{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.003637818763869184,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.637818763869184e-05,
      "grad_norm": 3.02694952551974e-05,
      "learning_rate": 1.0017e-05,
      "loss": 23.0,
      "step": 1
    },
    {
      "epoch": 3.637818763869184e-05,
      "eval_loss": 11.5,
      "eval_runtime": 151.1383,
      "eval_samples_per_second": 76.585,
      "eval_steps_per_second": 19.148,
      "step": 1
    },
    {
      "epoch": 7.275637527738368e-05,
      "grad_norm": 2.229630626970902e-05,
      "learning_rate": 2.0034e-05,
      "loss": 23.0,
      "step": 2
    },
    {
      "epoch": 0.00010913456291607552,
      "grad_norm": 1.7369073248119093e-05,
      "learning_rate": 3.0050999999999997e-05,
      "loss": 23.0,
      "step": 3
    },
    {
      "epoch": 0.00014551275055476736,
      "grad_norm": 2.0572153516695835e-05,
      "learning_rate": 4.0068e-05,
      "loss": 23.0,
      "step": 4
    },
    {
      "epoch": 0.0001818909381934592,
      "grad_norm": 2.1671123249689117e-05,
      "learning_rate": 5.0085e-05,
      "loss": 23.0,
      "step": 5
    },
    {
      "epoch": 0.00021826912583215103,
      "grad_norm": 3.2477018976351246e-05,
      "learning_rate": 6.0101999999999995e-05,
      "loss": 23.0,
      "step": 6
    },
    {
      "epoch": 0.00025464731347084286,
      "grad_norm": 2.8829166694777086e-05,
      "learning_rate": 7.0119e-05,
      "loss": 23.0,
      "step": 7
    },
    {
      "epoch": 0.0002910255011095347,
      "grad_norm": 1.7811666111811064e-05,
      "learning_rate": 8.0136e-05,
      "loss": 23.0,
      "step": 8
    },
    {
      "epoch": 0.00032740368874822657,
      "grad_norm": 3.275599010521546e-05,
      "learning_rate": 9.0153e-05,
      "loss": 23.0,
      "step": 9
    },
    {
      "epoch": 0.0003637818763869184,
      "grad_norm": 2.8053269488736987e-05,
      "learning_rate": 0.00010017,
      "loss": 23.0,
      "step": 10
    },
    {
      "epoch": 0.00040016006402561027,
      "grad_norm": 1.9141238226438873e-05,
      "learning_rate": 9.964278947368421e-05,
      "loss": 23.0,
      "step": 11
    },
    {
      "epoch": 0.00043653825166430207,
      "grad_norm": 2.7660466002998874e-05,
      "learning_rate": 9.911557894736841e-05,
      "loss": 23.0,
      "step": 12
    },
    {
      "epoch": 0.0004729164393029939,
      "grad_norm": 4.070868089911528e-05,
      "learning_rate": 9.858836842105263e-05,
      "loss": 23.0,
      "step": 13
    },
    {
      "epoch": 0.0005092946269416857,
      "grad_norm": 4.520040602074005e-05,
      "learning_rate": 9.806115789473684e-05,
      "loss": 23.0,
      "step": 14
    },
    {
      "epoch": 0.0005456728145803776,
      "grad_norm": 3.214128810213879e-05,
      "learning_rate": 9.753394736842106e-05,
      "loss": 23.0,
      "step": 15
    },
    {
      "epoch": 0.0005820510022190694,
      "grad_norm": 2.628938455018215e-05,
      "learning_rate": 9.700673684210526e-05,
      "loss": 23.0,
      "step": 16
    },
    {
      "epoch": 0.0006184291898577613,
      "grad_norm": 4.2206476791761816e-05,
      "learning_rate": 9.647952631578948e-05,
      "loss": 23.0,
      "step": 17
    },
    {
      "epoch": 0.0006548073774964531,
      "grad_norm": 7.11869724909775e-05,
      "learning_rate": 9.595231578947368e-05,
      "loss": 23.0,
      "step": 18
    },
    {
      "epoch": 0.0006911855651351449,
      "grad_norm": 6.381978164426982e-05,
      "learning_rate": 9.542510526315789e-05,
      "loss": 23.0,
      "step": 19
    },
    {
      "epoch": 0.0007275637527738368,
      "grad_norm": 5.668163066729903e-05,
