{
  "best_metric": 0.01937755011022091,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3872216844143272,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003872216844143272,
      "grad_norm": 0.33036765456199646,
      "learning_rate": 1e-05,
      "loss": 0.297,
      "step": 1
    },
    {
      "epoch": 0.003872216844143272,
      "eval_loss": 0.7128530144691467,
      "eval_runtime": 30.3619,
      "eval_samples_per_second": 14.327,
      "eval_steps_per_second": 3.59,
      "step": 1
    },
    {
      "epoch": 0.007744433688286544,
      "grad_norm": 0.3850049376487732,
      "learning_rate": 2e-05,
      "loss": 0.3563,
      "step": 2
    },
    {
      "epoch": 0.011616650532429816,
      "grad_norm": 0.37881961464881897,
      "learning_rate": 3e-05,
      "loss": 0.3861,
      "step": 3
    },
    {
      "epoch": 0.015488867376573089,
      "grad_norm": 0.4100344181060791,
      "learning_rate": 4e-05,
      "loss": 0.3982,
      "step": 4
    },
    {
      "epoch": 0.01936108422071636,
      "grad_norm": 0.40349701046943665,
      "learning_rate": 5e-05,
      "loss": 0.3863,
      "step": 5
    },
    {
      "epoch": 0.023233301064859633,
      "grad_norm": 0.36773568391799927,
      "learning_rate": 6e-05,
      "loss": 0.3498,
      "step": 6
    },
    {
      "epoch": 0.027105517909002903,
      "grad_norm": 0.33091726899147034,
      "learning_rate": 7e-05,
      "loss": 0.2986,
      "step": 7
    },
    {
      "epoch": 0.030977734753146177,
      "grad_norm": 0.28258058428764343,
      "learning_rate": 8e-05,
      "loss": 0.2337,
      "step": 8
    },
    {
      "epoch": 0.03484995159728945,
      "grad_norm": 0.2912766933441162,
      "learning_rate": 9e-05,
      "loss": 0.2093,
      "step": 9
    },
    {
      "epoch": 0.03872216844143272,
      "grad_norm": 0.3206344544887543,
      "learning_rate": 0.0001,
      "loss": 0.1629,
      "step": 10
    },
    {
      "epoch": 0.04259438528557599,
      "grad_norm": 0.3448626399040222,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.1203,
      "step": 11
    },
    {
      "epoch": 0.046466602129719266,
      "grad_norm": 0.26453205943107605,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0952,
      "step": 12
    },
    {
      "epoch": 0.05033881897386254,
      "grad_norm": 0.27510973811149597,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0601,
      "step": 13
    },
    {
      "epoch": 0.05421103581800581,
      "grad_norm": 0.19839665293693542,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0684,
      "step": 14
    },
    {
      "epoch": 0.05808325266214908,
      "grad_norm": 0.31500810384750366,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0835,
      "step": 15
    },
    {
      "epoch": 0.061955469506292354,
      "grad_norm": 0.1898542046546936,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0471,
      "step": 16
    },
    {
      "epoch": 0.06582768635043562,
      "grad_norm": 0.16449055075645447,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0428,
      "step": 17
    },
    {
      "epoch": 0.0696999031945789,
      "grad_norm": 0.17914803326129913,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.053,
      "step": 18
    },
    {
      "epoch": 0.07357212003872217,
      "grad_norm": 0.13265900313854218,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0347,
      "step": 19
    },
    {
      "epoch": 0.07744433688286544,
      "grad_norm": 0.20040208101272583,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.038,
      "step": 20
    },
    {
      "epoch": 0.08131655372700872,
      "grad_norm": 0.14658556878566742,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0417,
      "step": 21
    },
    {
      "epoch": 0.08518877057115198,
      "grad_norm": 0.10912320762872696,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0336,
      "step": 22
    },
    {
      "epoch": 0.08906098741529525,
      "grad_norm": 0.10982748866081238,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0278,
      "step": 23
    },
    {
      "epoch": 0.09293320425943853,
      "grad_norm": 0.08335252106189728,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0214,
      "step": 24
    },
    {
      "epoch": 0.0968054211035818,
      "grad_norm": 0.10161011666059494,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0413,
      "step": 25
    },
    {
      "epoch": 0.10067763794772508,
      "grad_norm": 0.09783328324556351,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.032,
      "step": 26
    },
    {
      "epoch": 0.10454985479186835,
      "grad_norm": 0.05879473313689232,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0151,
      "step": 27
    },
    {
      "epoch": 0.10842207163601161,
      "grad_norm": 0.10748795419931412,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0394,
      "step": 28
    },
    {
      "epoch": 0.1122942884801549,
      "grad_norm": 0.09443118423223495,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0375,
      "step": 29
    },
    {
      "epoch": 0.11616650532429816,
      "grad_norm": 0.08883603662252426,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0325,
      "step": 30
    },
    {
      "epoch": 0.12003872216844143,
      "grad_norm": 0.06886650621891022,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0313,
      "step": 31
    },
    {
      "epoch": 0.12391093901258471,
      "grad_norm": 0.07295922935009003,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0276,
      "step": 32
    },
    {
      "epoch": 0.12778315585672798,
      "grad_norm": 0.06310761719942093,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0234,
      "step": 33
    },
    {
      "epoch": 0.13165537270087124,
