{
  "best_metric": 2.1340065002441406,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.02730561813093044,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002730561813093044,
      "grad_norm": 43.446266174316406,
      "learning_rate": 1e-05,
      "loss": 10.0397,
      "step": 1
    },
    {
      "epoch": 0.0002730561813093044,
      "eval_loss": 4.238278865814209,
      "eval_runtime": 693.1619,
      "eval_samples_per_second": 8.898,
      "eval_steps_per_second": 2.225,
      "step": 1
    },
    {
      "epoch": 0.0005461123626186088,
      "grad_norm": 44.35715866088867,
      "learning_rate": 2e-05,
      "loss": 11.7295,
      "step": 2
    },
    {
      "epoch": 0.0008191685439279131,
      "grad_norm": 49.75259017944336,
      "learning_rate": 3e-05,
      "loss": 11.851,
      "step": 3
    },
    {
      "epoch": 0.0010922247252372176,
      "grad_norm": 46.56555938720703,
      "learning_rate": 4e-05,
      "loss": 11.3896,
      "step": 4
    },
    {
      "epoch": 0.0013652809065465218,
      "grad_norm": 40.56822967529297,
      "learning_rate": 5e-05,
      "loss": 10.777,
      "step": 5
    },
    {
      "epoch": 0.0016383370878558263,
      "grad_norm": 29.243772506713867,
      "learning_rate": 6e-05,
      "loss": 8.8778,
      "step": 6
    },
    {
      "epoch": 0.0019113932691651307,
      "grad_norm": 27.35118293762207,
      "learning_rate": 7e-05,
      "loss": 8.5317,
      "step": 7
    },
    {
      "epoch": 0.0021844494504744353,
      "grad_norm": 28.01230239868164,
      "learning_rate": 8e-05,
      "loss": 8.6976,
      "step": 8
    },
    {
      "epoch": 0.0024575056317837395,
      "grad_norm": 24.44605255126953,
      "learning_rate": 9e-05,
      "loss": 9.1925,
      "step": 9
    },
    {
      "epoch": 0.0027305618130930437,
      "grad_norm": 25.969579696655273,
      "learning_rate": 0.0001,
      "loss": 8.022,
      "step": 10
    },
    {
      "epoch": 0.0030036179944023483,
      "grad_norm": 27.08025550842285,
      "learning_rate": 9.999316524962345e-05,
      "loss": 9.1533,
      "step": 11
    },
    {
      "epoch": 0.0032766741757116525,
      "grad_norm": 18.790332794189453,
      "learning_rate": 9.997266286704631e-05,
      "loss": 7.5891,
      "step": 12
    },
    {
      "epoch": 0.003549730357020957,
      "grad_norm": 23.858049392700195,
      "learning_rate": 9.993849845741524e-05,
      "loss": 9.0651,
      "step": 13
    },
    {
      "epoch": 0.0038227865383302613,
      "grad_norm": 20.80962562561035,
      "learning_rate": 9.989068136093873e-05,
      "loss": 7.7469,
      "step": 14
    },
    {
      "epoch": 0.0040958427196395655,
      "grad_norm": 21.938926696777344,
      "learning_rate": 9.98292246503335e-05,
      "loss": 8.5726,
      "step": 15
    },
    {
      "epoch": 0.004368898900948871,
      "grad_norm": 19.670955657958984,
      "learning_rate": 9.975414512725057e-05,
      "loss": 7.9194,
      "step": 16
    },
    {
      "epoch": 0.004641955082258175,
      "grad_norm": 21.373003005981445,
      "learning_rate": 9.966546331768191e-05,
      "loss": 8.5548,
      "step": 17
    },
    {
      "epoch": 0.004915011263567479,
      "grad_norm": 21.677001953125,
      "learning_rate": 9.956320346634876e-05,
      "loss": 7.7842,
      "step": 18
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 21.132835388183594,
      "learning_rate": 9.944739353007344e-05,
      "loss": 9.1783,
      "step": 19
    },
    {
      "epoch": 0.005461123626186087,
      "grad_norm": 19.698659896850586,
