{
  "best_metric": 1.4711685180664062,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.030483158055174518,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030483158055174517,
      "grad_norm": 21.98695945739746,
      "learning_rate": 1e-05,
      "loss": 6.4084,
      "step": 1
    },
    {
      "epoch": 0.00030483158055174517,
      "eval_loss": 1.6319817304611206,
      "eval_runtime": 406.8129,
      "eval_samples_per_second": 13.581,
      "eval_steps_per_second": 3.397,
      "step": 1
    },
    {
      "epoch": 0.0006096631611034903,
      "grad_norm": 30.730119705200195,
      "learning_rate": 2e-05,
      "loss": 7.5115,
      "step": 2
    },
    {
      "epoch": 0.0009144947416552355,
      "grad_norm": 21.137592315673828,
      "learning_rate": 3e-05,
      "loss": 8.1242,
      "step": 3
    },
    {
      "epoch": 0.0012193263222069807,
      "grad_norm": 9.523544311523438,
      "learning_rate": 4e-05,
      "loss": 5.8435,
      "step": 4
    },
    {
      "epoch": 0.0015241579027587258,
      "grad_norm": 8.481056213378906,
      "learning_rate": 5e-05,
      "loss": 5.4949,
      "step": 5
    },
    {
      "epoch": 0.001828989483310471,
      "grad_norm": 8.523990631103516,
      "learning_rate": 6e-05,
      "loss": 6.9845,
      "step": 6
    },
    {
      "epoch": 0.002133821063862216,
      "grad_norm": 8.88631820678711,
      "learning_rate": 7e-05,
      "loss": 6.1626,
      "step": 7
    },
    {
      "epoch": 0.0024386526444139613,
      "grad_norm": 6.518802165985107,
      "learning_rate": 8e-05,
      "loss": 5.7615,
      "step": 8
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 9.041634559631348,
      "learning_rate": 9e-05,
      "loss": 6.5459,
      "step": 9
    },
    {
      "epoch": 0.0030483158055174516,
      "grad_norm": 6.668817520141602,
      "learning_rate": 0.0001,
      "loss": 5.616,
      "step": 10
    },
    {
      "epoch": 0.003353147386069197,
      "grad_norm": 6.139564514160156,
      "learning_rate": 9.999316524962345e-05,
      "loss": 6.3069,
      "step": 11
    },
    {
      "epoch": 0.003657978966620942,
      "grad_norm": 7.532167434692383,
      "learning_rate": 9.997266286704631e-05,
      "loss": 5.9633,
      "step": 12
    },
    {
      "epoch": 0.003962810547172687,
      "grad_norm": 7.122283458709717,
      "learning_rate": 9.993849845741524e-05,
      "loss": 6.1261,
      "step": 13
    },
    {
      "epoch": 0.004267642127724432,
      "grad_norm": 5.265317440032959,
      "learning_rate": 9.989068136093873e-05,
      "loss": 5.3817,
      "step": 14
    },
    {
      "epoch": 0.004572473708276178,
      "grad_norm": 7.952268600463867,
      "learning_rate": 9.98292246503335e-05,
      "loss": 5.1071,
      "step": 15
    },
    {
      "epoch": 0.004877305288827923,
      "grad_norm": 6.769160747528076,
      "learning_rate": 9.975414512725057e-05,
      "loss": 5.6123,
      "step": 16
    },
    {
      "epoch": 0.005182136869379668,
      "grad_norm": 5.8532609939575195,
      "learning_rate": 9.966546331768191e-05,
      "loss": 6.1175,
      "step": 17
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 6.581336498260498,
      "learning_rate": 9.956320346634876e-05,
      "loss": 5.7228,
      "step": 18
    },
    {
      "epoch": 0.005791800030483158,
      "grad_norm": 5.720799922943115,
      "learning_rate": 9.944739353007344e-05,
      "loss": 5.4601,
      "step": 19
    },
    {
      "epoch": 0.006096631611034903,
      "grad_norm": 5.528389930725098,
      "learning_rate": 9.931806517013612e-05,
      "loss": 5.5383,
      "step": 20
    },
    {
      "epoch": 0.006401463191586648,
      "grad_norm": 5.521410942077637,
      "learning_rate": 9.917525374361912e-05,
      "loss": 6.0581,
      "step": 21
    },
    {
      "epoch": 0.006706294772138394,
      "grad_norm": 6.04514741897583,
      "learning_rate": 9.901899829374047e-05,
      "loss": 6.1071,
      "step": 22
    },
    {
      "epoch": 0.007011126352690139,
      "grad_norm": 6.623475074768066,
      "learning_rate": 9.884934153917997e-05,
      "loss": 4.7752,
      "step": 23
    },
    {
      "epoch": 0.007315957933241884,
      "grad_norm": 6.270343780517578,
      "learning_rate": 9.86663298624003e-05,
      "loss": 5.4616,
      "step": 24
    },
    {
      "epoch": 0.007620789513793629,
