{
  "best_metric": 1.9553877115249634,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.10020040080160321,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001002004008016032,
      "grad_norm": 1.9892041683197021,
      "learning_rate": 1e-05,
      "loss": 3.228,
      "step": 1
    },
    {
      "epoch": 0.001002004008016032,
      "eval_loss": 3.713639497756958,
      "eval_runtime": 9.9764,
      "eval_samples_per_second": 168.497,
      "eval_steps_per_second": 21.15,
      "step": 1
    },
    {
      "epoch": 0.002004008016032064,
      "grad_norm": 2.06142520904541,
      "learning_rate": 2e-05,
      "loss": 3.3001,
      "step": 2
    },
    {
      "epoch": 0.003006012024048096,
      "grad_norm": 1.839006781578064,
      "learning_rate": 3e-05,
      "loss": 3.1721,
      "step": 3
    },
    {
      "epoch": 0.004008016032064128,
      "grad_norm": 2.000424861907959,
      "learning_rate": 4e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.00501002004008016,
      "grad_norm": 1.9487165212631226,
      "learning_rate": 5e-05,
      "loss": 3.2505,
      "step": 5
    },
    {
      "epoch": 0.006012024048096192,
      "grad_norm": 1.8743599653244019,
      "learning_rate": 6e-05,
      "loss": 3.3262,
      "step": 6
    },
    {
      "epoch": 0.0070140280561122245,
      "grad_norm": 1.6559370756149292,
      "learning_rate": 7e-05,
      "loss": 3.2131,
      "step": 7
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 1.6868617534637451,
      "learning_rate": 8e-05,
      "loss": 3.1389,
      "step": 8
    },
    {
      "epoch": 0.009018036072144289,
      "grad_norm": 1.593652606010437,
      "learning_rate": 9e-05,
      "loss": 3.1291,
      "step": 9
    },
    {
      "epoch": 0.01002004008016032,
      "grad_norm": 1.531032681465149,
      "learning_rate": 0.0001,
      "loss": 3.1035,
      "step": 10
    },
    {
      "epoch": 0.011022044088176353,
      "grad_norm": 1.59713876247406,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.0948,
      "step": 11
    },
    {
      "epoch": 0.012024048096192385,
      "grad_norm": 1.5284147262573242,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8201,
      "step": 12
    },
    {
      "epoch": 0.013026052104208416,
      "grad_norm": 1.542348027229309,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.8589,
      "step": 13
    },
    {
      "epoch": 0.014028056112224449,
      "grad_norm": 1.7238450050354004,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.8647,
      "step": 14
    },
    {
      "epoch": 0.01503006012024048,
      "grad_norm": 1.7485935688018799,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.7815,
      "step": 15
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 1.9041484594345093,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.751,
      "step": 16
    },
    {
      "epoch": 0.017034068136272545,
      "grad_norm": 1.754050850868225,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.6011,
      "step": 17
    },
    {
      "epoch": 0.018036072144288578,
      "grad_norm": 1.5712624788284302,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6006,
      "step": 18
    },
    {
      "epoch": 0.01903807615230461,
      "grad_norm": 1.6208561658859253,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.57,
      "step": 19
    },
    {
      "epoch": 0.02004008016032064,
      "grad_norm": 1.7021604776382446,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5362,
      "step": 20
    },
    {
      "epoch": 0.021042084168336674,
      "grad_norm": 1.6615126132965088,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4146,
      "step": 21
    },
    {
      "epoch": 0.022044088176352707,
      "grad_norm": 1.4819920063018799,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.4761,
      "step": 22
    },
    {
      "epoch": 0.023046092184368736,
      "grad_norm": 1.5472745895385742,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.3338,
      "step": 23
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 1.9091078042984009,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3523,
      "step": 24
    },
    {
      "epoch": 0.025050100200400802,
      "grad_norm": 1.7454297542572021,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3323,
      "step": 25
    },
    {
      "epoch": 0.026052104208416832,
      "grad_norm": 1.334761142730713,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.3424,
      "step": 26
    },
    {
      "epoch": 0.027054108216432865,
      "grad_norm": 1.5471727848052979,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3023,
      "step": 27
    },
    {
      "epoch": 0.028056112224448898,
      "grad_norm": 2.1018128395080566,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3096,
      "step": 28
    },
    {
      "epoch": 0.02905811623246493,
      "grad_norm": 2.2362749576568604,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.4362,
      "step": 29
    },
    {
      "epoch": 0.03006012024048096,
      "grad_norm": 1.7347625494003296,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.4654,
      "step": 30
    },
    {
      "epoch": 0.031062124248496994,
      "grad_norm": 1.1744818687438965,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.2959,
      "step": 31
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 1.3074371814727783,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2445,
      "step": 32
    },
    {
      "epoch": 0.033066132264529056,
      "grad_norm": 1.2176134586334229,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.212,
      "step": 33
    },
    {
      "epoch": 0.03406813627254509,