      "learning_rate": 9.931806517013612e-05,
      "loss": 7.6789,
      "step": 20
    },
    {
      "epoch": 0.0057341798074953924,
      "grad_norm": 26.263071060180664,
      "learning_rate": 9.917525374361912e-05,
      "loss": 8.8006,
      "step": 21
    },
    {
      "epoch": 0.006007235988804697,
      "grad_norm": 19.799365997314453,
      "learning_rate": 9.901899829374047e-05,
      "loss": 8.5378,
      "step": 22
    },
    {
      "epoch": 0.006280292170114001,
      "grad_norm": 25.806068420410156,
      "learning_rate": 9.884934153917997e-05,
      "loss": 8.5017,
      "step": 23
    },
    {
      "epoch": 0.006553348351423305,
      "grad_norm": 24.34381866455078,
      "learning_rate": 9.86663298624003e-05,
      "loss": 8.9881,
      "step": 24
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 18.999231338500977,
      "learning_rate": 9.847001329696653e-05,
      "loss": 7.9945,
      "step": 25
    },
    {
      "epoch": 0.007099460714041914,
      "grad_norm": 20.11553382873535,
      "learning_rate": 9.826044551386744e-05,
      "loss": 8.4672,
      "step": 26
    },
    {
      "epoch": 0.0073725168953512185,
      "grad_norm": 21.312238693237305,
      "learning_rate": 9.803768380684242e-05,
      "loss": 8.6953,
      "step": 27
    },
    {
      "epoch": 0.007645573076660523,
      "grad_norm": 31.490800857543945,
      "learning_rate": 9.780178907671789e-05,
      "loss": 9.7065,
      "step": 28
    },
    {
      "epoch": 0.007918629257969828,
      "grad_norm": 20.707792282104492,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.5876,
      "step": 29
    },
    {
      "epoch": 0.008191685439279131,
      "grad_norm": 19.695018768310547,
      "learning_rate": 9.729086208503174e-05,
      "loss": 8.0395,
      "step": 30
    },
    {
      "epoch": 0.008464741620588436,
      "grad_norm": 21.563302993774414,
      "learning_rate": 9.701596950580806e-05,
      "loss": 7.869,
      "step": 31
    },
    {
      "epoch": 0.008737797801897741,
      "grad_norm": 25.480226516723633,
      "learning_rate": 9.672822322997305e-05,
      "loss": 8.0559,
      "step": 32
    },
    {
      "epoch": 0.009010853983207045,
      "grad_norm": 23.27593231201172,
      "learning_rate": 9.642770192448536e-05,
      "loss": 8.9705,
      "step": 33
    },
    {
      "epoch": 0.00928391016451635,
      "grad_norm": 22.600749969482422,
      "learning_rate": 9.611448774886924e-05,
      "loss": 8.3754,
      "step": 34
    },
    {
      "epoch": 0.009556966345825653,
      "grad_norm": 24.033321380615234,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.4395,
      "step": 35
    },
    {
      "epoch": 0.009830022527134958,
      "grad_norm": 25.064741134643555,
      "learning_rate": 9.545032675245813e-05,
      "loss": 8.8034,
      "step": 36
    },
    {
      "epoch": 0.010103078708444263,
      "grad_norm": 28.80820083618164,
      "learning_rate": 9.509956150664796e-05,
      "loss": 8.2912,
      "step": 37
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 29.365997314453125,
      "learning_rate": 9.473646649103818e-05,
      "loss": 7.6412,
      "step": 38
    },
    {
      "epoch": 0.010649191071062871,
      "grad_norm": 22.005088806152344,
      "learning_rate": 9.43611409721806e-05,
      "loss": 8.3727,
      "step": 39
    },
    {
      "epoch": 0.010922247252372175,
      "grad_norm": 22.131328582763672,
      "learning_rate": 9.397368756032445e-05,
      "loss": 7.4845,
      "step": 40
    },
    {
      "epoch": 0.01119530343368148,
      "grad_norm": 26.777101516723633,
