{
  "best_metric": 10.34882926940918,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.01864193503285641,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001864193503285641,
      "grad_norm": 0.029469789937138557,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 10.3815,
      "step": 1
    },
    {
      "epoch": 0.0001864193503285641,
      "eval_loss": 10.381146430969238,
      "eval_runtime": 27.3606,
      "eval_samples_per_second": 330.22,
      "eval_steps_per_second": 165.128,
      "step": 1
    },
    {
      "epoch": 0.0003728387006571282,
      "grad_norm": 0.03511423617601395,
      "learning_rate": 6.666666666666667e-06,
      "loss": 10.3815,
      "step": 2
    },
    {
      "epoch": 0.0005592580509856923,
      "grad_norm": 0.03218838572502136,
      "learning_rate": 1e-05,
      "loss": 10.3826,
      "step": 3
    },
    {
      "epoch": 0.0007456774013142564,
      "grad_norm": 0.027689678594470024,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 10.3792,
      "step": 4
    },
    {
      "epoch": 0.0009320967516428206,
      "grad_norm": 0.03155677765607834,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 10.3816,
      "step": 5
    },
    {
      "epoch": 0.0011185161019713846,
      "grad_norm": 0.03052655979990959,
      "learning_rate": 2e-05,
      "loss": 10.38,
      "step": 6
    },
    {
      "epoch": 0.0013049354522999487,
      "grad_norm": 0.0268377885222435,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 10.3798,
      "step": 7
    },
    {
      "epoch": 0.0014913548026285128,
      "grad_norm": 0.03491060808300972,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 10.3801,
      "step": 8
    },
    {
      "epoch": 0.0016777741529570768,
      "grad_norm": 0.03049907088279724,
      "learning_rate": 3e-05,
      "loss": 10.3793,
      "step": 9
    },
    {
      "epoch": 0.0018641935032856411,
      "grad_norm": 0.03284202516078949,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3808,
      "step": 10
    },
    {
      "epoch": 0.002050612853614205,
      "grad_norm": 0.03127828985452652,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 10.3818,
      "step": 11
    },
    {
      "epoch": 0.0022370322039427693,
      "grad_norm": 0.029472503811120987,
      "learning_rate": 4e-05,
      "loss": 10.3824,
      "step": 12
    },
    {
      "epoch": 0.0024234515542713333,
      "grad_norm": 0.03045397251844406,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 10.3807,
      "step": 13
    },
    {
      "epoch": 0.0026098709045998974,
      "grad_norm": 0.030138535425066948,
      "learning_rate": 4.666666666666667e-05,
      "loss": 10.3783,
      "step": 14
    },
    {
      "epoch": 0.0027962902549284615,
      "grad_norm": 0.033551353961229324,
      "learning_rate": 5e-05,
      "loss": 10.3795,
      "step": 15
    },
    {
      "epoch": 0.0029827096052570255,
      "grad_norm": 0.04115981236100197,
      "learning_rate": 5.333333333333333e-05,
      "loss": 10.3785,
      "step": 16
    },
    {
      "epoch": 0.0031691289555855896,
      "grad_norm": 0.036658305674791336,
      "learning_rate": 5.666666666666667e-05,
      "loss": 10.3802,
      "step": 17
    },
    {
      "epoch": 0.0033555483059141537,
      "grad_norm": 0.03716996684670448,
      "learning_rate": 6e-05,
      "loss": 10.3815,
      "step": 18
    },
    {
      "epoch": 0.003541967656242718,
      "grad_norm": 0.03936820104718208,
      "learning_rate": 6.333333333333333e-05,
      "loss": 10.3802,
      "step": 19
    },
    {
      "epoch": 0.0037283870065712823,
      "grad_norm": 0.03620583936572075,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.3805,
      "step": 20
    },
    {
      "epoch": 0.003914806356899846,
      "grad_norm": 0.03842416778206825,
      "learning_rate": 7e-05,
      "loss": 10.3793,
      "step": 21
    },
    {
      "epoch": 0.00410122570722841,
      "grad_norm": 0.039217282086610794,
      "learning_rate": 7.333333333333333e-05,
      "loss": 10.3797,
      "step": 22
    },
    {
      "epoch": 0.0042876450575569745,
      "grad_norm": 0.04393612593412399,
      "learning_rate": 7.666666666666667e-05,
      "loss": 10.3784,
      "step": 23
    },
    {
      "epoch": 0.0044740644078855385,
      "grad_norm": 0.03723832592368126,
      "learning_rate": 8e-05,
      "loss": 10.3764,
      "step": 24
    },
    {
      "epoch": 0.004660483758214103,
      "grad_norm": 0.05864546820521355,
