{
  "best_metric": 11.911147117614746,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.014739479696366718,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014739479696366717,
      "grad_norm": 0.35100623965263367,
      "learning_rate": 1e-06,
      "loss": 11.9361,
      "step": 1
    },
    {
      "epoch": 0.00014739479696366717,
      "eval_loss": 11.935647010803223,
      "eval_runtime": 28.2565,
      "eval_samples_per_second": 101.11,
      "eval_steps_per_second": 25.304,
      "step": 1
    },
    {
      "epoch": 0.00029478959392733434,
      "grad_norm": 0.43427085876464844,
      "learning_rate": 2e-06,
      "loss": 11.936,
      "step": 2
    },
    {
      "epoch": 0.00044218439089100157,
      "grad_norm": 0.3589724004268646,
      "learning_rate": 3e-06,
      "loss": 11.9356,
      "step": 3
    },
    {
      "epoch": 0.0005895791878546687,
      "grad_norm": 0.4418796896934509,
      "learning_rate": 4e-06,
      "loss": 11.9401,
      "step": 4
    },
    {
      "epoch": 0.000736973984818336,
      "grad_norm": 0.41620200872421265,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 11.9395,
      "step": 5
    },
    {
      "epoch": 0.0008843687817820031,
      "grad_norm": 0.40812376141548157,
      "learning_rate": 6e-06,
      "loss": 11.9332,
      "step": 6
    },
    {
      "epoch": 0.0010317635787456703,
      "grad_norm": 0.5508431196212769,
      "learning_rate": 7e-06,
      "loss": 11.9332,
      "step": 7
    },
    {
      "epoch": 0.0011791583757093374,
      "grad_norm": 0.4912180006504059,
      "learning_rate": 8e-06,
      "loss": 11.939,
      "step": 8
    },
    {
      "epoch": 0.0013265531726730046,
      "grad_norm": 0.3752216100692749,
      "learning_rate": 9e-06,
      "loss": 11.9346,
      "step": 9
    },
    {
      "epoch": 0.001473947969636672,
      "grad_norm": 0.4868999123573303,
      "learning_rate": 9.999999999999999e-06,
      "loss": 11.9301,
      "step": 10
    },
    {
      "epoch": 0.001621342766600339,
      "grad_norm": 0.4001573324203491,
      "learning_rate": 1.1e-05,
      "loss": 11.9349,
      "step": 11
    },
    {
      "epoch": 0.0017687375635640063,
      "grad_norm": 0.4238738715648651,
      "learning_rate": 1.2e-05,
      "loss": 11.9308,
      "step": 12
    },
    {
      "epoch": 0.0019161323605276733,
      "grad_norm": 0.4206545054912567,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 11.9329,
      "step": 13
    },
    {
      "epoch": 0.0020635271574913406,
      "grad_norm": 0.422513872385025,
      "learning_rate": 1.4e-05,
      "loss": 11.9281,
      "step": 14
    },
    {
      "epoch": 0.002210921954455008,
      "grad_norm": 0.45320990681648254,
      "learning_rate": 1.5e-05,
      "loss": 11.935,
      "step": 15
    },
    {
      "epoch": 0.0023583167514186747,
      "grad_norm": 0.3867875933647156,
      "learning_rate": 1.6e-05,
      "loss": 11.944,
      "step": 16
    },
    {
      "epoch": 0.002505711548382342,
      "grad_norm": 0.48071491718292236,
      "learning_rate": 1.7e-05,
      "loss": 11.9362,
      "step": 17
    },
    {
      "epoch": 0.0026531063453460093,
      "grad_norm": 0.38572871685028076,
      "learning_rate": 1.8e-05,
      "loss": 11.9346,
      "step": 18
    },
    {
      "epoch": 0.0028005011423096766,
      "grad_norm": 0.4020826816558838,
      "learning_rate": 1.9e-05,
      "loss": 11.9327,
      "step": 19
    },
    {
      "epoch": 0.002947895939273344,
      "grad_norm": 0.3733803629875183,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 11.9317,
      "step": 20
    },
    {
      "epoch": 0.0030952907362370107,
      "grad_norm": 0.5193566083908081,
      "learning_rate": 2.1e-05,
      "loss": 11.929,
      "step": 21
    },
    {
      "epoch": 0.003242685533200678,
      "grad_norm": 0.4131641387939453,
      "learning_rate": 2.2e-05,
      "loss": 11.9257,
      "step": 22
    },
    {
      "epoch": 0.0033900803301643453,
      "grad_norm": 0.537693977355957,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 11.9209,
      "step": 23
    },
    {
      "epoch": 0.0035374751271280125,
      "grad_norm": 0.36677348613739014,
      "learning_rate": 2.4e-05,
      "loss": 11.9224,
      "step": 24
    },
    {
      "epoch": 0.0036848699240916794,
      "grad_norm": 0.43583834171295166,
      "learning_rate": 2.5e-05,
      "loss": 11.9339,
      "step": 25
    },