      "grad_norm": 1.319883942604065,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2957,
      "step": 34
    },
    {
      "epoch": 0.03507014028056112,
      "grad_norm": 1.2122143507003784,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3501,
      "step": 35
    },
    {
      "epoch": 0.036072144288577156,
      "grad_norm": 1.1644178628921509,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.226,
      "step": 36
    },
    {
      "epoch": 0.03707414829659319,
      "grad_norm": 1.1486573219299316,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2286,
      "step": 37
    },
    {
      "epoch": 0.03807615230460922,
      "grad_norm": 1.1184206008911133,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.1459,
      "step": 38
    },
    {
      "epoch": 0.03907815631262525,
      "grad_norm": 1.2232961654663086,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.2814,
      "step": 39
    },
    {
      "epoch": 0.04008016032064128,
      "grad_norm": 1.3489000797271729,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3264,
      "step": 40
    },
    {
      "epoch": 0.041082164328657314,
      "grad_norm": 1.279327154159546,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3779,
      "step": 41
    },
    {
      "epoch": 0.04208416833667335,
      "grad_norm": 1.269199013710022,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.26,
      "step": 42
    },
    {
      "epoch": 0.04308617234468938,
      "grad_norm": 1.5359389781951904,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.355,
      "step": 43
    },
    {
      "epoch": 0.04408817635270541,
      "grad_norm": 1.267220377922058,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.1603,
      "step": 44
    },
    {
      "epoch": 0.045090180360721446,
      "grad_norm": 1.2115416526794434,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0991,
      "step": 45
    },
    {
      "epoch": 0.04609218436873747,
      "grad_norm": 1.1847515106201172,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1158,
      "step": 46
    },
    {
      "epoch": 0.047094188376753505,
      "grad_norm": 1.1961596012115479,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1763,
      "step": 47
    },
    {
      "epoch": 0.04809619238476954,
      "grad_norm": 2.5090718269348145,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2434,
      "step": 48
    },
    {
      "epoch": 0.04909819639278557,
      "grad_norm": 1.6135358810424805,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.3868,
      "step": 49
    },
    {
      "epoch": 0.050100200400801605,
      "grad_norm": 1.4976840019226074,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.3013,
      "step": 50
    },
    {
      "epoch": 0.050100200400801605,
      "eval_loss": 2.088284492492676,
      "eval_runtime": 9.5901,
      "eval_samples_per_second": 175.286,
      "eval_steps_per_second": 22.002,
      "step": 50
    },
    {
      "epoch": 0.05110220440881764,
      "grad_norm": 5.009476661682129,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.1321,
      "step": 51
    },
    {
      "epoch": 0.052104208416833664,
      "grad_norm": 3.8039870262145996,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.0542,
      "step": 52
    },
    {
      "epoch": 0.0531062124248497,
      "grad_norm": 1.9156354665756226,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8746,
      "step": 53
    },
    {
      "epoch": 0.05410821643286573,
      "grad_norm": 1.2341103553771973,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0515,
      "step": 54
    },
    {
      "epoch": 0.05511022044088176,
      "grad_norm": 1.197675108909607,
      "learning_rate": 5e-05,
      "loss": 1.9927,
      "step": 55
    },
    {
      "epoch": 0.056112224448897796,
      "grad_norm": 1.473565936088562,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.9117,
      "step": 56
    },
    {
      "epoch": 0.05711422845691383,
      "grad_norm": 1.9182207584381104,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.9596,
      "step": 57
    },
    {
      "epoch": 0.05811623246492986,
      "grad_norm": 1.9375628232955933,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.8432,
      "step": 58
    },
    {
      "epoch": 0.05911823647294589,
      "grad_norm": 1.3622163534164429,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.9311,
      "step": 59
    },
    {
      "epoch": 0.06012024048096192,
      "grad_norm": 1.1024616956710815,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.9859,
      "step": 60
    },
    {
      "epoch": 0.061122244488977955,
      "grad_norm": 1.1622207164764404,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.0643,
      "step": 61
    },
    {
      "epoch": 0.06212424849699399,
      "grad_norm": 0.9732226133346558,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.9253,
      "step": 62
    },
    {
      "epoch": 0.06312625250501001,
      "grad_norm": 0.9754781723022461,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8487,
      "step": 63
    },
    {
      "epoch": 0.06412825651302605,
      "grad_norm": 0.9494886994361877,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.8671,
      "step": 64
    },
    {
      "epoch": 0.06513026052104208,
      "grad_norm": 1.0573123693466187,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.9093,
      "step": 65
    },
    {
      "epoch": 0.06613226452905811,
      "grad_norm": 0.9759222865104675,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8703,
      "step": 66
    },
    {
      "epoch": 0.06713426853707415,
      "grad_norm": 1.0865356922149658,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.9515,
      "step": 67
    },