      "learning_rate": 9.357421218136386e-05,
      "loss": 8.6799,
      "step": 41
    },
    {
      "epoch": 0.011468359614990785,
      "grad_norm": 27.420764923095703,
      "learning_rate": 9.316282404787871e-05,
      "loss": 8.6992,
      "step": 42
    },
    {
      "epoch": 0.011741415796300088,
      "grad_norm": 27.803956985473633,
      "learning_rate": 9.273963562927695e-05,
      "loss": 9.0848,
      "step": 43
    },
    {
      "epoch": 0.012014471977609393,
      "grad_norm": 32.42679214477539,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.5448,
      "step": 44
    },
    {
      "epoch": 0.012287528158918698,
      "grad_norm": 28.605180740356445,
      "learning_rate": 9.185832391312644e-05,
      "loss": 8.5635,
      "step": 45
    },
    {
      "epoch": 0.012560584340228002,
      "grad_norm": 28.457530975341797,
      "learning_rate": 9.140044155740101e-05,
      "loss": 9.0221,
      "step": 46
    },
    {
      "epoch": 0.012833640521537307,
      "grad_norm": 24.8094425201416,
      "learning_rate": 9.093124073433463e-05,
      "loss": 7.0862,
      "step": 47
    },
    {
      "epoch": 0.01310669670284661,
      "grad_norm": 30.082542419433594,
      "learning_rate": 9.045084971874738e-05,
      "loss": 8.431,
      "step": 48
    },
    {
      "epoch": 0.013379752884155915,
      "grad_norm": 26.035165786743164,
      "learning_rate": 8.995939984474624e-05,
      "loss": 8.7725,
      "step": 49
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 48.76018142700195,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.7992,
      "step": 50
    },
    {
      "epoch": 0.01365280906546522,
      "eval_loss": 2.271299362182617,
      "eval_runtime": 698.4085,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 2.208,
      "step": 50
    },
    {
      "epoch": 0.013925865246774524,
      "grad_norm": 24.909616470336914,
      "learning_rate": 8.894386393810563e-05,
      "loss": 7.0786,
      "step": 51
    },
    {
      "epoch": 0.014198921428083829,
      "grad_norm": 24.512235641479492,
      "learning_rate": 8.842005554284296e-05,
      "loss": 8.499,
      "step": 52
    },
    {
      "epoch": 0.014471977609393132,
      "grad_norm": 20.238571166992188,
      "learning_rate": 8.788574348801675e-05,
      "loss": 8.7019,
      "step": 53
    },
    {
      "epoch": 0.014745033790702437,
      "grad_norm": 20.472135543823242,
      "learning_rate": 8.73410738492077e-05,
      "loss": 7.191,
      "step": 54
    },
    {
      "epoch": 0.015018089972011742,
      "grad_norm": 18.48778533935547,
      "learning_rate": 8.678619553365659e-05,
      "loss": 8.5567,
      "step": 55
    },
    {
      "epoch": 0.015291146153321045,
      "grad_norm": 17.57303810119629,
      "learning_rate": 8.622126023955446e-05,
      "loss": 8.4159,
      "step": 56
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 17.54515266418457,
      "learning_rate": 8.564642241456986e-05,
      "loss": 8.3224,
      "step": 57
    },
    {
      "epoch": 0.015837258515939655,
      "grad_norm": 18.000179290771484,
      "learning_rate": 8.506183921362443e-05,
      "loss": 9.0583,
      "step": 58
    },
    {
      "epoch": 0.01611031469724896,
      "grad_norm": 22.772430419921875,
      "learning_rate": 8.44676704559283e-05,
      "loss": 8.5008,
      "step": 59
    },
    {
      "epoch": 0.016383370878558262,
      "grad_norm": 16.104167938232422,
      "learning_rate": 8.386407858128706e-05,
      "loss": 7.918,
      "step": 60
    },
    {
      "epoch": 0.016656427059867567,