    {
      "epoch": 0.0038322647210553467,
      "grad_norm": 0.5099343657493591,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 11.9235,
      "step": 26
    },
    {
      "epoch": 0.003979659518019014,
      "grad_norm": 0.517809271812439,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 11.9358,
      "step": 27
    },
    {
      "epoch": 0.004127054314982681,
      "grad_norm": 0.5331243276596069,
      "learning_rate": 2.8e-05,
      "loss": 11.9338,
      "step": 28
    },
    {
      "epoch": 0.0042744491119463485,
      "grad_norm": 0.6989299058914185,
      "learning_rate": 2.9e-05,
      "loss": 11.9256,
      "step": 29
    },
    {
      "epoch": 0.004421843908910016,
      "grad_norm": 0.5452754497528076,
      "learning_rate": 3e-05,
      "loss": 11.9337,
      "step": 30
    },
    {
      "epoch": 0.004569238705873683,
      "grad_norm": 0.7042813301086426,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 11.9234,
      "step": 31
    },
    {
      "epoch": 0.0047166335028373495,
      "grad_norm": 0.5744752287864685,
      "learning_rate": 2.993961440992859e-05,
      "loss": 11.9165,
      "step": 32
    },
    {
      "epoch": 0.004864028299801017,
      "grad_norm": 0.6824164390563965,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 11.9191,
      "step": 33
    },
    {
      "epoch": 0.005011423096764684,
      "grad_norm": 0.6746728420257568,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 11.9211,
      "step": 34
    },
    {
      "epoch": 0.005158817893728351,
      "grad_norm": 0.662025511264801,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 11.925,
      "step": 35
    },
    {
      "epoch": 0.005306212690692019,
      "grad_norm": 0.6042633652687073,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 11.9334,
      "step": 36
    },
    {
      "epoch": 0.005453607487655686,
      "grad_norm": 0.6327781081199646,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 11.9326,
      "step": 37
    },
    {
      "epoch": 0.005601002284619353,
      "grad_norm": 0.5950946807861328,
      "learning_rate": 2.904352305959606e-05,
      "loss": 11.9335,
      "step": 38
    },
    {
      "epoch": 0.00574839708158302,
      "grad_norm": 0.7648773193359375,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 11.9299,
      "step": 39
    },
    {
      "epoch": 0.005895791878546688,
      "grad_norm": 0.6954667568206787,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 11.9404,
      "step": 40
    },
    {
      "epoch": 0.006043186675510354,
      "grad_norm": 0.7465963363647461,
      "learning_rate": 2.820893297785107e-05,
      "loss": 11.9329,
      "step": 41
    },
    {
      "epoch": 0.006190581472474021,
      "grad_norm": 0.8332831859588623,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 11.9387,
      "step": 42
    },
    {
      "epoch": 0.006337976269437689,
      "grad_norm": 0.8731632828712463,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 11.9216,
      "step": 43
    },
    {
      "epoch": 0.006485371066401356,
      "grad_norm": 0.7785435318946838,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 11.9156,
      "step": 44
    },
    {
      "epoch": 0.006632765863365023,
      "grad_norm": 0.8320671319961548,
      "learning_rate": 2.672747223702045e-05,
      "loss": 11.9493,
      "step": 45
    },
    {
      "epoch": 0.0067801606603286905,
      "grad_norm": 1.1334259510040283,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 11.9229,
      "step": 46
    },
    {
      "epoch": 0.006927555457292358,
      "grad_norm": 1.0933701992034912,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 11.961,
      "step": 47
    },
    {
      "epoch": 0.007074950254256025,
      "grad_norm": 1.2650146484375,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 11.9437,
      "step": 48
    },
    {
      "epoch": 0.007222345051219692,
      "grad_norm": 1.2658061981201172,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 11.9361,
      "step": 49
    },
    {
      "epoch": 0.007369739848183359,
      "grad_norm": 1.4777532815933228,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 11.9409,
      "step": 50
    },
    {
      "epoch": 0.007369739848183359,
      "eval_loss": 11.921281814575195,
      "eval_runtime": 27.8756,
      "eval_samples_per_second": 102.491,
      "eval_steps_per_second": 25.65,
      "step": 50
    },
    {