    {
      "epoch": 0.06813627254509018,
      "grad_norm": 1.320967435836792,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1222,
      "step": 68
    },
    {
      "epoch": 0.06913827655310621,
      "grad_norm": 1.0985479354858398,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.949,
      "step": 69
    },
    {
      "epoch": 0.07014028056112225,
      "grad_norm": 1.15016508102417,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.9248,
      "step": 70
    },
    {
      "epoch": 0.07114228456913828,
      "grad_norm": 1.0512685775756836,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.9727,
      "step": 71
    },
    {
      "epoch": 0.07214428857715431,
      "grad_norm": 1.0246506929397583,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9059,
      "step": 72
    },
    {
      "epoch": 0.07314629258517034,
      "grad_norm": 1.0503231287002563,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.903,
      "step": 73
    },
    {
      "epoch": 0.07414829659318638,
      "grad_norm": 1.047714352607727,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9435,
      "step": 74
    },
    {
      "epoch": 0.07515030060120241,
      "grad_norm": 0.9988422393798828,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8911,
      "step": 75
    },
    {
      "epoch": 0.07615230460921844,
      "grad_norm": 1.0220667123794556,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.9138,
      "step": 76
    },
    {
      "epoch": 0.07715430861723446,
      "grad_norm": 1.0607954263687134,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.0026,
      "step": 77
    },
    {
      "epoch": 0.0781563126252505,
      "grad_norm": 1.0461175441741943,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9518,
      "step": 78
    },
    {
      "epoch": 0.07915831663326653,
      "grad_norm": 1.0595484972000122,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.0095,
      "step": 79
    },
    {
      "epoch": 0.08016032064128256,
      "grad_norm": 1.0464117527008057,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.9532,
      "step": 80
    },
    {
      "epoch": 0.0811623246492986,
      "grad_norm": 1.083019495010376,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.0481,
      "step": 81
    },
    {
      "epoch": 0.08216432865731463,
      "grad_norm": 1.0056906938552856,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.896,
      "step": 82
    },
    {
      "epoch": 0.08316633266533066,
      "grad_norm": 1.087171196937561,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.022,
      "step": 83
    },
    {
      "epoch": 0.0841683366733467,
      "grad_norm": 1.0407052040100098,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.8995,
      "step": 84
    },
    {
      "epoch": 0.08517034068136273,
      "grad_norm": 1.1170405149459839,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8842,
      "step": 85
    },
    {
      "epoch": 0.08617234468937876,
      "grad_norm": 1.1040823459625244,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.867,
      "step": 86
    },
    {
      "epoch": 0.0871743486973948,
      "grad_norm": 1.0043014287948608,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.9638,
      "step": 87
    },
    {
      "epoch": 0.08817635270541083,
      "grad_norm": 1.1229714155197144,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.9637,
      "step": 88
    },
    {
      "epoch": 0.08917835671342686,
      "grad_norm": 1.1226463317871094,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.953,
      "step": 89
    },
    {
      "epoch": 0.09018036072144289,
      "grad_norm": 1.147606611251831,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.927,
      "step": 90
    },
    {
      "epoch": 0.09118236472945891,
      "grad_norm": 1.227723479270935,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9815,
      "step": 91
    },
    {
      "epoch": 0.09218436873747494,
      "grad_norm": 1.0677237510681152,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8739,
      "step": 92
    },
    {
      "epoch": 0.09318637274549098,
      "grad_norm": 1.1743624210357666,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.0189,
      "step": 93
    },
    {
      "epoch": 0.09418837675350701,
      "grad_norm": 1.2376830577850342,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.0479,
      "step": 94
    },
    {
      "epoch": 0.09519038076152304,
      "grad_norm": 1.1650396585464478,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.9083,
      "step": 95
    },
    {
      "epoch": 0.09619238476953908,
      "grad_norm": 1.2286704778671265,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.0419,
      "step": 96
    },
    {
      "epoch": 0.09719438877755511,
      "grad_norm": 1.3613375425338745,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.0559,
      "step": 97
    },
    {
      "epoch": 0.09819639278557114,
      "grad_norm": 1.5550633668899536,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.3656,
      "step": 98
    },
    {
      "epoch": 0.09919839679358718,
      "grad_norm": 1.7067337036132812,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.372,
      "step": 99
    },
    {
      "epoch": 0.10020040080160321,
      "grad_norm": 2.390549421310425,
      "learning_rate": 0.0,
      "loss": 2.2388,
      "step": 100
    },
    {
      "epoch": 0.10020040080160321,
      "eval_loss": 1.9553877115249634,
      "eval_runtime": 9.5891,
      "eval_samples_per_second": 175.303,
      "eval_steps_per_second": 22.004,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2976789823488000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}