{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.010980564401010211,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010980564401010212,
      "grad_norm": 0.005295205395668745,
      "learning_rate": 1e-05,
      "loss": 12.4581,
      "step": 1
    },
    {
      "epoch": 0.00010980564401010212,
      "eval_loss": NaN,
      "eval_runtime": 105.7149,
      "eval_samples_per_second": 145.088,
      "eval_steps_per_second": 36.277,
      "step": 1
    },
    {
      "epoch": 0.00021961128802020424,
      "grad_norm": 0.005485564470291138,
      "learning_rate": 2e-05,
      "loss": 12.4572,
      "step": 2
    },
    {
      "epoch": 0.00032941693203030636,
      "grad_norm": 0.004944846499711275,
      "learning_rate": 3e-05,
      "loss": 12.4557,
      "step": 3
    },
    {
      "epoch": 0.0004392225760404085,
      "grad_norm": 0.006096905097365379,
      "learning_rate": 4e-05,
      "loss": 12.4568,
      "step": 4
    },
    {
      "epoch": 0.0005490282200505106,
      "grad_norm": 0.005918541457504034,
      "learning_rate": 5e-05,
      "loss": 12.4486,
      "step": 5
    },
    {
      "epoch": 0.0006588338640606127,
      "grad_norm": 0.008583322167396545,
      "learning_rate": 6e-05,
      "loss": 12.4563,
      "step": 6
    },
    {
      "epoch": 0.0007686395080707148,
      "grad_norm": 0.007781935855746269,
      "learning_rate": 7e-05,
      "loss": 12.4584,
      "step": 7
    },
    {
      "epoch": 0.000878445152080817,
      "grad_norm": 0.0075157927349209785,
      "learning_rate": 8e-05,
      "loss": 12.4541,
      "step": 8
    },
    {
      "epoch": 0.000988250796090919,
      "grad_norm": 0.008060351014137268,
      "learning_rate": 9e-05,
      "loss": 12.454,
      "step": 9
    },
    {
      "epoch": 0.0010980564401010212,
      "grad_norm": 0.009477085433900356,
      "learning_rate": 0.0001,
      "loss": 12.4544,
      "step": 10
    },
    {
      "epoch": 0.0012078620841111233,
      "grad_norm": 0.00922788679599762,
      "learning_rate": 9.999316524962345e-05,
      "loss": 12.4502,
      "step": 11
    },
    {
      "epoch": 0.0013176677281212254,
      "grad_norm": 0.011367438361048698,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.4525,
      "step": 12
    },
    {
      "epoch": 0.0014274733721313276,
      "grad_norm": 0.010452193208038807,
      "learning_rate": 9.993849845741524e-05,
      "loss": 12.4521,
      "step": 13
    },
    {
      "epoch": 0.0015372790161414297,
      "grad_norm": 0.012774151749908924,
      "learning_rate": 9.989068136093873e-05,
      "loss": 12.4511,
      "step": 14
    },
    {
      "epoch": 0.0016470846601515318,
      "grad_norm": 0.012014582753181458,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4485,
      "step": 15
    },
    {
      "epoch": 0.001756890304161634,
      "grad_norm": 0.015250686556100845,
      "learning_rate": 9.975414512725057e-05,
      "loss": 12.4452,
      "step": 16
    },
    {
      "epoch": 0.001866695948171736,
      "grad_norm": 0.013115638867020607,
      "learning_rate": 9.966546331768191e-05,
      "loss": 12.4534,
      "step": 17
    },
    {
      "epoch": 0.001976501592181838,
      "grad_norm": 0.014557444490492344,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.4524,
      "step": 18
    },
    {
      "epoch": 0.00208630723619194,
      "grad_norm": 0.015748385339975357,
      "learning_rate": 9.944739353007344e-05,
      "loss": 12.4496,
      "step": 19
    },
    {
      "epoch": 0.0021961128802020424,
      "grad_norm": 0.01659594289958477,
      "learning_rate": 9.931806517013612e-05,
      "loss": 12.4684,
      "step": 20
    },
    {
      "epoch": 0.0023059185242121443,
      "grad_norm": 0.019817043095827103,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.448,
      "step": 21
    },
    {
      "epoch": 0.0024157241682222466,
      "grad_norm": 0.02010353095829487,
      "learning_rate": 9.901899829374047e-05,
      "loss": 12.4573,
      "step": 22
    },
    {
      "epoch": 0.0025255298122323485,
      "grad_norm": 0.021140344440937042,
      "learning_rate": 9.884934153917997e-05,
      "loss": 12.4504,
      "step": 23
    },
    {
      "epoch": 0.002635335456242451,
      "grad_norm": 0.03636853024363518,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4552,
      "step": 24
    },
    {
      "epoch": 0.0027451411002525528,
