{
  "best_metric": 10.372788429260254,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 2.3928215353938187,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031904287138584245,
      "grad_norm": 0.06419440358877182,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3808,
      "step": 1
    },
    {
      "epoch": 0.031904287138584245,
      "eval_loss": 10.379875183105469,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 286.696,
      "eval_steps_per_second": 74.541,
      "step": 1
    },
    {
      "epoch": 0.06380857427716849,
      "grad_norm": 0.03532293438911438,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.3804,
      "step": 2
    },
    {
      "epoch": 0.09571286141575275,
      "grad_norm": 0.027720365673303604,
      "learning_rate": 0.0001,
      "loss": 10.3797,
      "step": 3
    },
    {
      "epoch": 0.12761714855433698,
      "grad_norm": 0.02375604398548603,
      "learning_rate": 9.99571699711836e-05,
      "loss": 10.3803,
      "step": 4
    },
    {
      "epoch": 0.15952143569292124,
      "grad_norm": 0.02083384059369564,
      "learning_rate": 9.982876141412856e-05,
      "loss": 10.3797,
      "step": 5
    },
    {
      "epoch": 0.1914257228315055,
      "grad_norm": 0.021519361063838005,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3804,
      "step": 6
    },
    {
      "epoch": 0.22333000997008973,
      "grad_norm": 0.021820418536663055,
      "learning_rate": 9.931634888554937e-05,
      "loss": 10.3802,
      "step": 7
    },
    {
      "epoch": 0.25523429710867396,
      "grad_norm": 0.09350977092981339,
      "learning_rate": 9.893332032039701e-05,
      "loss": 10.3806,
      "step": 8
    },
    {
      "epoch": 0.28713858424725824,
      "grad_norm": 0.039236634969711304,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3797,
      "step": 9
    },
    {
      "epoch": 0.3190428713858425,
      "grad_norm": 0.035836756229400635,
      "learning_rate": 9.791726278367022e-05,
      "loss": 10.3808,
      "step": 10
    },
    {
      "epoch": 0.3509471585244267,
      "grad_norm": 0.031301405280828476,
      "learning_rate": 9.728616793536588e-05,
      "loss": 10.3788,
      "step": 11
    },
    {
      "epoch": 0.382851445663011,
      "grad_norm": 0.02643793448805809,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3789,
      "step": 12
    },
    {
      "epoch": 0.4147557328015952,
      "grad_norm": 0.02430611290037632,
      "learning_rate": 9.578385041664925e-05,
      "loss": 10.3781,
      "step": 13
    },
    {
      "epoch": 0.44666001994017945,
      "grad_norm": 0.02308354340493679,
      "learning_rate": 9.491548749301997e-05,
      "loss": 10.3784,
      "step": 14
    },
    {
      "epoch": 0.4785643070787637,
      "grad_norm": 0.028244340792298317,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.379,
      "step": 15
    },
    {
      "epoch": 0.5104685942173479,
      "grad_norm": 0.07378281652927399,
      "learning_rate": 9.295261506157986e-05,
      "loss": 10.3785,
      "step": 16
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.03998374566435814,
      "learning_rate": 9.186184199300464e-05,
      "loss": 10.3793,
      "step": 17
    },
    {
      "epoch": 0.5742771684945165,
      "grad_norm": 0.03800854831933975,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3776,
      "step": 18
    },
    {
      "epoch": 0.6061814556331007,
      "grad_norm": 0.030691292136907578,
      "learning_rate": 8.947199994035401e-05,
      "loss": 10.3782,
      "step": 19
    },
    {
      "epoch": 0.638085742771685,
      "grad_norm": 0.027072234079241753,
      "learning_rate": 8.817748015645558e-05,
      "loss": 10.3783,
      "step": 20
    },
    {
      "epoch": 0.6699900299102692,
      "grad_norm": 0.02719455398619175,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3792,
      "step": 21
    },
    {
      "epoch": 0.7018943170488534,
      "grad_norm": 0.026329834014177322,
      "learning_rate": 8.540155934270471e-05,
      "loss": 10.3786,
      "step": 22
    },
    {
      "epoch": 0.7337986041874377,
      "grad_norm": 0.03928585723042488,
      "learning_rate": 8.392544243589427e-05,
      "loss": 10.3772,
      "step": 23
    },
    {
      "epoch": 0.765702891326022,
      "grad_norm": 0.08308948576450348,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3773,
      "step": 24
    },
    {
      "epoch": 0.7976071784646062,
      "grad_norm": 0.050812482833862305,
      "learning_rate": 8.081093963579707e-05,
      "loss": 10.3767,
      "step": 25