      "learning_rate": 9.48978947368421e-05,
      "loss": 23.0,
      "step": 20
    },
    {
      "epoch": 0.0007639419404125286,
      "grad_norm": 5.15950086992234e-05,
      "learning_rate": 9.437068421052632e-05,
      "loss": 23.0,
      "step": 21
    },
    {
      "epoch": 0.0008003201280512205,
      "grad_norm": 3.6641820770455524e-05,
      "learning_rate": 9.384347368421052e-05,
      "loss": 23.0,
      "step": 22
    },
    {
      "epoch": 0.0008366983156899123,
      "grad_norm": 4.6492976252920926e-05,
      "learning_rate": 9.331626315789474e-05,
      "loss": 23.0,
      "step": 23
    },
    {
      "epoch": 0.0008730765033286041,
      "grad_norm": 3.108743840130046e-05,
      "learning_rate": 9.278905263157894e-05,
      "loss": 23.0,
      "step": 24
    },
    {
      "epoch": 0.000909454690967296,
      "grad_norm": 7.915790774859488e-05,
      "learning_rate": 9.226184210526316e-05,
      "loss": 23.0,
      "step": 25
    },
    {
      "epoch": 0.0009458328786059878,
      "grad_norm": 6.270438461797312e-05,
      "learning_rate": 9.173463157894736e-05,
      "loss": 23.0,
      "step": 26
    },
    {
      "epoch": 0.0009822110662446796,
      "grad_norm": 7.017728785285726e-05,
      "learning_rate": 9.120742105263159e-05,
      "loss": 23.0,
      "step": 27
    },
    {
      "epoch": 0.0010185892538833714,
      "grad_norm": 5.595381298917346e-05,
      "learning_rate": 9.068021052631579e-05,
      "loss": 23.0,
      "step": 28
    },
    {
      "epoch": 0.0010549674415220635,
      "grad_norm": 0.00011628826177911833,
      "learning_rate": 9.0153e-05,
      "loss": 23.0,
      "step": 29
    },
    {
      "epoch": 0.0010913456291607553,
      "grad_norm": 0.00014665414346382022,
      "learning_rate": 8.96257894736842e-05,
      "loss": 23.0,
      "step": 30
    },
    {
      "epoch": 0.001127723816799447,
      "grad_norm": 7.506920519517735e-05,
      "learning_rate": 8.909857894736842e-05,
      "loss": 23.0,
      "step": 31
    },
    {
      "epoch": 0.0011641020044381389,
      "grad_norm": 5.339025301509537e-05,
      "learning_rate": 8.857136842105263e-05,
      "loss": 23.0,
      "step": 32
    },
    {
      "epoch": 0.0012004801920768306,
      "grad_norm": 0.00014683412155136466,
      "learning_rate": 8.804415789473684e-05,
      "loss": 23.0,
      "step": 33
    },
    {
      "epoch": 0.0012368583797155227,
      "grad_norm": 8.226917998399585e-05,
      "learning_rate": 8.751694736842105e-05,
      "loss": 23.0,
      "step": 34
    },
    {
      "epoch": 0.0012732365673542145,
      "grad_norm": 9.31067843339406e-05,
      "learning_rate": 8.698973684210527e-05,
      "loss": 23.0,
      "step": 35
    },
    {
      "epoch": 0.0013096147549929063,
      "grad_norm": 0.00013525430404115468,
      "learning_rate": 8.646252631578948e-05,
      "loss": 23.0,
      "step": 36
    },
    {
      "epoch": 0.001345992942631598,
      "grad_norm": 0.00012200818309793249,
      "learning_rate": 8.593531578947368e-05,
      "loss": 23.0,
      "step": 37
    },
    {
      "epoch": 0.0013823711302702899,
      "grad_norm": 8.02081631263718e-05,
      "learning_rate": 8.54081052631579e-05,
      "loss": 23.0,
      "step": 38
    },
    {
      "epoch": 0.0014187493179089819,
      "grad_norm": 8.921958215069026e-05,
      "learning_rate": 8.48808947368421e-05,
      "loss": 23.0,
      "step": 39
    },
    {
      "epoch": 0.0014551275055476737,
      "grad_norm": 0.00017843855312094092,
      "learning_rate": 8.435368421052631e-05,
      "loss": 23.0,
      "step": 40
    },
    {
      "epoch": 0.0014915056931863655,
      "grad_norm": 0.00016177799261640757,