      "grad_norm": 0.024292292073369026,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.4455,
      "step": 25
    },
    {
      "epoch": 0.002854946744262655,
      "grad_norm": 0.0418277382850647,
      "learning_rate": 9.826044551386744e-05,
      "loss": 12.4445,
      "step": 26
    },
    {
      "epoch": 0.002964752388272757,
      "grad_norm": 0.03029468096792698,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.4518,
      "step": 27
    },
    {
      "epoch": 0.0030745580322828594,
      "grad_norm": 0.03751302883028984,
      "learning_rate": 9.780178907671789e-05,
      "loss": 12.4348,
      "step": 28
    },
    {
      "epoch": 0.0031843636762929613,
      "grad_norm": 0.03355684503912926,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.4521,
      "step": 29
    },
    {
      "epoch": 0.0032941693203030636,
      "grad_norm": 0.055962417274713516,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4396,
      "step": 30
    },
    {
      "epoch": 0.0034039749643131655,
      "grad_norm": 0.05316566675901413,
      "learning_rate": 9.701596950580806e-05,
      "loss": 12.4507,
      "step": 31
    },
    {
      "epoch": 0.003513780608323268,
      "grad_norm": 0.052443914115428925,
      "learning_rate": 9.672822322997305e-05,
      "loss": 12.4335,
      "step": 32
    },
    {
      "epoch": 0.0036235862523333697,
      "grad_norm": 0.10784019529819489,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.4565,
      "step": 33
    },
    {
      "epoch": 0.003733391896343472,
      "grad_norm": 0.09334560483694077,
      "learning_rate": 9.611448774886924e-05,
      "loss": 12.4436,
      "step": 34
    },
    {
      "epoch": 0.003843197540353574,
      "grad_norm": 0.08733153343200684,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.4456,
      "step": 35
    },
    {
      "epoch": 0.003953003184363676,
      "grad_norm": 0.09157176315784454,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4515,
      "step": 36
    },
    {
      "epoch": 0.004062808828373779,
      "grad_norm": 0.10120932757854462,
      "learning_rate": 9.509956150664796e-05,
      "loss": 12.452,
      "step": 37
    },
    {
      "epoch": 0.00417261447238388,
      "grad_norm": 0.1628744900226593,
      "learning_rate": 9.473646649103818e-05,
      "loss": 12.4513,
      "step": 38
    },
    {
      "epoch": 0.0042824201163939824,
      "grad_norm": 0.20253495872020721,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.459,
      "step": 39
    },
    {
      "epoch": 0.004392225760404085,
      "grad_norm": 0.1669420748949051,
      "learning_rate": 9.397368756032445e-05,
      "loss": 12.4468,
      "step": 40
    },
    {
      "epoch": 0.004502031404414187,
      "grad_norm": 0.1850309669971466,
      "learning_rate": 9.357421218136386e-05,
      "loss": 12.4537,
      "step": 41
    },
    {
      "epoch": 0.004611837048424289,
      "grad_norm": 0.1741914004087448,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4632,
      "step": 42
    },
    {
      "epoch": 0.004721642692434391,
      "grad_norm": 0.23635537922382355,
      "learning_rate": 9.273963562927695e-05,
      "loss": 12.4505,
      "step": 43
    },
    {
      "epoch": 0.004831448336444493,
      "grad_norm": 0.1862466037273407,
      "learning_rate": 9.230476262104677e-05,
      "loss": 12.4435,
      "step": 44
    },
    {
      "epoch": 0.004941253980454596,
      "grad_norm": 0.3158741295337677,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.4488,
      "step": 45
    },
    {
      "epoch": 0.005051059624464697,
      "grad_norm": 0.2830805778503418,
      "learning_rate": 9.140044155740101e-05,
      "loss": 12.4452,
      "step": 46
    },
    {
      "epoch": 0.005160865268474799,
      "grad_norm": 0.31400245428085327,
      "learning_rate": 9.093124073433463e-05,
      "loss": 12.4199,
      "step": 47
    },
    {
      "epoch": 0.005270670912484902,
      "grad_norm": 0.40273311734199524,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4289,
      "step": 48
    },
    {
      "epoch": 0.005380476556495004,
      "grad_norm": 0.48538336157798767,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.3998,
      "step": 49
    },
    {
      "epoch": 0.0054902822005051055,
      "grad_norm": 0.0,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0054902822005051055,
      "eval_loss": NaN,
      "eval_runtime": 105.2599,
      "eval_samples_per_second": 145.715,