      "epoch": 0.007517134645147026,
      "grad_norm": 0.5872039794921875,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 11.9115,
      "step": 51
    },
    {
      "epoch": 0.007664529442110693,
      "grad_norm": 0.6489221453666687,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 11.9098,
      "step": 52
    },
    {
      "epoch": 0.007811924239074361,
      "grad_norm": 0.6628962755203247,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 11.9117,
      "step": 53
    },
    {
      "epoch": 0.007959319036038028,
      "grad_norm": 0.7021000981330872,
      "learning_rate": 2.210802993709498e-05,
      "loss": 11.9152,
      "step": 54
    },
    {
      "epoch": 0.008106713833001695,
      "grad_norm": 0.5459302663803101,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 11.9118,
      "step": 55
    },
    {
      "epoch": 0.008254108629965362,
      "grad_norm": 0.6460722088813782,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 11.9029,
      "step": 56
    },
    {
      "epoch": 0.00840150342692903,
      "grad_norm": 0.5547419786453247,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 11.919,
      "step": 57
    },
    {
      "epoch": 0.008548898223892697,
      "grad_norm": 0.6414921879768372,
      "learning_rate": 1.963525491562421e-05,
      "loss": 11.9148,
      "step": 58
    },
    {
      "epoch": 0.008696293020856364,
      "grad_norm": 0.6565684080123901,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 11.9007,
      "step": 59
    },
    {
      "epoch": 0.008843687817820032,
      "grad_norm": 0.6434023380279541,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 11.9103,
      "step": 60
    },
    {
      "epoch": 0.008991082614783699,
      "grad_norm": 0.7591976523399353,
      "learning_rate": 1.767835342197955e-05,
      "loss": 11.9003,
      "step": 61
    },
    {
      "epoch": 0.009138477411747366,
      "grad_norm": 0.7066131234169006,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 11.9028,
      "step": 62
    },
    {
      "epoch": 0.009285872208711032,
      "grad_norm": 0.5851216316223145,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 11.9107,
      "step": 63
    },
    {
      "epoch": 0.009433267005674699,
      "grad_norm": 0.6990211009979248,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 11.9065,
      "step": 64
    },
    {
      "epoch": 0.009580661802638366,
      "grad_norm": 0.584298849105835,
      "learning_rate": 1.5e-05,
      "loss": 11.9111,
      "step": 65
    },
    {
      "epoch": 0.009728056599602034,
      "grad_norm": 0.5437385439872742,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 11.9126,
      "step": 66
    },
    {
      "epoch": 0.0098754513965657,
      "grad_norm": 0.5812602639198303,
      "learning_rate": 1.36554103664485e-05,
      "loss": 11.9088,
      "step": 67
    },
    {
      "epoch": 0.010022846193529368,
      "grad_norm": 0.5316656827926636,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 11.9143,
      "step": 68
    },
    {
      "epoch": 0.010170240990493035,
      "grad_norm": 0.7123498320579529,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 11.8966,
      "step": 69
    },
    {
      "epoch": 0.010317635787456703,
      "grad_norm": 0.650571346282959,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 11.9099,
      "step": 70
    },
    {
      "epoch": 0.01046503058442037,
      "grad_norm": 0.5798699259757996,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 11.9111,
      "step": 71
    },
    {
      "epoch": 0.010612425381384037,
      "grad_norm": 0.6300530433654785,
      "learning_rate": 1.036474508437579e-05,
      "loss": 11.9058,
      "step": 72
    },
    {
      "epoch": 0.010759820178347704,
      "grad_norm": 0.5782929062843323,
      "learning_rate": 9.729377638779859e-06,
      "loss": 11.9175,
      "step": 73
    },
    {
      "epoch": 0.010907214975311372,
      "grad_norm": 0.6827853322029114,
      "learning_rate": 9.104624525191147e-06,
      "loss": 11.9128,
      "step": 74
    },
    {
      "epoch": 0.011054609772275039,
      "grad_norm": 0.5620612502098083,
      "learning_rate": 8.491743913236629e-06,
      "loss": 11.9179,
      "step": 75
    },
    {
      "epoch": 0.011202004569238706,
      "grad_norm": 0.6192479729652405,
      "learning_rate": 7.89197006290502e-06,
      "loss": 11.909,
      "step": 76
    },
    {
