{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.45662100456621,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0045662100456621,
      "grad_norm": 8.059554238570854e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0045662100456621,
      "eval_loss": 11.5,
      "eval_runtime": 1.7171,
      "eval_samples_per_second": 214.893,
      "eval_steps_per_second": 54.16,
      "step": 1
    },
    {
      "epoch": 0.0091324200913242,
      "grad_norm": 7.725170144112781e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 0.00011649386578937992,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 0.00011197748244740069,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 9.972299449145794e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 9.729398152558133e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0319634703196347,
      "grad_norm": 0.00010867356468224898,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 9.06689529074356e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 8.329401316586882e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 0.0001071416845661588,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0502283105022831,
      "grad_norm": 8.3968996477779e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.00011577801342355087,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0593607305936073,
      "grad_norm": 0.00011205614282516763,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.0639269406392694,
      "grad_norm": 0.0001299805153394118,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 0.00010637332161422819,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0730593607305936,
      "grad_norm": 0.00013713561929762363,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.0776255707762557,
      "grad_norm": 0.00013045275409240276,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 0.0001452165306545794,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0867579908675799,
      "grad_norm": 0.00015322290710173547,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.00016047945246100426,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 0.00013506690447684377,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.1004566210045662,
      "grad_norm": 0.00022384630574379116,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.1050228310502283,
      "grad_norm": 0.00014535199443344027,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.00016746729670558125,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 0.00021024489251431078,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.1187214611872146,
      "grad_norm": 0.00022625093697570264,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 0.00025768938940018415,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.1278538812785388,
      "grad_norm": 0.00023034152400214225,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.1324200913242009,
      "grad_norm": 0.0002421868994133547,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.0002471384941600263,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.1415525114155251,
      "grad_norm": 0.0002549161436036229,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.1461187214611872,
      "grad_norm": 0.00026167635223828256,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.00019860765314660966,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.1552511415525114,
      "grad_norm": 0.00023082777624949813,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 0.00025193035253323615,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.000353545299731195,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.1689497716894977,
      "grad_norm": 0.000276066770311445,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.1735159817351598,
      "grad_norm": 0.000340762228006497,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 0.00029458003700710833,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.0002935014490503818,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.1872146118721461,
      "grad_norm": 0.00022610751329921186,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.00031101962667889893,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.1963470319634703,
      "grad_norm": 0.0004010914417449385,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.2009132420091324,
      "grad_norm": 0.000310201634420082,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.000341634702635929,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.2100456621004566,
      "grad_norm": 0.0004853562859352678,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.2146118721461187,
      "grad_norm": 0.0005005667917430401,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.00038649883936159313,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.2237442922374429,
      "grad_norm": 0.0005638391012325883,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 0.00046245846897363663,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.228310502283105,
      "eval_loss": 11.5,
      "eval_runtime": 1.715,
      "eval_samples_per_second": 215.155,
      "eval_steps_per_second": 54.226,
      "step": 50
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": 0.00040655932389199734,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.2374429223744292,
      "grad_norm": 0.00042956735705956817,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.2420091324200913,
      "grad_norm": 0.0004275771207176149,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.00047701314906589687,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.2511415525114155,
      "grad_norm": 0.0004980015801265836,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.2557077625570776,
      "grad_norm": 0.000446185382315889,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": 0.0005313682486303151,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.2648401826484018,
      "grad_norm": 0.0004277624248061329,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.2694063926940639,
      "grad_norm": 0.000427818187745288,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.00042764373938553035,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.2785388127853881,
      "grad_norm": 0.0005254355492070317,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.2831050228310502,
      "grad_norm": 0.0005730969714932144,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": 0.0006673636380583048,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.2922374429223744,
      "grad_norm": 0.0005790100549347699,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.2968036529680365,
      "grad_norm": 0.0007312895613722503,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.0006767067243345082,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.3059360730593607,
      "grad_norm": 0.0004702599544543773,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.3105022831050228,
      "grad_norm": 0.0007162991678342223,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": 0.0005246931104920805,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 0.0007114880718290806,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.3242009132420091,
      "grad_norm": 0.0006357156671583652,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.0007180926040746272,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.0008215095149353147,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.3378995433789954,
      "grad_norm": 0.0006481394520960748,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.0008435904164798558,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.3470319634703196,
      "grad_norm": 0.0006904362817294896,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.3515981735159817,
      "grad_norm": 0.0008087602909654379,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.000898570055142045,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.3607305936073059,
      "grad_norm": 0.0008144844323396683,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.0010215967195108533,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": 0.0007516633486375213,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.3744292237442922,
      "grad_norm": 0.0006957156001590192,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.3789954337899543,
      "grad_norm": 0.0009946052450686693,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.0009533686097711325,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.3881278538812785,
      "grad_norm": 0.0009758371161296964,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.3926940639269406,
      "grad_norm": 0.0011669308878481388,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": 0.0011805103858932853,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.4018264840182648,
      "grad_norm": 0.0010835855500772595,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.4063926940639269,
      "grad_norm": 0.0010419510072097182,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.0007723980234004557,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.4155251141552511,
      "grad_norm": 0.0011891524773091078,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.4200913242009132,
      "grad_norm": 0.001149424584582448,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": 0.0005744436057284474,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.4292237442922374,
      "grad_norm": 0.0010896094609051943,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.4337899543378995,
      "grad_norm": 0.00104077800642699,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.0011777642648667097,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.4429223744292237,
      "grad_norm": 0.0012576085282489657,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.4474885844748858,
      "grad_norm": 0.0010945805115625262,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": 0.0012017119443044066,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.0012969861272722483,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.45662100456621,
      "eval_loss": 11.5,
      "eval_runtime": 1.7077,
      "eval_samples_per_second": 216.083,
      "eval_steps_per_second": 54.46,
      "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": 16079231385600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}