
      "epoch": 0.13629160063391443,
      "grad_norm": 0.8525876998901367,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.5122,
      "step": 86
    },
    {
      "epoch": 0.13787638668779714,
      "grad_norm": 1.6866328716278076,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.6012,
      "step": 87
    },
    {
      "epoch": 0.13946117274167988,
      "grad_norm": 0.9566619992256165,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.7856,
      "step": 88
    },
    {
      "epoch": 0.1410459587955626,
      "grad_norm": 0.5302878618240356,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.8218,
      "step": 89
    },
    {
      "epoch": 0.14263074484944532,
      "grad_norm": 0.4923751950263977,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.7623,
      "step": 90
    },
    {
      "epoch": 0.14421553090332806,
      "grad_norm": 0.5600050091743469,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.6418,
      "step": 91
    },
    {
      "epoch": 0.14580031695721077,
      "grad_norm": 0.528347373008728,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.6164,
      "step": 92
    },
    {
      "epoch": 0.1473851030110935,
      "grad_norm": 0.571899950504303,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.723,
      "step": 93
    },
    {
      "epoch": 0.14896988906497624,
      "grad_norm": 0.5378746390342712,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.509,
      "step": 94
    },
    {
      "epoch": 0.15055467511885895,
      "grad_norm": 0.6092713475227356,
      "learning_rate": 1e-05,
      "loss": 0.5414,
      "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": 1.0108364981796864e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}