      "grad_norm": 5.578817367553711,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.7652,
      "step": 25
    },
    {
      "epoch": 0.007925621094345374,
      "grad_norm": 5.500857353210449,
      "learning_rate": 9.826044551386744e-05,
      "loss": 5.847,
      "step": 26
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 5.762143135070801,
      "learning_rate": 9.803768380684242e-05,
      "loss": 5.1161,
      "step": 27
    },
    {
      "epoch": 0.008535284255448864,
      "grad_norm": 5.709066390991211,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.4723,
      "step": 28
    },
    {
      "epoch": 0.00884011583600061,
      "grad_norm": 6.137989044189453,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.713,
      "step": 29
    },
    {
      "epoch": 0.009144947416552356,
      "grad_norm": 5.169020175933838,
      "learning_rate": 9.729086208503174e-05,
      "loss": 5.5467,
      "step": 30
    },
    {
      "epoch": 0.0094497789971041,
      "grad_norm": 5.7181572914123535,
      "learning_rate": 9.701596950580806e-05,
      "loss": 5.6103,
      "step": 31
    },
    {
      "epoch": 0.009754610577655845,
      "grad_norm": 6.780881404876709,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.9878,
      "step": 32
    },
    {
      "epoch": 0.010059442158207591,
      "grad_norm": 6.543086528778076,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.4962,
      "step": 33
    },
    {
      "epoch": 0.010364273738759335,
      "grad_norm": 5.252728462219238,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.7776,
      "step": 34
    },
    {
      "epoch": 0.010669105319311081,
      "grad_norm": 6.615414619445801,
      "learning_rate": 9.578866633275288e-05,
      "loss": 5.0635,
      "step": 35
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 6.838690280914307,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.4688,
      "step": 36
    },
    {
      "epoch": 0.01127876848041457,
      "grad_norm": 5.915197849273682,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.9103,
      "step": 37
    },
    {
      "epoch": 0.011583600060966317,
      "grad_norm": 6.228452682495117,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.1491,
      "step": 38
    },
    {
      "epoch": 0.01188843164151806,
      "grad_norm": 5.874170303344727,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.726,
      "step": 39
    },
    {
      "epoch": 0.012193263222069806,
      "grad_norm": 8.163307189941406,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.914,
      "step": 40
    },
    {
      "epoch": 0.012498094802621552,
      "grad_norm": 6.320303916931152,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.8544,
      "step": 41
    },
    {
      "epoch": 0.012802926383173296,
      "grad_norm": 6.844880104064941,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.4912,
      "step": 42
    },
    {
      "epoch": 0.013107757963725042,
      "grad_norm": 6.402690410614014,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.5663,
      "step": 43
    },
    {
      "epoch": 0.013412589544276788,
      "grad_norm": 7.34266471862793,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.7022,
      "step": 44
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 7.211582660675049,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.6953,
      "step": 45
    },
    {
      "epoch": 0.014022252705380277,
      "grad_norm": 7.074850082397461,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.3511,
      "step": 46
    },
    {
      "epoch": 0.014327084285932023,
      "grad_norm": 8.328790664672852,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.6233,
      "step": 47
    },
    {
      "epoch": 0.014631915866483767,
      "grad_norm": 7.469939708709717,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.0542,
      "step": 48
    },
    {
      "epoch": 0.014936747447035513,
      "grad_norm": 9.632752418518066,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.0364,
      "step": 49
    },
    {
      "epoch": 0.015241579027587259,
      "grad_norm": 13.907831192016602,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.9153,
      "step": 50
    },
    {
      "epoch": 0.015241579027587259,
      "eval_loss": 1.7195719480514526,
      "eval_runtime": 409.849,
      "eval_samples_per_second": 13.481,
      "eval_steps_per_second": 3.372,