      "epoch": 0.011349399366202374,
      "grad_norm": 0.7718151211738586,
      "learning_rate": 7.30651083891141e-06,
      "loss": 11.9166,
      "step": 77
    },
    {
      "epoch": 0.01149679416316604,
      "grad_norm": 0.6424961090087891,
      "learning_rate": 6.736545278218464e-06,
      "loss": 11.9209,
      "step": 78
    },
    {
      "epoch": 0.011644188960129708,
      "grad_norm": 0.7047587633132935,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 11.9061,
      "step": 79
    },
    {
      "epoch": 0.011791583757093375,
      "grad_norm": 0.7561933994293213,
      "learning_rate": 5.647652972118998e-06,
      "loss": 11.9037,
      "step": 80
    },
    {
      "epoch": 0.011938978554057041,
      "grad_norm": 0.6360583305358887,
      "learning_rate": 5.130919110904311e-06,
      "loss": 11.8987,
      "step": 81
    },
    {
      "epoch": 0.012086373351020708,
      "grad_norm": 0.6373894214630127,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 11.913,
      "step": 82
    },
    {
      "epoch": 0.012233768147984376,
      "grad_norm": 0.6560659408569336,
      "learning_rate": 4.158077042589129e-06,
      "loss": 11.9012,
      "step": 83
    },
    {
      "epoch": 0.012381162944948043,
      "grad_norm": 0.6833062767982483,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 11.9041,
      "step": 84
    },
    {
      "epoch": 0.01252855774191171,
      "grad_norm": 0.6426090598106384,
      "learning_rate": 3.272527762979553e-06,
      "loss": 11.9201,
      "step": 85
    },
    {
      "epoch": 0.012675952538875377,
      "grad_norm": 0.6073688864707947,
      "learning_rate": 2.86474508437579e-06,
      "loss": 11.9167,
      "step": 86
    },
    {
      "epoch": 0.012823347335839045,
      "grad_norm": 0.8581821918487549,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 11.8962,
      "step": 87
    },
    {
      "epoch": 0.012970742132802712,
      "grad_norm": 0.8890104293823242,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 11.8993,
      "step": 88
    },
    {
      "epoch": 0.01311813692976638,
      "grad_norm": 0.6319490075111389,
      "learning_rate": 1.79106702214893e-06,
      "loss": 11.9299,
      "step": 89
    },
    {
      "epoch": 0.013265531726730046,
      "grad_norm": 0.9312055706977844,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 11.9074,
      "step": 90
    },
    {
      "epoch": 0.013412926523693714,
      "grad_norm": 1.1547194719314575,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 11.9202,
      "step": 91
    },
    {
      "epoch": 0.013560321320657381,
      "grad_norm": 0.8375909328460693,
      "learning_rate": 9.56476940403942e-07,
      "loss": 11.9072,
      "step": 92
    },
    {
      "epoch": 0.013707716117621048,
      "grad_norm": 0.786160945892334,
      "learning_rate": 7.341522555726971e-07,
      "loss": 11.922,
      "step": 93
    },
    {
      "epoch": 0.013855110914584716,
      "grad_norm": 0.7640759944915771,
      "learning_rate": 5.405570895622014e-07,
      "loss": 11.9342,
      "step": 94
    },
    {
      "epoch": 0.014002505711548383,
      "grad_norm": 1.0815062522888184,
      "learning_rate": 3.760813172726457e-07,
      "loss": 11.9631,
      "step": 95
    },
    {
      "epoch": 0.01414990050851205,
      "grad_norm": 1.0811342000961304,
      "learning_rate": 2.41056171020555e-07,
      "loss": 11.9287,
      "step": 96
    },
    {
      "epoch": 0.014297295305475717,
      "grad_norm": 1.0506001710891724,
      "learning_rate": 1.357535734809795e-07,
      "loss": 11.9304,
      "step": 97
    },
    {
      "epoch": 0.014444690102439385,
      "grad_norm": 1.1852604150772095,
      "learning_rate": 6.038559007141397e-08,
      "loss": 11.9235,
      "step": 98
    },
    {
      "epoch": 0.01459208489940305,
      "grad_norm": 1.3889933824539185,
      "learning_rate": 1.510400188028116e-08,
      "loss": 11.9587,
      "step": 99
    },
    {
      "epoch": 0.014739479696366718,
      "grad_norm": 1.4530335664749146,
      "learning_rate": 0.0,
      "loss": 11.9395,
      "step": 100
    },
    {
      "epoch": 0.014739479696366718,
      "eval_loss": 11.911147117614746,
      "eval_runtime": 27.8546,
      "eval_samples_per_second": 102.568,
      "eval_steps_per_second": 25.669,
      "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": 27682504704000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}