    },
    {
      "epoch": 0.7976071784646062,
      "eval_loss": 10.377211570739746,
      "eval_runtime": 0.1813,
      "eval_samples_per_second": 275.802,
      "eval_steps_per_second": 71.709,
      "step": 25
    },
    {
      "epoch": 0.8295114656031904,
      "grad_norm": 0.0448242649435997,
      "learning_rate": 7.917848237560709e-05,
      "loss": 10.3768,
      "step": 26
    },
    {
      "epoch": 0.8614157527417746,
      "grad_norm": 0.03327423706650734,
      "learning_rate": 7.75e-05,
      "loss": 10.3765,
      "step": 27
    },
    {
      "epoch": 0.8933200398803589,
      "grad_norm": 0.029801176860928535,
      "learning_rate": 7.577868759557654e-05,
      "loss": 10.3774,
      "step": 28
    },
    {
      "epoch": 0.9252243270189432,
      "grad_norm": 0.031676966696977615,
      "learning_rate": 7.401782177833148e-05,
      "loss": 10.378,
      "step": 29
    },
    {
      "epoch": 0.9571286141575274,
      "grad_norm": 0.032815348356962204,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3778,
      "step": 30
    },
    {
      "epoch": 0.9890329012961117,
      "grad_norm": 0.05490710586309433,
      "learning_rate": 7.03909064496551e-05,
      "loss": 10.3771,
      "step": 31
    },
    {
      "epoch": 1.0209371884346958,
      "grad_norm": 0.10271252691745758,
      "learning_rate": 6.853176097769229e-05,
      "loss": 17.344,
      "step": 32
    },
    {
      "epoch": 1.0528414755732802,
      "grad_norm": 0.06409234553575516,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.2565,
      "step": 33
    },
    {
      "epoch": 1.0847457627118644,
      "grad_norm": 0.05500740185379982,
      "learning_rate": 6.473978262721463e-05,
      "loss": 10.3753,
      "step": 34
    },
    {
      "epoch": 1.1166500498504486,
      "grad_norm": 0.03728007897734642,
      "learning_rate": 6.281416799501188e-05,
      "loss": 10.3715,
      "step": 35
    },
    {
      "epoch": 1.148554336989033,
      "grad_norm": 0.03842683136463165,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.4211,
      "step": 36
    },
    {
      "epoch": 1.1804586241276172,
      "grad_norm": 0.03933300822973251,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 10.6714,
      "step": 37
    },
    {
      "epoch": 1.2123629112662013,
      "grad_norm": 0.03183865174651146,
      "learning_rate": 5.696287243144013e-05,
      "loss": 10.4574,
      "step": 38
    },
    {
      "epoch": 1.2442671984047857,
      "grad_norm": 0.036480437964200974,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.8814,
      "step": 39
    },
    {
      "epoch": 1.27617148554337,
      "grad_norm": 0.1208992525935173,
      "learning_rate": 5.303712756855988e-05,
      "loss": 13.486,
      "step": 40
    },
    {
      "epoch": 1.308075772681954,
      "grad_norm": 0.058902185410261154,
      "learning_rate": 5.107799157635538e-05,
      "loss": 10.3354,
      "step": 41
    },
    {
      "epoch": 1.3399800598205385,
      "grad_norm": 0.05739002674818039,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3683,
      "step": 42
    },
    {
      "epoch": 1.3718843469591226,
      "grad_norm": 0.050218719989061356,
      "learning_rate": 4.718583200498814e-05,
      "loss": 10.3865,
      "step": 43
    },
    {
      "epoch": 1.4037886340977068,
      "grad_norm": 0.03760230913758278,
      "learning_rate": 4.526021737278538e-05,
      "loss": 10.4672,
      "step": 44
    },
    {
      "epoch": 1.4356929212362912,
      "grad_norm": 0.03762374445796013,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.6383,
      "step": 45
    },
    {
      "epoch": 1.4675972083748754,
      "grad_norm": 0.03604252636432648,
      "learning_rate": 4.146823902230772e-05,
      "loss": 10.726,
      "step": 46
    },
    {
      "epoch": 1.4995014955134596,
      "grad_norm": 0.07998944073915482,
      "learning_rate": 3.960909355034491e-05,
      "loss": 7.2666,
      "step": 47
    },
    {
      "epoch": 1.531405782652044,
      "grad_norm": 0.11271944642066956,
      "learning_rate": 3.777924554357096e-05,
      "loss": 12.796,
      "step": 48
    },
    {
      "epoch": 1.5633100697906281,
      "grad_norm": 0.0690908133983612,
      "learning_rate": 3.598217822166854e-05,
      "loss": 10.352,
      "step": 49
    },
    {
      "epoch": 1.5952143569292123,
      "grad_norm": 0.056807372719049454,
      "learning_rate": 3.422131240442349e-05,
      "loss": 10.3753,
      "step": 50
    },
    {
      "epoch": 1.5952143569292123,
      "eval_loss": 10.374171257019043,
