{
  "best_metric": 11.939474105834961,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2292920607623961,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004585841215247922,
      "grad_norm": 0.027800368145108223,
      "learning_rate": 5e-05,
      "loss": 11.9442,
      "step": 1
    },
    {
      "epoch": 0.004585841215247922,
      "eval_loss": 11.943634033203125,
      "eval_runtime": 3.1218,
      "eval_samples_per_second": 470.884,
      "eval_steps_per_second": 58.941,
      "step": 1
    },
    {
      "epoch": 0.009171682430495844,
      "grad_norm": 0.029491420835256577,
      "learning_rate": 0.0001,
      "loss": 11.9438,
      "step": 2
    },
    {
      "epoch": 0.013757523645743766,
      "grad_norm": 0.025944799184799194,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9431,
      "step": 3
    },
    {
      "epoch": 0.01834336486099169,
      "grad_norm": 0.029730679467320442,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9416,
      "step": 4
    },
    {
      "epoch": 0.02292920607623961,
      "grad_norm": 0.027700157836079597,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9428,
      "step": 5
    },
    {
      "epoch": 0.027515047291487533,
      "grad_norm": 0.02923009917140007,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.9451,
      "step": 6
    },
    {
      "epoch": 0.03210088850673545,
      "grad_norm": 0.030315719544887543,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9473,
      "step": 7
    },
    {
      "epoch": 0.03668672972198338,
      "grad_norm": 0.029349561780691147,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9422,
      "step": 8
    },
    {
      "epoch": 0.0412725709372313,
      "grad_norm": 0.029398830607533455,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9411,
      "step": 9
    },
    {
      "epoch": 0.04585841215247922,
      "grad_norm": 0.03133676201105118,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9429,
      "step": 10
    },
    {
      "epoch": 0.05044425336772714,
      "grad_norm": 0.028583215549588203,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.9448,
      "step": 11
    },
    {
      "epoch": 0.055030094582975066,
      "grad_norm": 0.030547212809324265,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9427,
      "step": 12
    },
    {
      "epoch": 0.05961593579822299,
      "grad_norm": 0.03508062660694122,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9432,
      "step": 13
    },
    {
      "epoch": 0.0642017770134709,
      "grad_norm": 0.04035867378115654,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9421,
      "step": 14
    },
    {
      "epoch": 0.06878761822871883,
      "grad_norm": 0.038033198565244675,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9406,
      "step": 15
    },
    {
      "epoch": 0.07337345944396675,
      "grad_norm": 0.0361713282763958,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9437,
      "step": 16
    },
    {
      "epoch": 0.07795930065921468,
      "grad_norm": 0.038304127752780914,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9419,
      "step": 17
    },
    {
      "epoch": 0.0825451418744626,
      "grad_norm": 0.03976590558886528,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9435,
      "step": 18
    },
    {
      "epoch": 0.08713098308971051,
      "grad_norm": 0.039501603692770004,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9418,
      "step": 19
    },
    {
      "epoch": 0.09171682430495844,
      "grad_norm": 0.04031922668218613,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9415,
      "step": 20
    },
    {
      "epoch": 0.09630266552020636,
      "grad_norm": 0.04376734048128128,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.942,
      "step": 21
    },
    {
      "epoch": 0.10088850673545428,
      "grad_norm": 0.041407857090234756,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9435,
      "step": 22
    },
    {
      "epoch": 0.10547434795070221,
      "grad_norm": 0.04024423658847809,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9402,
      "step": 23
    },
    {
      "epoch": 0.11006018916595013,
      "grad_norm": 0.042554643005132675,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9423,
      "step": 24
    },
    {
      "epoch": 0.11464603038119806,
      "grad_norm": 0.04869154840707779,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.942,
      "step": 25
    },
    {
      "epoch": 0.11464603038119806,
      "eval_loss": 11.940805435180664,
      "eval_runtime": 3.1155,