      "step": 50
    },
    {
      "epoch": 0.015546410608139003,
      "grad_norm": 61.46236801147461,
      "learning_rate": 8.894386393810563e-05,
      "loss": 6.5024,
      "step": 51
    },
    {
      "epoch": 0.01585124218869075,
      "grad_norm": 18.183862686157227,
      "learning_rate": 8.842005554284296e-05,
      "loss": 7.4495,
      "step": 52
    },
    {
      "epoch": 0.016156073769242493,
      "grad_norm": 9.397269248962402,
      "learning_rate": 8.788574348801675e-05,
      "loss": 6.7986,
      "step": 53
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 6.099393367767334,
      "learning_rate": 8.73410738492077e-05,
      "loss": 6.4461,
      "step": 54
    },
    {
      "epoch": 0.016765736930345984,
      "grad_norm": 6.682137489318848,
      "learning_rate": 8.678619553365659e-05,
      "loss": 7.5984,
      "step": 55
    },
    {
      "epoch": 0.017070568510897728,
      "grad_norm": 6.377115726470947,
      "learning_rate": 8.622126023955446e-05,
      "loss": 6.2782,
      "step": 56
    },
    {
      "epoch": 0.017375400091449476,
      "grad_norm": 5.823065757751465,
      "learning_rate": 8.564642241456986e-05,
      "loss": 6.1547,
      "step": 57
    },
    {
      "epoch": 0.01768023167200122,
      "grad_norm": 8.691300392150879,
      "learning_rate": 8.506183921362443e-05,
      "loss": 6.4599,
      "step": 58
    },
    {
      "epoch": 0.017985063252552964,
      "grad_norm": 9.507842063903809,
      "learning_rate": 8.44676704559283e-05,
      "loss": 5.7283,
      "step": 59
    },
    {
      "epoch": 0.01828989483310471,
      "grad_norm": 5.431769371032715,
      "learning_rate": 8.386407858128706e-05,
      "loss": 5.9659,
      "step": 60
    },
    {
      "epoch": 0.018594726413656455,
      "grad_norm": 6.959444046020508,
      "learning_rate": 8.32512286056924e-05,
      "loss": 6.4109,
      "step": 61
    },
    {
      "epoch": 0.0188995579942082,
      "grad_norm": 6.050416469573975,
      "learning_rate": 8.262928807620843e-05,
      "loss": 6.0308,
      "step": 62
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 4.650235176086426,
      "learning_rate": 8.199842702516583e-05,
      "loss": 6.0326,
      "step": 63
    },
    {
      "epoch": 0.01950922115531169,
      "grad_norm": 4.57441520690918,
      "learning_rate": 8.135881792367686e-05,
      "loss": 5.9429,
      "step": 64
    },
    {
      "epoch": 0.019814052735863435,
      "grad_norm": 6.164806365966797,
      "learning_rate": 8.07106356344834e-05,
      "loss": 6.2539,
      "step": 65
    },
    {
      "epoch": 0.020118884316415182,
      "grad_norm": 4.8528666496276855,
      "learning_rate": 8.005405736415126e-05,
      "loss": 6.0395,
      "step": 66
    },
    {
      "epoch": 0.020423715896966926,
      "grad_norm": 4.227317810058594,
      "learning_rate": 7.938926261462366e-05,
      "loss": 5.2637,
      "step": 67
    },
    {
      "epoch": 0.02072854747751867,
      "grad_norm": 5.101165294647217,
      "learning_rate": 7.871643313414718e-05,
      "loss": 6.3507,
      "step": 68
    },
    {
      "epoch": 0.021033379058070414,
      "grad_norm": 5.496352672576904,
      "learning_rate": 7.803575286758364e-05,
      "loss": 5.3826,
      "step": 69
    },
    {
      "epoch": 0.021338210638622162,
      "grad_norm": 4.831961154937744,
      "learning_rate": 7.734740790612136e-05,
      "loss": 6.2885,
      "step": 70
    },
    {
      "epoch": 0.021643042219173906,
      "grad_norm": 6.279645919799805,
      "learning_rate": 7.66515864363997e-05,
      "loss": 6.4799,
      "step": 71
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 5.281492710113525,
      "learning_rate": 7.594847868906076e-05,
      "loss": 6.5732,
      "step": 72
    },
    {
      "epoch": 0.022252705380277397,
      "grad_norm": 4.832489967346191,
      "learning_rate": 7.52382768867422e-05,
      "loss": 6.281,
      "step": 73
    },
    {
      "epoch": 0.02255753696082914,
      "grad_norm": 5.089521408081055,
      "learning_rate": 7.452117519152542e-05,
      "loss": 5.4511,
      "step": 74
    },
    {
      "epoch": 0.022862368541380886,
      "grad_norm": 5.891453742980957,
      "learning_rate": 7.379736965185368e-05,
      "loss": 5.7084,
      "step": 75
    },
    {
      "epoch": 0.023167200121932633,
      "grad_norm": 4.8378987312316895,
