{
  "best_metric": 10.372817039489746,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.02929222657537256,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002929222657537256,
      "grad_norm": 0.025340523570775986,
      "learning_rate": 5.000000000000001e-07,
      "loss": 10.3728,
      "step": 1
    },
    {
      "epoch": 0.0002929222657537256,
      "eval_loss": 10.373064994812012,
      "eval_runtime": 14.2255,
      "eval_samples_per_second": 404.203,
      "eval_steps_per_second": 101.086,
      "step": 1
    },
    {
      "epoch": 0.0005858445315074512,
      "grad_norm": 0.02154785953462124,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 10.3758,
      "step": 2
    },
    {
      "epoch": 0.0008787667972611768,
      "grad_norm": 0.02488698996603489,
      "learning_rate": 1.5e-06,
      "loss": 10.3737,
      "step": 3
    },
    {
      "epoch": 0.0011716890630149024,
      "grad_norm": 0.02246084250509739,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 10.3739,
      "step": 4
    },
    {
      "epoch": 0.001464611328768628,
      "grad_norm": 0.024568594992160797,
      "learning_rate": 2.5e-06,
      "loss": 10.3741,
      "step": 5
    },
    {
      "epoch": 0.0017575335945223536,
      "grad_norm": 0.02053692936897278,
      "learning_rate": 3e-06,
      "loss": 10.3734,
      "step": 6
    },
    {
      "epoch": 0.002050455860276079,
      "grad_norm": 0.02354443445801735,
      "learning_rate": 3.5e-06,
      "loss": 10.3743,
      "step": 7
    },
    {
      "epoch": 0.0023433781260298048,
      "grad_norm": 0.02450806088745594,
      "learning_rate": 4.000000000000001e-06,
      "loss": 10.3753,
      "step": 8
    },
    {
      "epoch": 0.0026363003917835304,
      "grad_norm": 0.024845441803336143,
      "learning_rate": 4.5e-06,
      "loss": 10.3759,
      "step": 9
    },
    {
      "epoch": 0.002929222657537256,
      "grad_norm": 0.0253719724714756,
      "learning_rate": 5e-06,
      "loss": 10.3731,
      "step": 10
    },
    {
      "epoch": 0.0032221449232909816,
      "grad_norm": 0.02256913110613823,
      "learning_rate": 4.99847706754774e-06,
      "loss": 10.3737,
      "step": 11
    },
    {
      "epoch": 0.003515067189044707,
      "grad_norm": 0.0258257444947958,
      "learning_rate": 4.993910125649561e-06,
      "loss": 10.3741,
      "step": 12
    },
    {
      "epoch": 0.0038079894547984328,
      "grad_norm": 0.03032153844833374,
      "learning_rate": 4.986304738420684e-06,
      "loss": 10.3725,
      "step": 13
    },
    {
      "epoch": 0.004100911720552158,
      "grad_norm": 0.026030762121081352,
      "learning_rate": 4.975670171853926e-06,
      "loss": 10.3745,
      "step": 14
    },
    {
      "epoch": 0.004393833986305884,
      "grad_norm": 0.02117944322526455,
      "learning_rate": 4.962019382530521e-06,
      "loss": 10.3723,
      "step": 15
    },
    {
      "epoch": 0.0046867562520596096,
      "grad_norm": 0.029438018798828125,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 10.3753,
      "step": 16
    },
    {
      "epoch": 0.004979678517813335,
      "grad_norm": 0.026865482330322266,
      "learning_rate": 4.925739315689991e-06,
      "loss": 10.376,
      "step": 17
    },
    {
      "epoch": 0.005272600783567061,
      "grad_norm": 0.026240473613142967,
      "learning_rate": 4.903154239845798e-06,
      "loss": 10.3722,
      "step": 18
    },
    {
      "epoch": 0.005565523049320786,
      "grad_norm": 0.02773893065750599,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 10.3746,
      "step": 19
    },
    {
      "epoch": 0.005858445315074512,
      "grad_norm": 0.024244513362646103,
      "learning_rate": 4.849231551964771e-06,
      "loss": 10.3727,
      "step": 20
    },
    {
      "epoch": 0.0061513675808282375,
      "grad_norm": 0.028417950496077538,
      "learning_rate": 4.817959636416969e-06,
      "loss": 10.3738,
      "step": 21
    },
    {
      "epoch": 0.006444289846581963,
      "grad_norm": 0.028397424146533012,
      "learning_rate": 4.783863644106502e-06,
      "loss": 10.371,
      "step": 22
    },
    {
      "epoch": 0.006737212112335689,
      "grad_norm": 0.026659617200493813,
      "learning_rate": 4.746985115747918e-06,
      "loss": 10.3725,
      "step": 23
    },
    {
      "epoch": 0.007030134378089414,
      "grad_norm": 0.029838740825653076,
      "learning_rate": 4.707368982147318e-06,
      "loss": 10.3733,
      "step": 24
    },
    {
      "epoch": 0.00732305664384314,
      "grad_norm": 0.03084457293152809,
