{
  "best_metric": 0.0014108235482126474,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.16924053310767928,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033848106621535857,
      "grad_norm": 2.287355899810791,
      "learning_rate": 5e-05,
      "loss": 1.1034,
      "step": 1
    },
    {
      "epoch": 0.0033848106621535857,
      "eval_loss": 1.1992753744125366,
      "eval_runtime": 57.3646,
      "eval_samples_per_second": 34.69,
      "eval_steps_per_second": 4.341,
      "step": 1
    },
    {
      "epoch": 0.006769621324307171,
      "grad_norm": 2.4537482261657715,
      "learning_rate": 0.0001,
      "loss": 1.1493,
      "step": 2
    },
    {
      "epoch": 0.010154431986460757,
      "grad_norm": 2.4352898597717285,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.0508,
      "step": 3
    },
    {
      "epoch": 0.013539242648614343,
      "grad_norm": 1.6917345523834229,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.686,
      "step": 4
    },
    {
      "epoch": 0.01692405331076793,
      "grad_norm": 1.4392510652542114,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5158,
      "step": 5
    },
    {
      "epoch": 0.020308863972921514,
      "grad_norm": 1.1602476835250854,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2749,
      "step": 6
    },
    {
      "epoch": 0.0236936746350751,
      "grad_norm": 0.5011272430419922,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.1216,
      "step": 7
    },
    {
      "epoch": 0.027078485297228685,
      "grad_norm": 0.6883003115653992,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1001,
      "step": 8
    },
    {
      "epoch": 0.030463295959382273,
      "grad_norm": 0.7780411839485168,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0692,
      "step": 9
    },
    {
      "epoch": 0.03384810662153586,
      "grad_norm": 0.2887956202030182,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0259,
      "step": 10
    },
    {
      "epoch": 0.037232917283689444,
      "grad_norm": 0.11445723474025726,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0071,
      "step": 11
    },
    {
      "epoch": 0.04061772794584303,
      "grad_norm": 0.1323813498020172,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.006,
      "step": 12
    },
    {
      "epoch": 0.04400253860799661,
      "grad_norm": 1.0943286418914795,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0234,
      "step": 13
    },
    {
      "epoch": 0.0473873492701502,
      "grad_norm": 0.382942795753479,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.009,
      "step": 14
    },
    {
      "epoch": 0.05077215993230379,
      "grad_norm": 0.435187429189682,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0097,
      "step": 15
    },
    {
      "epoch": 0.05415697059445737,
      "grad_norm": 0.22337676584720612,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.004,
      "step": 16
    },
    {
      "epoch": 0.057541781256610955,
      "grad_norm": 0.40100961923599243,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0052,
      "step": 17
    },
    {
      "epoch": 0.060926591918764546,
      "grad_norm": 0.12107855081558228,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0029,
      "step": 18
    },
    {
      "epoch": 0.06431140258091814,
      "grad_norm": 0.5011308193206787,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0059,
      "step": 19
    },
    {
      "epoch": 0.06769621324307172,
      "grad_norm": 0.06344273686408997,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0021,
      "step": 20
    },
    {
      "epoch": 0.0710810239052253,
      "grad_norm": 0.10359528660774231,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0013,
      "step": 21
    },
    {
      "epoch": 0.07446583456737889,
      "grad_norm": 0.05229415372014046,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0012,
      "step": 22
    },
    {
      "epoch": 0.07785064522953247,
      "grad_norm": 0.06729074567556381,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0011,
      "step": 23
    },
    {
      "epoch": 0.08123545589168606,
      "grad_norm": 0.02676481194794178,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0009,
      "step": 24
    },
    {
      "epoch": 0.08462026655383964,
      "grad_norm": 0.16672037541866302,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0022,
      "step": 25
    },
    {
      "epoch": 0.08462026655383964,
      "eval_loss": 0.003064053598791361,
      "eval_runtime": 57.3673,
      "eval_samples_per_second": 34.689,
      "eval_steps_per_second": 4.34,
      "step": 25
    },
    {
      "epoch": 0.08800507721599322,
      "grad_norm": 1.4910016059875488,
      "learning_rate": 5e-05,
      "loss": 0.0228,
      "step": 26
    },
    {
      "epoch": 0.09138988787814682,
      "grad_norm": 0.24254511296749115,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0037,
      "step": 27
    },
    {
      "epoch": 0.0947746985403004,
      "grad_norm": 0.2668854892253876,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0015,
      "step": 28
    },
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 0.5330218076705933,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0019,
      "step": 29
    },
    {
      "epoch": 0.10154431986460757,
      "grad_norm": 0.03539638966321945,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0012,
      "step": 30
    },
    {
      "epoch": 0.10492913052676116,
      "grad_norm": 0.034347571432590485,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0012,
      "step": 31
    },
    {
      "epoch": 0.10831394118891474,
      "grad_norm": 0.054929472506046295,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.001,
      "step": 32
    },
    {
      "epoch": 0.11169875185106833,
      "grad_norm": 0.197361558675766,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0021,
      "step": 33
    },
    {
      "epoch": 0.11508356251322191,
      "grad_norm": 0.18690542876720428,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.004,
      "step": 34
    },
    {
      "epoch": 0.11846837317537551,
      "grad_norm": 0.010866144672036171,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0006,
      "step": 35
    },
    {
      "epoch": 0.12185318383752909,
      "grad_norm": 0.037227921187877655,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0008,
      "step": 36
    },
    {
      "epoch": 0.12523799449968268,
      "grad_norm": 0.026730114594101906,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0015,
      "step": 37
    },
    {
      "epoch": 0.12862280516183627,
      "grad_norm": 0.09857242554426193,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0032,
      "step": 38
    },
    {
      "epoch": 0.13200761582398984,
      "grad_norm": 0.08650778979063034,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0017,
      "step": 39
    },
    {
      "epoch": 0.13539242648614344,
      "grad_norm": 0.02394554391503334,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0013,
      "step": 40
    },
    {
      "epoch": 0.138777237148297,
      "grad_norm": 0.3927086889743805,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0048,
      "step": 41
    },
    {
      "epoch": 0.1421620478104506,
      "grad_norm": 0.02811684086918831,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0013,
      "step": 42
    },
    {
      "epoch": 0.14554685847260418,
      "grad_norm": 0.04668286442756653,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0011,
      "step": 43
    },
    {
      "epoch": 0.14893166913475778,
      "grad_norm": 0.05839909240603447,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0014,
      "step": 44
    },
    {
      "epoch": 0.15231647979691135,
      "grad_norm": 0.06195997819304466,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0012,
      "step": 45
    },
    {
      "epoch": 0.15570129045906494,
      "grad_norm": 0.02771010622382164,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0011,
      "step": 46
    },
    {
      "epoch": 0.15908610112121854,
      "grad_norm": 0.02765018679201603,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0006,
      "step": 47
    },
    {
      "epoch": 0.1624709117833721,
      "grad_norm": 0.028453974053263664,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0009,
      "step": 48
    },
    {
      "epoch": 0.1658557224455257,
      "grad_norm": 0.0173852127045393,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0012,
      "step": 49
    },
    {
      "epoch": 0.16924053310767928,
      "grad_norm": 0.02612384408712387,
      "learning_rate": 0.0,
      "loss": 0.001,
      "step": 50
    },
    {
      "epoch": 0.16924053310767928,
      "eval_loss": 0.0014108235482126474,
      "eval_runtime": 57.3651,
      "eval_samples_per_second": 34.69,
      "eval_steps_per_second": 4.341,
      "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": 5.305284264198144e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}