      "learning_rate": 8.333333333333334e-05,
      "loss": 10.3784,
      "step": 25
    },
    {
      "epoch": 0.004846903108542667,
      "grad_norm": 0.05707390606403351,
      "learning_rate": 8.666666666666667e-05,
      "loss": 10.3796,
      "step": 26
    },
    {
      "epoch": 0.005033322458871231,
      "grad_norm": 0.05543961003422737,
      "learning_rate": 9e-05,
      "loss": 10.38,
      "step": 27
    },
    {
      "epoch": 0.005219741809199795,
      "grad_norm": 0.06495416909456253,
      "learning_rate": 9.333333333333334e-05,
      "loss": 10.3752,
      "step": 28
    },
    {
      "epoch": 0.005406161159528359,
      "grad_norm": 0.07095163315534592,
      "learning_rate": 9.666666666666667e-05,
      "loss": 10.376,
      "step": 29
    },
    {
      "epoch": 0.005592580509856923,
      "grad_norm": 0.07251051068305969,
      "learning_rate": 0.0001,
      "loss": 10.3783,
      "step": 30
    },
    {
      "epoch": 0.005778999860185487,
      "grad_norm": 0.0717591941356659,
      "learning_rate": 9.994965332706573e-05,
      "loss": 10.3761,
      "step": 31
    },
    {
      "epoch": 0.005965419210514051,
      "grad_norm": 0.08555017411708832,
      "learning_rate": 9.979871469976196e-05,
      "loss": 10.3753,
      "step": 32
    },
    {
      "epoch": 0.006151838560842615,
      "grad_norm": 0.11320396512746811,
      "learning_rate": 9.954748808839674e-05,
      "loss": 10.3745,
      "step": 33
    },
    {
      "epoch": 0.006338257911171179,
      "grad_norm": 0.09341420978307724,
      "learning_rate": 9.919647942993148e-05,
      "loss": 10.3745,
      "step": 34
    },
    {
      "epoch": 0.006524677261499743,
      "grad_norm": 0.11599099636077881,
      "learning_rate": 9.874639560909117e-05,
      "loss": 10.3704,
      "step": 35
    },
    {
      "epoch": 0.006711096611828307,
      "grad_norm": 0.10898492485284805,
      "learning_rate": 9.819814303479267e-05,
      "loss": 10.3727,
      "step": 36
    },
    {
      "epoch": 0.006897515962156872,
      "grad_norm": 0.14422820508480072,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3704,
      "step": 37
    },
    {
      "epoch": 0.007083935312485436,
      "grad_norm": 0.14940433204174042,
      "learning_rate": 9.681174353198687e-05,
      "loss": 10.3691,
      "step": 38
    },
    {
      "epoch": 0.0072703546628140004,
      "grad_norm": 0.14902304112911224,
      "learning_rate": 9.597638862757255e-05,
      "loss": 10.3665,
      "step": 39
    },
    {
      "epoch": 0.0074567740131425645,
      "grad_norm": 0.16568797826766968,
      "learning_rate": 9.504844339512095e-05,
      "loss": 10.3681,
      "step": 40
    },
    {
      "epoch": 0.007643193363471129,
      "grad_norm": 0.17017991840839386,
      "learning_rate": 9.40297765928369e-05,
      "loss": 10.3653,
      "step": 41
    },
    {
      "epoch": 0.007829612713799693,
      "grad_norm": 0.18572087585926056,
      "learning_rate": 9.292243968009331e-05,
      "loss": 10.3632,
      "step": 42
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 0.22373846173286438,
      "learning_rate": 9.172866268606513e-05,
      "loss": 10.3638,
      "step": 43
    },
    {
      "epoch": 0.00820245141445682,
      "grad_norm": 0.19732271134853363,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3615,
      "step": 44
    },
    {
      "epoch": 0.008388870764785384,
      "grad_norm": 0.19585733115673065,
      "learning_rate": 8.90915741234015e-05,
      "loss": 10.3552,
      "step": 45
    },
    {
      "epoch": 0.008575290115113949,
      "grad_norm": 0.20070262253284454,
      "learning_rate": 8.765357330018056e-05,
      "loss": 10.361,
      "step": 46
    },
    {
      "epoch": 0.008761709465442512,
      "grad_norm": 0.18280582129955292,
      "learning_rate": 8.613974319136958e-05,
      "loss": 10.358,
      "step": 47
    },
    {
      "epoch": 0.008948128815771077,
      "grad_norm": 0.19768880307674408,
      "learning_rate": 8.455313244934324e-05,
      "loss": 10.3532,
      "step": 48
    },
    {
      "epoch": 0.009134548166099642,
      "grad_norm": 0.1908486932516098,
      "learning_rate": 8.289693629698564e-05,
      "loss": 10.3526,
      "step": 49
    },
    {
      "epoch": 0.009320967516428205,
      "grad_norm": 0.24415874481201172,
      "learning_rate": 8.117449009293668e-05,
      "loss": 10.3496,
      "step": 50
    },
    {
      "epoch": 0.009320967516428205,
      "eval_loss": 10.3571138381958,
      "eval_runtime": 27.4265,