      "learning_rate": 4.665063509461098e-06,
      "loss": 10.3728,
      "step": 25
    },
    {
      "epoch": 0.0076159789095968655,
      "grad_norm": 0.028473639860749245,
      "learning_rate": 4.620120240391065e-06,
      "loss": 10.3729,
      "step": 26
    },
    {
      "epoch": 0.007908901175350591,
      "grad_norm": 0.028158007189631462,
      "learning_rate": 4.572593931387604e-06,
      "loss": 10.3724,
      "step": 27
    },
    {
      "epoch": 0.008201823441104317,
      "grad_norm": 0.028451206162571907,
      "learning_rate": 4.522542485937369e-06,
      "loss": 10.3726,
      "step": 28
    },
    {
      "epoch": 0.008494745706858042,
      "grad_norm": 0.026855139061808586,
      "learning_rate": 4.470026884016805e-06,
      "loss": 10.3725,
      "step": 29
    },
    {
      "epoch": 0.008787667972611768,
      "grad_norm": 0.028105178847908974,
      "learning_rate": 4.415111107797445e-06,
      "loss": 10.3753,
      "step": 30
    },
    {
      "epoch": 0.009080590238365494,
      "grad_norm": 0.02491852454841137,
      "learning_rate": 4.357862063693486e-06,
      "loss": 10.3756,
      "step": 31
    },
    {
      "epoch": 0.009373512504119219,
      "grad_norm": 0.02876235358417034,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 10.3714,
      "step": 32
    },
    {
      "epoch": 0.009666434769872945,
      "grad_norm": 0.033276189118623734,
      "learning_rate": 4.236645926147493e-06,
      "loss": 10.3722,
      "step": 33
    },
    {
      "epoch": 0.00995935703562667,
      "grad_norm": 0.030624445527791977,
      "learning_rate": 4.172826515897146e-06,
      "loss": 10.3726,
      "step": 34
    },
    {
      "epoch": 0.010252279301380396,
      "grad_norm": 0.0296514630317688,
      "learning_rate": 4.106969024216348e-06,
      "loss": 10.3737,
      "step": 35
    },
    {
      "epoch": 0.010545201567134121,
      "grad_norm": 0.029347486793994904,
      "learning_rate": 4.039153688314146e-06,
      "loss": 10.3741,
      "step": 36
    },
    {
      "epoch": 0.010838123832887847,
      "grad_norm": 0.03406284749507904,
      "learning_rate": 3.969463130731183e-06,
      "loss": 10.3732,
      "step": 37
    },
    {
      "epoch": 0.011131046098641573,
      "grad_norm": 0.03096814826130867,
      "learning_rate": 3.897982258676867e-06,
      "loss": 10.3737,
      "step": 38
    },
    {
      "epoch": 0.011423968364395298,
      "grad_norm": 0.03231000900268555,
      "learning_rate": 3.824798160583012e-06,
      "loss": 10.3728,
      "step": 39
    },
    {
      "epoch": 0.011716890630149024,
      "grad_norm": 0.03423743322491646,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 10.3727,
      "step": 40
    },
    {
      "epoch": 0.01200981289590275,
      "grad_norm": 0.03633436933159828,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 10.371,
      "step": 41
    },
    {
      "epoch": 0.012302735161656475,
      "grad_norm": 0.03613651916384697,
      "learning_rate": 3.595927866972694e-06,
      "loss": 10.3698,
      "step": 42
    },
    {
      "epoch": 0.0125956574274102,
      "grad_norm": 0.03508604317903519,
      "learning_rate": 3.516841607689501e-06,
      "loss": 10.3709,
      "step": 43
    },
    {
      "epoch": 0.012888579693163926,
      "grad_norm": 0.03531428426504135,
      "learning_rate": 3.436516483539781e-06,
      "loss": 10.3693,
      "step": 44
    },
    {
      "epoch": 0.013181501958917652,
      "grad_norm": 0.0372382253408432,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 10.3731,
      "step": 45
    },
    {
      "epoch": 0.013474424224671377,
      "grad_norm": 0.037255220115184784,
      "learning_rate": 3.272542485937369e-06,
      "loss": 10.3696,
      "step": 46
    },
    {
      "epoch": 0.013767346490425103,
      "grad_norm": 0.03376002609729767,
      "learning_rate": 3.189093389542498e-06,
      "loss": 10.3722,
      "step": 47
    },
    {
      "epoch": 0.014060268756178829,
      "grad_norm": 0.03821876645088196,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 10.3675,
      "step": 48
    },
    {
      "epoch": 0.014353191021932554,
      "grad_norm": 0.04366350546479225,
      "learning_rate": 3.019779227044398e-06,
      "loss": 10.3713,
      "step": 49
    },
    {
      "epoch": 0.01464611328768628,
      "grad_norm": 0.04582428187131882,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 10.3714,
      "step": 50
    },
    {
      "epoch": 0.01464611328768628,
      "eval_loss": 10.3728666305542,