      "grad_norm": 15.550981521606445,
      "learning_rate": 8.32512286056924e-05,
      "loss": 7.9553,
      "step": 61
    },
    {
      "epoch": 0.016929483241176872,
      "grad_norm": 17.316165924072266,
      "learning_rate": 8.262928807620843e-05,
      "loss": 7.9485,
      "step": 62
    },
    {
      "epoch": 0.017202539422486177,
      "grad_norm": 17.424301147460938,
      "learning_rate": 8.199842702516583e-05,
      "loss": 7.3209,
      "step": 63
    },
    {
      "epoch": 0.017475595603795482,
      "grad_norm": 16.4025936126709,
      "learning_rate": 8.135881792367686e-05,
      "loss": 8.1016,
      "step": 64
    },
    {
      "epoch": 0.017748651785104784,
      "grad_norm": 18.199373245239258,
      "learning_rate": 8.07106356344834e-05,
      "loss": 8.2282,
      "step": 65
    },
    {
      "epoch": 0.01802170796641409,
      "grad_norm": 18.115741729736328,
      "learning_rate": 8.005405736415126e-05,
      "loss": 8.0613,
      "step": 66
    },
    {
      "epoch": 0.018294764147723394,
      "grad_norm": 18.224075317382812,
      "learning_rate": 7.938926261462366e-05,
      "loss": 8.5954,
      "step": 67
    },
    {
      "epoch": 0.0185678203290327,
      "grad_norm": 17.102075576782227,
      "learning_rate": 7.871643313414718e-05,
      "loss": 8.2442,
      "step": 68
    },
    {
      "epoch": 0.018840876510342004,
      "grad_norm": 23.462993621826172,
      "learning_rate": 7.803575286758364e-05,
      "loss": 9.5302,
      "step": 69
    },
    {
      "epoch": 0.019113932691651306,
      "grad_norm": 19.042011260986328,
      "learning_rate": 7.734740790612136e-05,
      "loss": 8.4879,
      "step": 70
    },
    {
      "epoch": 0.01938698887296061,
      "grad_norm": 16.553205490112305,
      "learning_rate": 7.66515864363997e-05,
      "loss": 6.8034,
      "step": 71
    },
    {
      "epoch": 0.019660045054269916,
      "grad_norm": 21.598339080810547,
      "learning_rate": 7.594847868906076e-05,
      "loss": 7.9676,
      "step": 72
    },
    {
      "epoch": 0.01993310123557922,
      "grad_norm": 18.137998580932617,
      "learning_rate": 7.52382768867422e-05,
      "loss": 7.6405,
      "step": 73
    },
    {
      "epoch": 0.020206157416888526,
      "grad_norm": 18.159276962280273,
      "learning_rate": 7.452117519152542e-05,
      "loss": 8.6501,
      "step": 74
    },
    {
      "epoch": 0.020479213598197828,
      "grad_norm": 15.387510299682617,
      "learning_rate": 7.379736965185368e-05,
      "loss": 7.4218,
      "step": 75
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": 23.088130950927734,
      "learning_rate": 7.30670581489344e-05,
      "loss": 8.0995,
      "step": 76
    },
    {
      "epoch": 0.021025325960816438,
      "grad_norm": 17.979206085205078,
      "learning_rate": 7.233044034264034e-05,
      "loss": 8.097,
      "step": 77
    },
    {
      "epoch": 0.021298382142125743,
      "grad_norm": 20.9732723236084,
      "learning_rate": 7.158771761692464e-05,
      "loss": 9.4713,
      "step": 78
    },
    {
      "epoch": 0.021571438323435048,
      "grad_norm": 20.32724952697754,
      "learning_rate": 7.083909302476453e-05,
      "loss": 7.8127,
      "step": 79
    },
    {
      "epoch": 0.02184449450474435,
      "grad_norm": 20.800214767456055,
      "learning_rate": 7.008477123264848e-05,
      "loss": 8.0962,
      "step": 80
    },
    {
      "epoch": 0.022117550686053655,
      "grad_norm": 19.788745880126953,
      "learning_rate": 6.932495846462261e-05,
      "loss": 9.1246,
      "step": 81
    },