      "grad_norm": 0.09747755527496338,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0267,
      "step": 34
    },
    {
      "epoch": 0.1355275895450145,
      "grad_norm": 0.04697493463754654,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.021,
      "step": 35
    },
    {
      "epoch": 0.1393998063891578,
      "grad_norm": 0.07634945958852768,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0263,
      "step": 36
    },
    {
      "epoch": 0.14327202323330107,
      "grad_norm": 0.048437684774398804,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0199,
      "step": 37
    },
    {
      "epoch": 0.14714424007744434,
      "grad_norm": 0.0893416479229927,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0219,
      "step": 38
    },
    {
      "epoch": 0.1510164569215876,
      "grad_norm": 0.08695591241121292,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0314,
      "step": 39
    },
    {
      "epoch": 0.15488867376573087,
      "grad_norm": 0.0652228444814682,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0223,
      "step": 40
    },
    {
      "epoch": 0.15876089060987417,
      "grad_norm": 0.08439888060092926,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0282,
      "step": 41
    },
    {
      "epoch": 0.16263310745401743,
      "grad_norm": 0.05719901621341705,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0226,
      "step": 42
    },
    {
      "epoch": 0.1665053242981607,
      "grad_norm": 0.05270665884017944,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0232,
      "step": 43
    },
    {
      "epoch": 0.17037754114230397,
      "grad_norm": 0.08705751597881317,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.022,
      "step": 44
    },
    {
      "epoch": 0.17424975798644723,
      "grad_norm": 0.0793544352054596,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0251,
      "step": 45
    },
    {
      "epoch": 0.1781219748305905,
      "grad_norm": 0.10614676028490067,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0284,
      "step": 46
    },
    {
      "epoch": 0.1819941916747338,
      "grad_norm": 0.05218925327062607,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.019,
      "step": 47
    },
    {
      "epoch": 0.18586640851887706,
      "grad_norm": 0.06523724645376205,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.025,
      "step": 48
    },
    {
      "epoch": 0.18973862536302033,
      "grad_norm": 0.05020613223314285,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0168,
      "step": 49
    },
    {
      "epoch": 0.1936108422071636,
      "grad_norm": 0.19285856187343597,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0267,
      "step": 50
    },
    {
      "epoch": 0.1936108422071636,
      "eval_loss": 0.022433165460824966,
      "eval_runtime": 31.0156,
      "eval_samples_per_second": 14.025,
      "eval_steps_per_second": 3.514,
      "step": 50
    },
    {
      "epoch": 0.19748305905130686,
      "grad_norm": 0.05130339413881302,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0219,
      "step": 51
    },
    {
      "epoch": 0.20135527589545016,
      "grad_norm": 0.054578520357608795,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0223,
      "step": 52
    },
    {
      "epoch": 0.20522749273959343,
      "grad_norm": 0.06454931199550629,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.027,
      "step": 53
    },
    {
      "epoch": 0.2090997095837367,
      "grad_norm": 0.06821908801794052,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0162,
      "step": 54
    },
    {
      "epoch": 0.21297192642787996,
      "grad_norm": 0.044611573219299316,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.018,
      "step": 55
    },
    {
      "epoch": 0.21684414327202323,
      "grad_norm": 0.03761984035372734,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0202,
      "step": 56
    },
    {
      "epoch": 0.2207163601161665,
      "grad_norm": 0.0433681458234787,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0154,
      "step": 57
    },
    {
      "epoch": 0.2245885769603098,
      "grad_norm": 0.05336097627878189,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0234,
      "step": 58
    },
    {
      "epoch": 0.22846079380445306,
      "grad_norm": 0.04495273903012276,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0158,
      "step": 59
    },
    {
      "epoch": 0.23233301064859632,
      "grad_norm": 0.05013081058859825,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0212,
      "step": 60
    },
    {
      "epoch": 0.2362052274927396,
      "grad_norm": 0.0574067123234272,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0284,
      "step": 61
    },
    {
      "epoch": 0.24007744433688286,
      "grad_norm": 0.03662450611591339,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0222,
      "step": 62
    },
    {
      "epoch": 0.24394966118102615,
      "grad_norm": 0.04296913370490074,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0177,
      "step": 63
    },
    {
      "epoch": 0.24782187802516942,
      "grad_norm": 0.06435459107160568,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0235,
      "step": 64
    },
    {
      "epoch": 0.25169409486931266,
      "grad_norm": 0.04163075610995293,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0226,
      "step": 65
    },
    {
      "epoch": 0.25556631171345595,
      "grad_norm": 0.03861234709620476,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0233,
      "step": 66
    },
    {
      "epoch": 0.25943852855759925,
      "grad_norm": 0.039693742990493774,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0186,
      "step": 67