      "learning_rate": 7.30670581489344e-05,
      "loss": 5.7123,
      "step": 76
    },
    {
      "epoch": 0.023472031702484377,
      "grad_norm": 4.414726734161377,
      "learning_rate": 7.233044034264034e-05,
      "loss": 5.1287,
      "step": 77
    },
    {
      "epoch": 0.02377686328303612,
      "grad_norm": 5.182641983032227,
      "learning_rate": 7.158771761692464e-05,
      "loss": 5.1877,
      "step": 78
    },
    {
      "epoch": 0.02408169486358787,
      "grad_norm": 5.3193254470825195,
      "learning_rate": 7.083909302476453e-05,
      "loss": 5.1346,
      "step": 79
    },
    {
      "epoch": 0.024386526444139613,
      "grad_norm": 5.478625297546387,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.8609,
      "step": 80
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 5.197872161865234,
      "learning_rate": 6.932495846462261e-05,
      "loss": 4.3952,
      "step": 81
    },
    {
      "epoch": 0.024996189605243104,
      "grad_norm": 5.30072546005249,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.9589,
      "step": 82
    },
    {
      "epoch": 0.025301021185794848,
      "grad_norm": 4.756397247314453,
      "learning_rate": 6.778969234612584e-05,
      "loss": 4.6308,
      "step": 83
    },
    {
      "epoch": 0.025605852766346592,
      "grad_norm": 5.27342414855957,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.4653,
      "step": 84
    },
    {
      "epoch": 0.02591068434689834,
      "grad_norm": 4.555075645446777,
      "learning_rate": 6.623497346023418e-05,
      "loss": 4.3031,
      "step": 85
    },
    {
      "epoch": 0.026215515927450084,
      "grad_norm": 5.166381359100342,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.1415,
      "step": 86
    },
    {
      "epoch": 0.026520347508001828,
      "grad_norm": 5.405249118804932,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.6427,
      "step": 87
    },
    {
      "epoch": 0.026825179088553575,
      "grad_norm": 5.342925548553467,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.1941,
      "step": 88
    },
    {
      "epoch": 0.02713001066910532,
      "grad_norm": 5.754428863525391,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.8832,
      "step": 89
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 5.4184088706970215,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.6651,
      "step": 90
    },
    {
      "epoch": 0.02773967383020881,
      "grad_norm": 6.166186809539795,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.7098,
      "step": 91
    },
    {
      "epoch": 0.028044505410760555,
      "grad_norm": 5.520735263824463,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.2639,
      "step": 92
    },
    {
      "epoch": 0.0283493369913123,
      "grad_norm": 6.3266730308532715,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.5446,
      "step": 93
    },
    {
      "epoch": 0.028654168571864046,
      "grad_norm": 6.167633056640625,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.4253,
      "step": 94
    },
    {
      "epoch": 0.02895900015241579,
      "grad_norm": 6.704769134521484,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.8071,
      "step": 95
    },
    {
      "epoch": 0.029263831732967534,
      "grad_norm": 6.315314292907715,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.2286,
      "step": 96
    },
    {
      "epoch": 0.029568663313519282,
      "grad_norm": 7.417150497436523,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.2532,
      "step": 97
    },
    {
      "epoch": 0.029873494894071026,
      "grad_norm": 7.790043354034424,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.9701,
      "step": 98
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 9.374876022338867,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.3668,
      "step": 99
    },
    {
      "epoch": 0.030483158055174518,
      "grad_norm": 14.421830177307129,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.331,
      "step": 100
    },
    {
      "epoch": 0.030483158055174518,
      "eval_loss": 1.4711685180664062,
      "eval_runtime": 409.8203,
      "eval_samples_per_second": 13.482,
      "eval_steps_per_second": 3.372,
      "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": 1.434577118649385e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}