      "eval_runtime": 13.841,
      "eval_samples_per_second": 415.431,
      "eval_steps_per_second": 103.894,
      "step": 50
    },
    {
      "epoch": 0.014939035553440005,
      "grad_norm": 0.021559344604611397,
      "learning_rate": 2.847932752400164e-06,
      "loss": 10.3754,
      "step": 51
    },
    {
      "epoch": 0.015231957819193731,
      "grad_norm": 0.020743314176797867,
      "learning_rate": 2.761321158169134e-06,
      "loss": 10.3743,
      "step": 52
    },
    {
      "epoch": 0.015524880084947457,
      "grad_norm": 0.02609257400035858,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 10.3738,
      "step": 53
    },
    {
      "epoch": 0.015817802350701182,
      "grad_norm": 0.025397269055247307,
      "learning_rate": 2.587248741756253e-06,
      "loss": 10.3742,
      "step": 54
    },
    {
      "epoch": 0.016110724616454908,
      "grad_norm": 0.020652655512094498,
      "learning_rate": 2.5e-06,
      "loss": 10.3751,
      "step": 55
    },
    {
      "epoch": 0.016403646882208633,
      "grad_norm": 0.02285030670464039,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 10.3742,
      "step": 56
    },
    {
      "epoch": 0.01669656914796236,
      "grad_norm": 0.030166851356625557,
      "learning_rate": 2.325608815639687e-06,
      "loss": 10.3752,
      "step": 57
    },
    {
      "epoch": 0.016989491413716085,
      "grad_norm": 0.023815235123038292,
      "learning_rate": 2.238678841830867e-06,
      "loss": 10.3737,
      "step": 58
    },
    {
      "epoch": 0.01728241367946981,
      "grad_norm": 0.026874296367168427,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 10.3723,
      "step": 59
    },
    {
      "epoch": 0.017575335945223536,
      "grad_norm": 0.02652282454073429,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 10.3757,
      "step": 60
    },
    {
      "epoch": 0.01786825821097726,
      "grad_norm": 0.025690890848636627,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 10.3728,
      "step": 61
    },
    {
      "epoch": 0.018161180476730987,
      "grad_norm": 0.0272552240639925,
      "learning_rate": 1.895195261000831e-06,
      "loss": 10.374,
      "step": 62
    },
    {
      "epoch": 0.018454102742484713,
      "grad_norm": 0.02339266426861286,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 10.3736,
      "step": 63
    },
    {
      "epoch": 0.018747025008238438,
      "grad_norm": 0.02955692633986473,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 10.3731,
      "step": 64
    },
    {
      "epoch": 0.019039947273992164,
      "grad_norm": 0.02567404881119728,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 10.3746,
      "step": 65
    },
    {
      "epoch": 0.01933286953974589,
      "grad_norm": 0.02690170146524906,
      "learning_rate": 1.56348351646022e-06,
      "loss": 10.3726,
      "step": 66
    },
    {
      "epoch": 0.019625791805499615,
      "grad_norm": 0.027145514264702797,
      "learning_rate": 1.4831583923105e-06,
      "loss": 10.3724,
      "step": 67
    },
    {
      "epoch": 0.01991871407125334,
      "grad_norm": 0.024161124601960182,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 10.3739,
      "step": 68
    },
    {
      "epoch": 0.020211636337007066,
      "grad_norm": 0.026307081803679466,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 10.3725,
      "step": 69
    },
    {
      "epoch": 0.020504558602760792,
      "grad_norm": 0.023980988189578056,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 10.3735,
      "step": 70
    },
    {
      "epoch": 0.020797480868514517,
      "grad_norm": 0.03129197284579277,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 10.3733,
      "step": 71
    },
    {
      "epoch": 0.021090403134268243,
      "grad_norm": 0.02808968722820282,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 10.3726,
      "step": 72
    },
    {
      "epoch": 0.02138332540002197,
      "grad_norm": 0.023781241849064827,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 10.373,
      "step": 73
    },
    {
      "epoch": 0.021676247665775694,
      "grad_norm": 0.028046894818544388,
      "learning_rate": 9.608463116858544e-07,
      "loss": 10.3713,
      "step": 74
    },
    {
      "epoch": 0.02196916993152942,
      "grad_norm": 0.03129149228334427,
      "learning_rate": 8.930309757836517e-07,
      "loss": 10.3702,
      "step": 75
    },
    {
      "epoch": 0.022262092197283145,
      "grad_norm": 0.028456272557377815,
      "learning_rate": 8.271734841028553e-07,