      "learning_rate": 8.382647368421053e-05,
      "loss": 23.0,
      "step": 41
    },
    {
      "epoch": 0.0015278838808250573,
      "grad_norm": 0.0001830129767768085,
      "learning_rate": 8.329926315789474e-05,
      "loss": 23.0,
      "step": 42
    },
    {
      "epoch": 0.001564262068463749,
      "grad_norm": 0.00019341587903909385,
      "learning_rate": 8.277205263157894e-05,
      "loss": 23.0,
      "step": 43
    },
    {
      "epoch": 0.001600640256102441,
      "grad_norm": 0.00021447647304739803,
      "learning_rate": 8.224484210526316e-05,
      "loss": 23.0,
      "step": 44
    },
    {
      "epoch": 0.0016370184437411329,
      "grad_norm": 0.0001244143204530701,
      "learning_rate": 8.171763157894736e-05,
      "loss": 23.0,
      "step": 45
    },
    {
      "epoch": 0.0016733966313798247,
      "grad_norm": 0.0001582489931024611,
      "learning_rate": 8.119042105263158e-05,
      "loss": 23.0,
      "step": 46
    },
    {
      "epoch": 0.0017097748190185165,
      "grad_norm": 0.00028872533584944904,
      "learning_rate": 8.066321052631578e-05,
      "loss": 23.0,
      "step": 47
    },
    {
      "epoch": 0.0017461530066572083,
      "grad_norm": 0.00030024562147445977,
      "learning_rate": 8.0136e-05,
      "loss": 23.0,
      "step": 48
    },
    {
      "epoch": 0.0017825311942959,
      "grad_norm": 9.963209595298395e-05,
      "learning_rate": 7.960878947368421e-05,
      "loss": 23.0,
      "step": 49
    },
    {
      "epoch": 0.001818909381934592,
      "grad_norm": 0.00030614796560257673,
      "learning_rate": 7.908157894736842e-05,
      "loss": 23.0,
      "step": 50
    },
    {
      "epoch": 0.001818909381934592,
      "eval_loss": 11.5,
      "eval_runtime": 151.0232,
      "eval_samples_per_second": 76.644,
      "eval_steps_per_second": 19.163,
      "step": 50
    },
    {
      "epoch": 0.0018552875695732839,
      "grad_norm": 6.623671652050689e-05,
      "learning_rate": 7.855436842105262e-05,
      "loss": 23.0,
      "step": 51
    },
    {
      "epoch": 0.0018916657572119757,
      "grad_norm": 6.400385609595105e-05,
      "learning_rate": 7.802715789473684e-05,
      "loss": 23.0,
      "step": 52
    },
    {
      "epoch": 0.0019280439448506675,
      "grad_norm": 0.00013267774193082005,
      "learning_rate": 7.749994736842104e-05,
      "loss": 23.0,
      "step": 53
    },
    {
      "epoch": 0.0019644221324893593,
      "grad_norm": 0.0001021127391140908,
      "learning_rate": 7.697273684210526e-05,
      "loss": 23.0,
      "step": 54
    },
    {
      "epoch": 0.0020008003201280513,
      "grad_norm": 3.8101632526377216e-05,
      "learning_rate": 7.644552631578947e-05,
      "loss": 23.0,
      "step": 55
    },
    {
      "epoch": 0.002037178507766743,
      "grad_norm": 0.0001221260172314942,
      "learning_rate": 7.591831578947369e-05,
      "loss": 23.0,
      "step": 56
    },
    {
      "epoch": 0.002073556695405435,
      "grad_norm": 0.00010851105616893619,
      "learning_rate": 7.539110526315789e-05,
      "loss": 23.0,
      "step": 57
    },
    {
      "epoch": 0.002109934883044127,
      "grad_norm": 0.00014188556815497577,
      "learning_rate": 7.48638947368421e-05,
      "loss": 23.0,
      "step": 58
    },
    {
      "epoch": 0.0021463130706828185,
      "grad_norm": 0.00020047224825248122,
      "learning_rate": 7.433668421052632e-05,
      "loss": 23.0,
      "step": 59
    },
    {
      "epoch": 0.0021826912583215105,
      "grad_norm": 6.952315743546933e-05,
      "learning_rate": 7.380947368421052e-05,
      "loss": 23.0,
      "step": 60
    },
    {