      "eval_steps_per_second": 36.434,
      "step": 50
    },
    {
      "epoch": 0.005600087844515208,
      "grad_norm": 0.010938960127532482,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.4581,
      "step": 51
    },
    {
      "epoch": 0.00570989348852531,
      "grad_norm": 0.014923685230314732,
      "learning_rate": 8.842005554284296e-05,
      "loss": 12.4501,
      "step": 52
    },
    {
      "epoch": 0.0058196991325354126,
      "grad_norm": 0.01725936494767666,
      "learning_rate": 8.788574348801675e-05,
      "loss": 12.4562,
      "step": 53
    },
    {
      "epoch": 0.005929504776545514,
      "grad_norm": 0.019850585609674454,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.4529,
      "step": 54
    },
    {
      "epoch": 0.006039310420555616,
      "grad_norm": 0.020352356135845184,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.4549,
      "step": 55
    },
    {
      "epoch": 0.006149116064565719,
      "grad_norm": 0.023946423083543777,
      "learning_rate": 8.622126023955446e-05,
      "loss": 12.4548,
      "step": 56
    },
    {
      "epoch": 0.006258921708575821,
      "grad_norm": 0.020938068628311157,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.452,
      "step": 57
    },
    {
      "epoch": 0.0063687273525859225,
      "grad_norm": 0.023144040256738663,
      "learning_rate": 8.506183921362443e-05,
      "loss": 12.4524,
      "step": 58
    },
    {
      "epoch": 0.006478532996596025,
      "grad_norm": 0.021375242620706558,
      "learning_rate": 8.44676704559283e-05,
      "loss": 12.4549,
      "step": 59
    },
    {
      "epoch": 0.006588338640606127,
      "grad_norm": 0.025442024692893028,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.4489,
      "step": 60
    },
    {
      "epoch": 0.0066981442846162295,
      "grad_norm": 0.02413768693804741,
      "learning_rate": 8.32512286056924e-05,
      "loss": 12.4501,
      "step": 61
    },
    {
      "epoch": 0.006807949928626331,
      "grad_norm": 0.02187233977019787,
      "learning_rate": 8.262928807620843e-05,
      "loss": 12.4463,
      "step": 62
    },
    {
      "epoch": 0.006917755572636433,
      "grad_norm": 0.032653287053108215,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.4471,
      "step": 63
    },
    {
      "epoch": 0.007027561216646536,
      "grad_norm": 0.03500797972083092,
      "learning_rate": 8.135881792367686e-05,
      "loss": 12.4517,
      "step": 64
    },
    {
      "epoch": 0.007137366860656638,
      "grad_norm": 0.030853718519210815,
      "learning_rate": 8.07106356344834e-05,
      "loss": 12.4476,
      "step": 65
    },
    {
      "epoch": 0.0072471725046667395,
      "grad_norm": 0.03660961240530014,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.4443,
      "step": 66
    },
    {
      "epoch": 0.007356978148676842,
      "grad_norm": 0.045098926872015,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4519,
      "step": 67
    },
    {
      "epoch": 0.007466783792686944,
      "grad_norm": 0.05310133844614029,
      "learning_rate": 7.871643313414718e-05,
      "loss": 12.4475,
      "step": 68
    },
    {
      "epoch": 0.0075765894366970465,
      "grad_norm": 0.06399852782487869,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4399,
      "step": 69
    },
    {
      "epoch": 0.007686395080707148,
      "grad_norm": 0.04524382948875427,
      "learning_rate": 7.734740790612136e-05,
      "loss": 12.4508,
      "step": 70
    },
    {
      "epoch": 0.00779620072471725,
      "grad_norm": 0.0656951367855072,
      "learning_rate": 7.66515864363997e-05,
      "loss": 12.4413,
      "step": 71
    },
    {
      "epoch": 0.007906006368727353,
      "grad_norm": 0.09559205174446106,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.4411,
      "step": 72
    },
    {
      "epoch": 0.008015812012737454,
      "grad_norm": 0.1631324142217636,
      "learning_rate": 7.52382768867422e-05,
      "loss": 12.4419,
      "step": 73
    },
    {
      "epoch": 0.008125617656747557,
      "grad_norm": 0.08460504561662674,
      "learning_rate": 7.452117519152542e-05,
      "loss": 12.4445,
      "step": 74
    },
    {
      "epoch": 0.008235423300757659,
      "grad_norm": 0.14222237467765808,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4401,
      "step": 75
    },
    {
      "epoch": 0.00834522894476776,