      "eval_samples_per_second": 471.834,
      "eval_steps_per_second": 59.059,
      "step": 25
    },
    {
      "epoch": 0.11923187159644598,
      "grad_norm": 0.05349224433302879,
      "learning_rate": 5e-05,
      "loss": 11.9391,
      "step": 26
    },
    {
      "epoch": 0.12381771281169389,
      "grad_norm": 0.050973717123270035,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 11.9392,
      "step": 27
    },
    {
      "epoch": 0.1284035540269418,
      "grad_norm": 0.050512637943029404,
      "learning_rate": 4.347369038899744e-05,
      "loss": 11.9378,
      "step": 28
    },
    {
      "epoch": 0.13298939524218975,
      "grad_norm": 0.0520334467291832,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 11.941,
      "step": 29
    },
    {
      "epoch": 0.13757523645743766,
      "grad_norm": 0.055656593292951584,
      "learning_rate": 3.705904774487396e-05,
      "loss": 11.9406,
      "step": 30
    },
    {
      "epoch": 0.14216107767268557,
      "grad_norm": 0.053649820387363434,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.9397,
      "step": 31
    },
    {
      "epoch": 0.1467469188879335,
      "grad_norm": 0.05413060635328293,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9393,
      "step": 32
    },
    {
      "epoch": 0.15133276010318142,
      "grad_norm": 0.0558125339448452,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 11.9418,
      "step": 33
    },
    {
      "epoch": 0.15591860131842936,
      "grad_norm": 0.052829060703516006,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.9406,
      "step": 34
    },
    {
      "epoch": 0.16050444253367727,
      "grad_norm": 0.060385338962078094,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 11.9413,
      "step": 35
    },
    {
      "epoch": 0.1650902837489252,
      "grad_norm": 0.04723364859819412,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 11.942,
      "step": 36
    },
    {
      "epoch": 0.16967612496417311,
      "grad_norm": 0.054764941334724426,
      "learning_rate": 1.703270924499656e-05,
      "loss": 11.9409,
      "step": 37
    },
    {
      "epoch": 0.17426196617942102,
      "grad_norm": 0.05203568935394287,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9395,
      "step": 38
    },
    {
      "epoch": 0.17884780739466896,
      "grad_norm": 0.0577789843082428,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 11.9406,
      "step": 39
    },
    {
      "epoch": 0.18343364860991687,
      "grad_norm": 0.05892513692378998,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 11.9378,
      "step": 40
    },
    {
      "epoch": 0.1880194898251648,
      "grad_norm": 0.057550907135009766,
      "learning_rate": 8.426519384872733e-06,
      "loss": 11.9383,
      "step": 41
    },
    {
      "epoch": 0.19260533104041272,
      "grad_norm": 0.06069960817694664,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.9408,
      "step": 42
    },
    {
      "epoch": 0.19719117225566066,
      "grad_norm": 0.061215341091156006,
      "learning_rate": 5.156362923365588e-06,
      "loss": 11.9385,
      "step": 43
    },
    {
      "epoch": 0.20177701347090857,
      "grad_norm": 0.06457344442605972,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9388,
      "step": 44
    },
    {
      "epoch": 0.2063628546861565,
      "grad_norm": 0.05859246104955673,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.9378,
      "step": 45
    },
    {
      "epoch": 0.21094869590140441,
      "grad_norm": 0.05629947409033775,
      "learning_rate": 1.70370868554659e-06,
      "loss": 11.9402,
      "step": 46
    },
    {
      "epoch": 0.21553453711665232,
      "grad_norm": 0.053209468722343445,
      "learning_rate": 9.607359798384785e-07,
      "loss": 11.9402,
      "step": 47
    },
    {
      "epoch": 0.22012037833190026,
      "grad_norm": 0.06205746904015541,
      "learning_rate": 4.277569313094809e-07,
      "loss": 11.9398,
      "step": 48
    },
    {
      "epoch": 0.22470621954714817,
      "grad_norm": 0.0625690147280693,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.9395,
      "step": 49
    },
    {
      "epoch": 0.2292920607623961,
      "grad_norm": 0.054081086069345474,
      "learning_rate": 0.0,
      "loss": 11.9422,
      "step": 50
    },
    {
      "epoch": 0.2292920607623961,
      "eval_loss": 11.939474105834961,
      "eval_runtime": 3.1182,
      "eval_samples_per_second": 471.422,
      "eval_steps_per_second": 59.008,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}