      "epoch": 0.002219069445960202,
      "grad_norm": 0.00011589556379476562,
      "learning_rate": 7.328226315789473e-05,
      "loss": 23.0,
      "step": 61
    },
    {
      "epoch": 0.002255447633598894,
      "grad_norm": 0.0001030775674735196,
      "learning_rate": 7.275505263157895e-05,
      "loss": 23.0,
      "step": 62
    },
    {
      "epoch": 0.002291825821237586,
      "grad_norm": 7.992862083483487e-05,
      "learning_rate": 7.222784210526316e-05,
      "loss": 23.0,
      "step": 63
    },
    {
      "epoch": 0.0023282040088762777,
      "grad_norm": 0.0001841662742663175,
      "learning_rate": 7.170063157894737e-05,
      "loss": 23.0,
      "step": 64
    },
    {
      "epoch": 0.0023645821965149697,
      "grad_norm": 0.0002175459812860936,
      "learning_rate": 7.117342105263158e-05,
      "loss": 23.0,
      "step": 65
    },
    {
      "epoch": 0.0024009603841536613,
      "grad_norm": 0.00013885030057281256,
      "learning_rate": 7.064621052631578e-05,
      "loss": 23.0,
      "step": 66
    },
    {
      "epoch": 0.0024373385717923533,
      "grad_norm": 0.00019218168745283037,
      "learning_rate": 7.0119e-05,
      "loss": 23.0,
      "step": 67
    },
    {
      "epoch": 0.0024737167594310453,
      "grad_norm": 9.952030086424202e-05,
      "learning_rate": 6.959178947368421e-05,
      "loss": 23.0,
      "step": 68
    },
    {
      "epoch": 0.002510094947069737,
      "grad_norm": 0.0002263988135382533,
      "learning_rate": 6.906457894736843e-05,
      "loss": 23.0,
      "step": 69
    },
    {
      "epoch": 0.002546473134708429,
      "grad_norm": 0.0002095073723467067,
      "learning_rate": 6.853736842105263e-05,
      "loss": 23.0,
      "step": 70
    },
    {
      "epoch": 0.0025828513223471205,
      "grad_norm": 0.0001873522560345009,
      "learning_rate": 6.801015789473684e-05,
      "loss": 23.0,
      "step": 71
    },
    {
      "epoch": 0.0026192295099858125,
      "grad_norm": 0.00012239122588653117,
      "learning_rate": 6.748294736842105e-05,
      "loss": 23.0,
      "step": 72
    },
    {
      "epoch": 0.0026556076976245045,
      "grad_norm": 0.0002145641337847337,
      "learning_rate": 6.695573684210526e-05,
      "loss": 23.0,
      "step": 73
    },
    {
      "epoch": 0.002691985885263196,
      "grad_norm": 0.0002729996922425926,
      "learning_rate": 6.642852631578946e-05,
      "loss": 23.0,
      "step": 74
    },
    {
      "epoch": 0.002728364072901888,
      "grad_norm": 0.00029615170205943286,
      "learning_rate": 6.590131578947369e-05,
      "loss": 23.0,
      "step": 75
    },
    {
      "epoch": 0.0027647422605405797,
      "grad_norm": 0.00010048908006865531,
      "learning_rate": 6.537410526315789e-05,
      "loss": 23.0,
      "step": 76
    },
    {
      "epoch": 0.0028011204481792717,
      "grad_norm": 0.00021512502280529588,
      "learning_rate": 6.484689473684211e-05,
      "loss": 23.0,
      "step": 77
    },
    {
      "epoch": 0.0028374986358179637,
      "grad_norm": 0.0001807186781661585,
      "learning_rate": 6.431968421052631e-05,
      "loss": 23.0,
      "step": 78
    },
    {
      "epoch": 0.0028738768234566553,
      "grad_norm": 0.0002783916424959898,
      "learning_rate": 6.379247368421052e-05,
      "loss": 23.0,
      "step": 79
    },
    {
      "epoch": 0.0029102550110953473,
      "grad_norm": 0.0002033570344792679,
      "learning_rate": 6.326526315789474e-05,
      "loss": 23.0,
      "step": 80
    },
    {
      "epoch": 0.002946633198734039,
      "grad_norm": 0.00041213902295567095,
      "learning_rate": 6.273805263157894e-05,
      "loss": 23.0,
      "step": 81