      "eval_samples_per_second": 329.426,
      "eval_steps_per_second": 164.731,
      "step": 50
    },
    {
      "epoch": 0.00950738686675677,
      "grad_norm": 0.1561504453420639,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3609,
      "step": 51
    },
    {
      "epoch": 0.009693806217085333,
      "grad_norm": 0.14776375889778137,
      "learning_rate": 7.754484907260513e-05,
      "loss": 10.3593,
      "step": 52
    },
    {
      "epoch": 0.009880225567413898,
      "grad_norm": 0.14880362153053284,
      "learning_rate": 7.564496387029532e-05,
      "loss": 10.3593,
      "step": 53
    },
    {
      "epoch": 0.010066644917742461,
      "grad_norm": 0.12313321232795715,
      "learning_rate": 7.369343312364993e-05,
      "loss": 10.3598,
      "step": 54
    },
    {
      "epoch": 0.010253064268071026,
      "grad_norm": 0.14246243238449097,
      "learning_rate": 7.169418695587791e-05,
      "loss": 10.3582,
      "step": 55
    },
    {
      "epoch": 0.01043948361839959,
      "grad_norm": 0.13358600437641144,
      "learning_rate": 6.965125158269619e-05,
      "loss": 10.3575,
      "step": 56
    },
    {
      "epoch": 0.010625902968728155,
      "grad_norm": 0.10732542723417282,
      "learning_rate": 6.756874120406714e-05,
      "loss": 10.3576,
      "step": 57
    },
    {
      "epoch": 0.010812322319056718,
      "grad_norm": 0.10971201956272125,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3567,
      "step": 58
    },
    {
      "epoch": 0.010998741669385283,
      "grad_norm": 0.09025903791189194,
      "learning_rate": 6.330184227833376e-05,
      "loss": 10.3538,
      "step": 59
    },
    {
      "epoch": 0.011185161019713846,
      "grad_norm": 0.10398943722248077,
      "learning_rate": 6.112604669781572e-05,
      "loss": 10.3545,
      "step": 60
    },
    {
      "epoch": 0.01137158037004241,
      "grad_norm": 0.10011833906173706,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 10.3557,
      "step": 61
    },
    {
      "epoch": 0.011557999720370974,
      "grad_norm": 0.10548334568738937,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 10.3532,
      "step": 62
    },
    {
      "epoch": 0.011744419070699539,
      "grad_norm": 0.08827032148838043,
      "learning_rate": 5.448196544517168e-05,
      "loss": 10.3518,
      "step": 63
    },
    {
      "epoch": 0.011930838421028102,
      "grad_norm": 0.05861261487007141,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 10.353,
      "step": 64
    },
    {
      "epoch": 0.012117257771356667,
      "grad_norm": 0.08971337974071503,
      "learning_rate": 5e-05,
      "loss": 10.355,
      "step": 65
    },
    {
      "epoch": 0.01230367712168523,
      "grad_norm": 0.08864837139844894,
      "learning_rate": 4.775675848247427e-05,
      "loss": 10.3548,
      "step": 66
    },
    {
      "epoch": 0.012490096472013795,
      "grad_norm": 0.08446395397186279,
      "learning_rate": 4.551803455482833e-05,
      "loss": 10.3526,
      "step": 67
    },
    {
      "epoch": 0.012676515822342358,
      "grad_norm": 0.06572958827018738,
      "learning_rate": 4.328833670911724e-05,
      "loss": 10.3523,
      "step": 68
    },
    {
      "epoch": 0.012862935172670923,
      "grad_norm": 0.08103340864181519,
      "learning_rate": 4.107215526006817e-05,
      "loss": 10.3508,
      "step": 69
    },
    {
      "epoch": 0.013049354522999487,
      "grad_norm": 0.06975308805704117,
      "learning_rate": 3.887395330218429e-05,
      "loss": 10.3515,
      "step": 70
    },
    {
      "epoch": 0.013235773873328052,
      "grad_norm": 0.055503133684396744,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 10.3512,
      "step": 71
    },
    {
      "epoch": 0.013422193223656615,
      "grad_norm": 0.06876011937856674,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3516,
      "step": 72
    },
    {
      "epoch": 0.01360861257398518,
      "grad_norm": 0.06682562828063965,
      "learning_rate": 3.243125879593286e-05,
      "loss": 10.3509,
      "step": 73
    },
    {
      "epoch": 0.013795031924313745,
      "grad_norm": 0.0667678713798523,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 10.3496,
      "step": 74
    },
    {
      "epoch": 0.013981451274642308,
      "grad_norm": 0.05310027301311493,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 10.3485,
      "step": 75
    },
    {
      "epoch": 0.014167870624970873,
      "grad_norm": 0.07601341605186462,