      "grad_norm": 0.13685190677642822,
      "learning_rate": 7.30670581489344e-05,
      "loss": 12.4354,
      "step": 76
    },
    {
      "epoch": 0.008455034588777863,
      "grad_norm": 0.1764751672744751,
      "learning_rate": 7.233044034264034e-05,
      "loss": 12.4395,
      "step": 77
    },
    {
      "epoch": 0.008564840232787965,
      "grad_norm": 0.2350654900074005,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.4403,
      "step": 78
    },
    {
      "epoch": 0.008674645876798068,
      "grad_norm": 0.21367262303829193,
      "learning_rate": 7.083909302476453e-05,
      "loss": 12.4411,
      "step": 79
    },
    {
      "epoch": 0.00878445152080817,
      "grad_norm": 0.6251615881919861,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.4137,
      "step": 80
    },
    {
      "epoch": 0.008894257164818271,
      "grad_norm": 0.17940542101860046,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.431,
      "step": 81
    },
    {
      "epoch": 0.009004062808828374,
      "grad_norm": 0.20948448777198792,
      "learning_rate": 6.855986244591104e-05,
      "loss": 12.4307,
      "step": 82
    },
    {
      "epoch": 0.009113868452838476,
      "grad_norm": 0.39900630712509155,
      "learning_rate": 6.778969234612584e-05,
      "loss": 12.4172,
      "step": 83
    },
    {
      "epoch": 0.009223674096848577,
      "grad_norm": 0.49331218004226685,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.4058,
      "step": 84
    },
    {
      "epoch": 0.00933347974085868,
      "grad_norm": 0.5143928527832031,
      "learning_rate": 6.623497346023418e-05,
      "loss": 12.4252,
      "step": 85
    },
    {
      "epoch": 0.009443285384868782,
      "grad_norm": 0.32338955998420715,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.4228,
      "step": 86
    },
    {
      "epoch": 0.009553091028878885,
      "grad_norm": 0.5905637145042419,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4069,
      "step": 87
    },
    {
      "epoch": 0.009662896672888987,
      "grad_norm": 0.6392964124679565,
      "learning_rate": 6.387014543809223e-05,
      "loss": 12.4135,
      "step": 88
    },
    {
      "epoch": 0.009772702316899088,
      "grad_norm": 0.6248819231987,
      "learning_rate": 6.307399704769099e-05,
      "loss": 12.4015,
      "step": 89
    },
    {
      "epoch": 0.009882507960909191,
      "grad_norm": 0.5917252898216248,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4128,
      "step": 90
    },
    {
      "epoch": 0.009992313604919293,
      "grad_norm": 0.8355460166931152,
      "learning_rate": 6.147119600233758e-05,
      "loss": 12.3783,
      "step": 91
    },
    {
      "epoch": 0.010102119248929394,
      "grad_norm": 0.945870041847229,
      "learning_rate": 6.066498153718735e-05,
      "loss": 12.3706,
      "step": 92
    },
    {
      "epoch": 0.010211924892939497,
      "grad_norm": 0.8929839730262756,
      "learning_rate": 5.985585137257401e-05,
      "loss": 12.3695,
      "step": 93
    },
    {
      "epoch": 0.010321730536949599,
      "grad_norm": 0.9245277047157288,
      "learning_rate": 5.90440267166055e-05,
      "loss": 12.3645,
      "step": 94
    },
    {
      "epoch": 0.010431536180959702,
      "grad_norm": 1.0025641918182373,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.3544,
      "step": 95
    },
    {
      "epoch": 0.010541341824969803,
      "grad_norm": 0.8262727856636047,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.3882,
      "step": 96
    },
    {
      "epoch": 0.010651147468979905,
      "grad_norm": 1.0223095417022705,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 12.3386,
      "step": 97
    },
    {
      "epoch": 0.010760953112990008,
      "grad_norm": 0.8433359265327454,
      "learning_rate": 5.577423184847932e-05,
      "loss": 12.3487,
      "step": 98
    },
    {
      "epoch": 0.01087075875700011,
      "grad_norm": 1.120093584060669,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.3204,
      "step": 99
    },
    {
      "epoch": 0.010980564401010211,
      "grad_norm": 0.0,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.010980564401010211,
      "eval_loss": NaN,
      "eval_runtime": 105.3319,
      "eval_samples_per_second": 145.616,
      "eval_steps_per_second": 36.409,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 387594584064.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}