      "eval_runtime": 0.1795,
      "eval_samples_per_second": 278.624,
      "eval_steps_per_second": 72.442,
      "step": 50
    },
    {
      "epoch": 1.6271186440677967,
      "grad_norm": 0.0471082478761673,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3914,
      "step": 51
    },
    {
      "epoch": 1.659022931206381,
      "grad_norm": 0.03859815374016762,
      "learning_rate": 3.082151762439293e-05,
      "loss": 10.5452,
      "step": 52
    },
    {
      "epoch": 1.690927218344965,
      "grad_norm": 0.043793581426143646,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 10.5909,
      "step": 53
    },
    {
      "epoch": 1.7228315054835495,
      "grad_norm": 0.056106261909008026,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.2968,
      "step": 54
    },
    {
      "epoch": 1.7547357926221336,
      "grad_norm": 0.09795401245355606,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 8.1943,
      "step": 55
    },
    {
      "epoch": 1.7866400797607178,
      "grad_norm": 0.09200040251016617,
      "learning_rate": 2.459844065729529e-05,
      "loss": 11.2377,
      "step": 56
    },
    {
      "epoch": 1.8185443668993022,
      "grad_norm": 0.06912614405155182,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3569,
      "step": 57
    },
    {
      "epoch": 1.8504486540378864,
      "grad_norm": 0.06139494851231575,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 10.3725,
      "step": 58
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.04969213530421257,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 10.4022,
      "step": 59
    },
    {
      "epoch": 1.914257228315055,
      "grad_norm": 0.045224543660879135,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.6288,
      "step": 60
    },
    {
      "epoch": 1.9461615154536391,
      "grad_norm": 0.040774866938591,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 10.4855,
      "step": 61
    },
    {
      "epoch": 1.9780658025922233,
      "grad_norm": 0.060824956744909286,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 11.9078,
      "step": 62
    },
    {
      "epoch": 2.0099700897308077,
      "grad_norm": 0.12398073822259903,
      "learning_rate": 1.602885682970026e-05,
      "loss": 15.4694,
      "step": 63
    },
    {
      "epoch": 2.0418743768693917,
      "grad_norm": 0.08448352664709091,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 10.1654,
      "step": 64
    },
    {
      "epoch": 2.073778664007976,
      "grad_norm": 0.07190793752670288,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 10.3571,
      "step": 65
    },
    {
      "epoch": 2.1056829511465605,
      "grad_norm": 0.06088152155280113,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3712,
      "step": 66
    },
    {
      "epoch": 2.1375872382851444,
      "grad_norm": 0.05480685457587242,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 10.4064,
      "step": 67
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.047166239470243454,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 10.6693,
      "step": 68
    },
    {
      "epoch": 2.201395812562313,
      "grad_norm": 0.04388361796736717,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.443,
      "step": 69
    },
    {
      "epoch": 2.233300099700897,
      "grad_norm": 0.03891513869166374,
      "learning_rate": 1.1066679679603e-05,
      "loss": 9.0255,
      "step": 70
    },
    {
      "epoch": 2.2652043868394816,
      "grad_norm": 0.12693141400814056,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 11.3904,
      "step": 71
    },
    {
      "epoch": 2.297108673978066,
      "grad_norm": 0.09395328909158707,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3146,
      "step": 72
    },
    {
      "epoch": 2.32901296111665,
      "grad_norm": 0.0779162272810936,
      "learning_rate": 1.017123858587145e-05,
      "loss": 10.3691,
      "step": 73
    },
    {
      "epoch": 2.3609172482552343,
      "grad_norm": 0.06264185160398483,
      "learning_rate": 1.00428300288164e-05,
      "loss": 10.3792,
      "step": 74
    },
    {
      "epoch": 2.3928215353938187,
      "grad_norm": 0.044317249208688736,
      "learning_rate": 1e-05,
      "loss": 10.4356,
      "step": 75
    },
    {
      "epoch": 2.3928215353938187,
      "eval_loss": 10.372788429260254,
      "eval_runtime": 0.1713,
      "eval_samples_per_second": 291.857,
      "eval_steps_per_second": 75.883,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 64152089395200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}