      "learning_rate": 2.630656687635007e-05,
      "loss": 10.3489,
      "step": 76
    },
    {
      "epoch": 0.014354289975299436,
      "grad_norm": 0.06028437986969948,
      "learning_rate": 2.43550361297047e-05,
      "loss": 10.3492,
      "step": 77
    },
    {
      "epoch": 0.014540709325628001,
      "grad_norm": 0.054510705173015594,
      "learning_rate": 2.245515092739488e-05,
      "loss": 10.3496,
      "step": 78
    },
    {
      "epoch": 0.014727128675956564,
      "grad_norm": 0.08019602298736572,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3497,
      "step": 79
    },
    {
      "epoch": 0.014913548026285129,
      "grad_norm": 0.0804019346833229,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 10.3537,
      "step": 80
    },
    {
      "epoch": 0.015099967376613692,
      "grad_norm": 0.07119160145521164,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 10.3479,
      "step": 81
    },
    {
      "epoch": 0.015286386726942257,
      "grad_norm": 0.0820232704281807,
      "learning_rate": 1.544686755065677e-05,
      "loss": 10.3519,
      "step": 82
    },
    {
      "epoch": 0.01547280607727082,
      "grad_norm": 0.055926691740751266,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 10.3495,
      "step": 83
    },
    {
      "epoch": 0.015659225427599385,
      "grad_norm": 0.06931938230991364,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 10.3468,
      "step": 84
    },
    {
      "epoch": 0.01584564477792795,
      "grad_norm": 0.08054453134536743,
      "learning_rate": 1.090842587659851e-05,
      "loss": 10.3472,
      "step": 85
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 0.07081463932991028,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3477,
      "step": 86
    },
    {
      "epoch": 0.016218483478585077,
      "grad_norm": 0.1176007091999054,
      "learning_rate": 8.271337313934869e-06,
      "loss": 10.3496,
      "step": 87
    },
    {
      "epoch": 0.01640490282891364,
      "grad_norm": 0.06712072342634201,
      "learning_rate": 7.077560319906695e-06,
      "loss": 10.3454,
      "step": 88
    },
    {
      "epoch": 0.016591322179242207,
      "grad_norm": 0.06814035773277283,
      "learning_rate": 5.9702234071631e-06,
      "loss": 10.3486,
      "step": 89
    },
    {
      "epoch": 0.016777741529570768,
      "grad_norm": 0.09200986474752426,
      "learning_rate": 4.951556604879048e-06,
      "loss": 10.3454,
      "step": 90
    },
    {
      "epoch": 0.016964160879899333,
      "grad_norm": 0.08182810246944427,
      "learning_rate": 4.023611372427471e-06,
      "loss": 10.3469,
      "step": 91
    },
    {
      "epoch": 0.017150580230227898,
      "grad_norm": 0.0823381245136261,
      "learning_rate": 3.18825646801314e-06,
      "loss": 10.3436,
      "step": 92
    },
    {
      "epoch": 0.017336999580556463,
      "grad_norm": 0.12770026922225952,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3455,
      "step": 93
    },
    {
      "epoch": 0.017523418930885024,
      "grad_norm": 0.09665341675281525,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 10.345,
      "step": 94
    },
    {
      "epoch": 0.01770983828121359,
      "grad_norm": 0.08394477516412735,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 10.342,
      "step": 95
    },
    {
      "epoch": 0.017896257631542154,
      "grad_norm": 0.15145687758922577,
      "learning_rate": 8.035205700685167e-07,
      "loss": 10.3465,
      "step": 96
    },
    {
      "epoch": 0.01808267698187072,
      "grad_norm": 0.11746706068515778,
      "learning_rate": 4.52511911603265e-07,
      "loss": 10.3434,
      "step": 97
    },
    {
      "epoch": 0.018269096332199284,
      "grad_norm": 0.09703138470649719,
      "learning_rate": 2.012853002380466e-07,
      "loss": 10.3448,
      "step": 98
    },
    {
      "epoch": 0.018455515682527845,
      "grad_norm": 0.15032333135604858,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 10.3436,
      "step": 99
    },
    {
      "epoch": 0.01864193503285641,
      "grad_norm": 0.18205277621746063,
      "learning_rate": 0.0,
      "loss": 10.3399,
      "step": 100
    },
    {
      "epoch": 0.01864193503285641,
      "eval_loss": 10.34882926940918,
      "eval_runtime": 27.4349,
      "eval_samples_per_second": 329.326,
      "eval_steps_per_second": 164.681,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11740707028992.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}