    {
      "epoch": 0.02239060686736296,
      "grad_norm": 20.843629837036133,
      "learning_rate": 6.855986244591104e-05,
      "loss": 8.05,
      "step": 82
    },
    {
      "epoch": 0.022663663048672265,
      "grad_norm": 16.206398010253906,
      "learning_rate": 6.778969234612584e-05,
      "loss": 7.2646,
      "step": 83
    },
    {
      "epoch": 0.02293671922998157,
      "grad_norm": 18.066072463989258,
      "learning_rate": 6.701465872208216e-05,
      "loss": 7.4305,
      "step": 84
    },
    {
      "epoch": 0.023209775411290875,
      "grad_norm": 20.16105079650879,
      "learning_rate": 6.623497346023418e-05,
      "loss": 8.6175,
      "step": 85
    },
    {
      "epoch": 0.023482831592600176,
      "grad_norm": 23.420856475830078,
      "learning_rate": 6.545084971874738e-05,
      "loss": 8.8125,
      "step": 86
    },
    {
      "epoch": 0.02375588777390948,
      "grad_norm": 23.20645523071289,
      "learning_rate": 6.466250186922325e-05,
      "loss": 7.9372,
      "step": 87
    },
    {
      "epoch": 0.024028943955218787,
      "grad_norm": 18.95828628540039,
      "learning_rate": 6.387014543809223e-05,
      "loss": 8.2753,
      "step": 88
    },
    {
      "epoch": 0.02430200013652809,
      "grad_norm": 20.9344482421875,
      "learning_rate": 6.307399704769099e-05,
      "loss": 8.9119,
      "step": 89
    },
    {
      "epoch": 0.024575056317837397,
      "grad_norm": 22.957317352294922,
      "learning_rate": 6.227427435703997e-05,
      "loss": 8.6468,
      "step": 90
    },
    {
      "epoch": 0.024848112499146698,
      "grad_norm": 20.31450653076172,
      "learning_rate": 6.147119600233758e-05,
      "loss": 7.4481,
      "step": 91
    },
    {
      "epoch": 0.025121168680456003,
      "grad_norm": 25.291793823242188,
      "learning_rate": 6.066498153718735e-05,
      "loss": 7.6528,
      "step": 92
    },
    {
      "epoch": 0.02539422486176531,
      "grad_norm": 23.33091926574707,
      "learning_rate": 5.985585137257401e-05,
      "loss": 8.0942,
      "step": 93
    },
    {
      "epoch": 0.025667281043074613,
      "grad_norm": 26.418405532836914,
      "learning_rate": 5.90440267166055e-05,
      "loss": 7.4102,
      "step": 94
    },
    {
      "epoch": 0.02594033722438392,
      "grad_norm": 25.400789260864258,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 8.5998,
      "step": 95
    },
    {
      "epoch": 0.02621339340569322,
      "grad_norm": 32.99055480957031,
      "learning_rate": 5.74131823855921e-05,
      "loss": 7.8845,
      "step": 96
    },
    {
      "epoch": 0.026486449587002525,
      "grad_norm": 25.209062576293945,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 6.6911,
      "step": 97
    },
    {
      "epoch": 0.02675950576831183,
      "grad_norm": 26.858041763305664,
      "learning_rate": 5.577423184847932e-05,
      "loss": 7.1683,
      "step": 98
    },
    {
      "epoch": 0.027032561949621135,
      "grad_norm": 28.698999404907227,
      "learning_rate": 5.495227651252315e-05,
      "loss": 7.3205,
      "step": 99
    },
    {
      "epoch": 0.02730561813093044,
      "grad_norm": 51.56425094604492,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 11.4165,
      "step": 100
    },
    {
      "epoch": 0.02730561813093044,
      "eval_loss": 2.1340065002441406,
      "eval_runtime": 697.8133,
      "eval_samples_per_second": 8.839,
      "eval_steps_per_second": 2.21,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.430998008987648e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}