    },
    {
      "epoch": 0.002983011386372731,
      "grad_norm": 0.0004079529899172485,
      "learning_rate": 6.221084210526315e-05,
      "loss": 23.0,
      "step": 82
    },
    {
      "epoch": 0.003019389574011423,
      "grad_norm": 0.00037718864041380584,
      "learning_rate": 6.168363157894737e-05,
      "loss": 23.0,
      "step": 83
    },
    {
      "epoch": 0.0030557677616501145,
      "grad_norm": 0.00021675822790712118,
      "learning_rate": 6.115642105263159e-05,
      "loss": 23.0,
      "step": 84
    },
    {
      "epoch": 0.0030921459492888066,
      "grad_norm": 0.000161567993927747,
      "learning_rate": 6.0629210526315787e-05,
      "loss": 23.0,
      "step": 85
    },
    {
      "epoch": 0.003128524136927498,
      "grad_norm": 0.00036831083707511425,
      "learning_rate": 6.0101999999999995e-05,
      "loss": 23.0,
      "step": 86
    },
    {
      "epoch": 0.00316490232456619,
      "grad_norm": 0.00021508059580810368,
      "learning_rate": 5.95747894736842e-05,
      "loss": 23.0,
      "step": 87
    },
    {
      "epoch": 0.003201280512204882,
      "grad_norm": 0.00037027744110673666,
      "learning_rate": 5.904757894736841e-05,
      "loss": 23.0,
      "step": 88
    },
    {
      "epoch": 0.0032376586998435737,
      "grad_norm": 0.0005091584753245115,
      "learning_rate": 5.852036842105263e-05,
      "loss": 23.0,
      "step": 89
    },
    {
      "epoch": 0.0032740368874822658,
      "grad_norm": 0.00018075609114021063,
      "learning_rate": 5.799315789473684e-05,
      "loss": 23.0,
      "step": 90
    },
    {
      "epoch": 0.0033104150751209573,
      "grad_norm": 0.0002826842537615448,
      "learning_rate": 5.746594736842105e-05,
      "loss": 23.0,
      "step": 91
    },
    {
      "epoch": 0.0033467932627596494,
      "grad_norm": 0.0003830195346381515,
      "learning_rate": 5.693873684210526e-05,
      "loss": 23.0,
      "step": 92
    },
    {
      "epoch": 0.003383171450398341,
      "grad_norm": 0.0003719093801919371,
      "learning_rate": 5.641152631578947e-05,
      "loss": 23.0,
      "step": 93
    },
    {
      "epoch": 0.003419549638037033,
      "grad_norm": 0.0003959982714150101,
      "learning_rate": 5.588431578947368e-05,
      "loss": 23.0,
      "step": 94
    },
    {
      "epoch": 0.003455927825675725,
      "grad_norm": 0.0005398475914262235,
      "learning_rate": 5.5357105263157896e-05,
      "loss": 23.0,
      "step": 95
    },
    {
      "epoch": 0.0034923060133144166,
      "grad_norm": 0.00043294107308611274,
      "learning_rate": 5.482989473684211e-05,
      "loss": 23.0,
      "step": 96
    },
    {
      "epoch": 0.0035286842009531086,
      "grad_norm": 0.0003873602254316211,
      "learning_rate": 5.430268421052632e-05,
      "loss": 23.0,
      "step": 97
    },
    {
      "epoch": 0.0035650623885918,
      "grad_norm": 0.0002535148523747921,
      "learning_rate": 5.377547368421053e-05,
      "loss": 23.0,
      "step": 98
    },
    {
      "epoch": 0.003601440576230492,
      "grad_norm": 0.000758410373236984,
      "learning_rate": 5.3248263157894736e-05,
      "loss": 23.0,
      "step": 99
    },
    {
      "epoch": 0.003637818763869184,
      "grad_norm": 0.0005609129439108074,
      "learning_rate": 5.2721052631578944e-05,
      "loss": 23.0,
      "step": 100
    },
    {
      "epoch": 0.003637818763869184,
      "eval_loss": 11.5,
      "eval_runtime": 151.0179,
      "eval_samples_per_second": 76.647,
      "eval_steps_per_second": 19.163,
      "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": 4039906885632.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}