      "loss": 10.3744,
      "step": 76
    },
    {
      "epoch": 0.02255501446303687,
      "grad_norm": 0.02571389265358448,
      "learning_rate": 7.633540738525066e-07,
      "loss": 10.372,
      "step": 77
    },
    {
      "epoch": 0.022847936728790597,
      "grad_norm": 0.025790490210056305,
      "learning_rate": 7.016504991533727e-07,
      "loss": 10.3731,
      "step": 78
    },
    {
      "epoch": 0.023140858994544322,
      "grad_norm": 0.029796477407217026,
      "learning_rate": 6.421379363065142e-07,
      "loss": 10.372,
      "step": 79
    },
    {
      "epoch": 0.023433781260298048,
      "grad_norm": 0.029225174337625504,
      "learning_rate": 5.848888922025553e-07,
      "loss": 10.371,
      "step": 80
    },
    {
      "epoch": 0.023726703526051773,
      "grad_norm": 0.026351463049650192,
      "learning_rate": 5.299731159831953e-07,
      "loss": 10.373,
      "step": 81
    },
    {
      "epoch": 0.0240196257918055,
      "grad_norm": 0.029768340289592743,
      "learning_rate": 4.774575140626317e-07,
      "loss": 10.3702,
      "step": 82
    },
    {
      "epoch": 0.024312548057559225,
      "grad_norm": 0.02940509095788002,
      "learning_rate": 4.27406068612396e-07,
      "loss": 10.3753,
      "step": 83
    },
    {
      "epoch": 0.02460547032331295,
      "grad_norm": 0.034831032156944275,
      "learning_rate": 3.798797596089351e-07,
      "loss": 10.3728,
      "step": 84
    },
    {
      "epoch": 0.024898392589066676,
      "grad_norm": 0.030161257833242416,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 10.372,
      "step": 85
    },
    {
      "epoch": 0.0251913148548204,
      "grad_norm": 0.03276588395237923,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 10.3712,
      "step": 86
    },
    {
      "epoch": 0.025484237120574127,
      "grad_norm": 0.03167412057518959,
      "learning_rate": 2.53014884252083e-07,
      "loss": 10.3727,
      "step": 87
    },
    {
      "epoch": 0.025777159386327853,
      "grad_norm": 0.031049178913235664,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 10.375,
      "step": 88
    },
    {
      "epoch": 0.026070081652081578,
      "grad_norm": 0.03434354439377785,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 10.3722,
      "step": 89
    },
    {
      "epoch": 0.026363003917835304,
      "grad_norm": 0.03324176371097565,
      "learning_rate": 1.507684480352292e-07,
      "loss": 10.3751,
      "step": 90
    },
    {
      "epoch": 0.02665592618358903,
      "grad_norm": 0.03137771412730217,
      "learning_rate": 1.223587092621162e-07,
      "loss": 10.3708,
      "step": 91
    },
    {
      "epoch": 0.026948848449342755,
      "grad_norm": 0.03048369660973549,
      "learning_rate": 9.684576015420277e-08,
      "loss": 10.3706,
      "step": 92
    },
    {
      "epoch": 0.02724177071509648,
      "grad_norm": 0.03266899660229683,
      "learning_rate": 7.426068431000883e-08,
      "loss": 10.3729,
      "step": 93
    },
    {
      "epoch": 0.027534692980850206,
      "grad_norm": 0.03793390840291977,
      "learning_rate": 5.463099816548578e-08,
      "loss": 10.3726,
      "step": 94
    },
    {
      "epoch": 0.02782761524660393,
      "grad_norm": 0.03327462822198868,
      "learning_rate": 3.798061746947995e-08,
      "loss": 10.3699,
      "step": 95
    },
    {
      "epoch": 0.028120537512357657,
      "grad_norm": 0.033858004957437515,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 10.3712,
      "step": 96
    },
    {
      "epoch": 0.028413459778111383,
      "grad_norm": 0.043706659227609634,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 10.3702,
      "step": 97
    },
    {
      "epoch": 0.02870638204386511,
      "grad_norm": 0.041960231959819794,
      "learning_rate": 6.089874350439507e-09,
      "loss": 10.3711,
      "step": 98
    },
    {
      "epoch": 0.028999304309618834,
      "grad_norm": 0.04037592187523842,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 10.3693,
      "step": 99
    },
    {
      "epoch": 0.02929222657537256,
      "grad_norm": 0.04143953323364258,
      "learning_rate": 0.0,
      "loss": 10.3714,
      "step": 100
    },
    {
      "epoch": 0.02929222657537256,
      "eval_loss": 10.372817039489746,
      "eval_runtime": 13.8116,
      "eval_samples_per_second": 416.317,
      "eval_steps_per_second": 104.116,
      "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": 11022740619264.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}