    },
    {
      "epoch": 0.2633107454017425,
      "grad_norm": 0.035804882645606995,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0154,
      "step": 68
    },
    {
      "epoch": 0.2671829622458858,
      "grad_norm": 0.025846365839242935,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0144,
      "step": 69
    },
    {
      "epoch": 0.271055179090029,
      "grad_norm": 0.05968935042619705,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0217,
      "step": 70
    },
    {
      "epoch": 0.2749273959341723,
      "grad_norm": 0.06286381930112839,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0209,
      "step": 71
    },
    {
      "epoch": 0.2787996127783156,
      "grad_norm": 0.028835639357566833,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0115,
      "step": 72
    },
    {
      "epoch": 0.28267182962245885,
      "grad_norm": 0.04784088954329491,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0229,
      "step": 73
    },
    {
      "epoch": 0.28654404646660214,
      "grad_norm": 0.05574282631278038,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0256,
      "step": 74
    },
    {
      "epoch": 0.2904162633107454,
      "grad_norm": 0.04102447256445885,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0174,
      "step": 75
    },
    {
      "epoch": 0.2942884801548887,
      "grad_norm": 0.0936175063252449,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.024,
      "step": 76
    },
    {
      "epoch": 0.29816069699903197,
      "grad_norm": 0.033699460327625275,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0156,
      "step": 77
    },
    {
      "epoch": 0.3020329138431752,
      "grad_norm": 0.06190520524978638,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0245,
      "step": 78
    },
    {
      "epoch": 0.3059051306873185,
      "grad_norm": 0.048285167664289474,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0219,
      "step": 79
    },
    {
      "epoch": 0.30977734753146174,
      "grad_norm": 0.042587533593177795,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0166,
      "step": 80
    },
    {
      "epoch": 0.31364956437560504,
      "grad_norm": 0.07332392781972885,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.024,
      "step": 81
    },
    {
      "epoch": 0.31752178121974833,
      "grad_norm": 0.12151223421096802,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0241,
      "step": 82
    },
    {
      "epoch": 0.3213939980638916,
      "grad_norm": 0.2832794487476349,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0219,
      "step": 83
    },
    {
      "epoch": 0.32526621490803487,
      "grad_norm": 0.06909225136041641,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0254,
      "step": 84
    },
    {
      "epoch": 0.3291384317521781,
      "grad_norm": 0.3256091773509979,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0196,
      "step": 85
    },
    {
      "epoch": 0.3330106485963214,
      "grad_norm": 0.05504089593887329,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0228,
      "step": 86
    },
    {
      "epoch": 0.33688286544046464,
      "grad_norm": 0.04585348442196846,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0182,
      "step": 87
    },
    {
      "epoch": 0.34075508228460794,
      "grad_norm": 0.06665895134210587,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0198,
      "step": 88
    },
    {
      "epoch": 0.34462729912875123,
      "grad_norm": 0.047711923718452454,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0206,
      "step": 89
    },
    {
      "epoch": 0.34849951597289447,
      "grad_norm": 0.040118634700775146,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.017,
      "step": 90
    },
    {
      "epoch": 0.35237173281703776,
      "grad_norm": 0.0628420040011406,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0233,
      "step": 91
    },
    {
      "epoch": 0.356243949661181,
      "grad_norm": 0.05141530930995941,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0246,
      "step": 92
    },
    {
      "epoch": 0.3601161665053243,
      "grad_norm": 0.08067324012517929,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0215,
      "step": 93
    },
    {
      "epoch": 0.3639883833494676,
      "grad_norm": 0.0874338448047638,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.021,
      "step": 94
    },
    {
      "epoch": 0.36786060019361083,
      "grad_norm": 0.05889058858156204,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0233,
      "step": 95
    },
    {
      "epoch": 0.3717328170377541,
      "grad_norm": 0.140172079205513,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0247,
      "step": 96
    },
    {
      "epoch": 0.37560503388189737,
      "grad_norm": 0.05803554505109787,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.014,
      "step": 97
    },
    {
      "epoch": 0.37947725072604066,
      "grad_norm": 0.05956672504544258,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0139,
      "step": 98
    },
    {
      "epoch": 0.38334946757018395,
      "grad_norm": 0.09673935920000076,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0224,
      "step": 99
    },
    {
      "epoch": 0.3872216844143272,
      "grad_norm": 0.12850569188594818,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0284,
      "step": 100
    },
    {
      "epoch": 0.3872216844143272,
      "eval_loss": 0.01937755011022091,
      "eval_runtime": 31.0085,
      "eval_samples_per_second": 14.028,
      "eval_steps_per_second": 3.515,
      "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": 1.330508659163136e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}