{
  "best_metric": 0.1403578221797943,
  "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": 8.242918968200684,
      "learning_rate": 5e-05,
      "loss": 2.1715,
      "step": 1
    },
    {
      "epoch": 0.0033848106621535857,
      "eval_loss": 2.5066440105438232,
      "eval_runtime": 74.8616,
      "eval_samples_per_second": 26.582,
      "eval_steps_per_second": 3.326,
      "step": 1
    },
    {
      "epoch": 0.006769621324307171,
      "grad_norm": 5.20304012298584,
      "learning_rate": 0.0001,
      "loss": 2.0776,
      "step": 2
    },
    {
      "epoch": 0.010154431986460757,
      "grad_norm": 4.873104572296143,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.0696,
      "step": 3
    },
    {
      "epoch": 0.013539242648614343,
      "grad_norm": 4.473555088043213,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.3712,
      "step": 4
    },
    {
      "epoch": 0.01692405331076793,
      "grad_norm": 3.8778748512268066,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9133,
      "step": 5
    },
    {
      "epoch": 0.020308863972921514,
      "grad_norm": 2.1852025985717773,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3128,
      "step": 6
    },
    {
      "epoch": 0.0236936746350751,
      "grad_norm": 2.7190582752227783,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.6498,
      "step": 7
    },
    {
      "epoch": 0.027078485297228685,
      "grad_norm": 2.0675923824310303,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3471,
      "step": 8
    },
    {
      "epoch": 0.030463295959382273,
      "grad_norm": 1.7876297235488892,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.1066,
      "step": 9
    },
    {
      "epoch": 0.03384810662153586,
      "grad_norm": 1.5072264671325684,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0825,
      "step": 10
    },
    {
      "epoch": 0.037232917283689444,
      "grad_norm": 1.4028645753860474,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1544,
      "step": 11
    },
    {
      "epoch": 0.04061772794584303,
      "grad_norm": 1.524824619293213,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0857,
      "step": 12
    },
    {
      "epoch": 0.04400253860799661,
      "grad_norm": 2.9816486835479736,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.7337,
      "step": 13
    },
    {
      "epoch": 0.0473873492701502,
      "grad_norm": 2.2506439685821533,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5646,
      "step": 14
    },
    {
      "epoch": 0.05077215993230379,
      "grad_norm": 1.8148720264434814,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.2973,
      "step": 15
    },
    {
      "epoch": 0.05415697059445737,
      "grad_norm": 1.5184000730514526,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.3993,
      "step": 16
    },
    {
      "epoch": 0.057541781256610955,
      "grad_norm": 0.9413993954658508,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1796,
      "step": 17
    },
    {
      "epoch": 0.060926591918764546,
      "grad_norm": 0.8061498999595642,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0982,
      "step": 18
    },
    {
      "epoch": 0.06431140258091814,
      "grad_norm": 1.446628451347351,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.2523,
      "step": 19
    },
    {
      "epoch": 0.06769621324307172,
      "grad_norm": 1.5441877841949463,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3505,
      "step": 20
    },
    {
      "epoch": 0.0710810239052253,
      "grad_norm": 0.8777207732200623,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0549,
      "step": 21
    },
    {
      "epoch": 0.07446583456737889,
      "grad_norm": 0.7810785174369812,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0478,
      "step": 22
    },
    {
      "epoch": 0.07785064522953247,
      "grad_norm": 2.0973148345947266,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0503,
      "step": 23
    },
    {
      "epoch": 0.08123545589168606,
      "grad_norm": 1.515192985534668,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0389,
      "step": 24
    },
    {
      "epoch": 0.08462026655383964,
      "grad_norm": 0.3591516315937042,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.011,
      "step": 25
    },
    {
      "epoch": 0.08462026655383964,
      "eval_loss": 0.2075149118900299,
      "eval_runtime": 75.129,
      "eval_samples_per_second": 26.488,
      "eval_steps_per_second": 3.314,
      "step": 25
    },
    {
      "epoch": 0.08800507721599322,
      "grad_norm": 1.6778769493103027,
      "learning_rate": 5e-05,
      "loss": 0.7129,
      "step": 26
    },
    {
      "epoch": 0.09138988787814682,
      "grad_norm": 1.6447440385818481,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.4329,
      "step": 27
    },
    {
      "epoch": 0.0947746985403004,
      "grad_norm": 1.28570556640625,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.2261,
      "step": 28
    },
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 1.2766765356063843,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.2562,
      "step": 29
    },
    {
      "epoch": 0.10154431986460757,
      "grad_norm": 0.8895098567008972,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.1062,
      "step": 30
    },
    {
      "epoch": 0.10492913052676116,
      "grad_norm": 0.8585551381111145,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0615,
      "step": 31
    },
    {
      "epoch": 0.10831394118891474,
      "grad_norm": 1.306959867477417,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2072,
      "step": 32
    },
    {
      "epoch": 0.11169875185106833,
      "grad_norm": 0.9922142028808594,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.15,
      "step": 33
    },
    {
      "epoch": 0.11508356251322191,
      "grad_norm": 0.5465759634971619,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0185,
      "step": 34
    },
    {
      "epoch": 0.11846837317537551,
      "grad_norm": 0.5579932928085327,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0183,
      "step": 35
    },
    {
      "epoch": 0.12185318383752909,
      "grad_norm": 0.8082761764526367,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0314,
      "step": 36
    },
    {
      "epoch": 0.12523799449968268,
      "grad_norm": 0.8889264464378357,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0274,
      "step": 37
    },
    {
      "epoch": 0.12862280516183627,
      "grad_norm": 1.2212693691253662,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6514,
      "step": 38
    },
    {
      "epoch": 0.13200761582398984,
      "grad_norm": 0.7712531685829163,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.3511,
      "step": 39
    },
    {
      "epoch": 0.13539242648614344,
      "grad_norm": 0.6609764695167542,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1331,
      "step": 40
    },
    {
      "epoch": 0.138777237148297,
      "grad_norm": 0.6676031351089478,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.1511,
      "step": 41
    },
    {
      "epoch": 0.1421620478104506,
      "grad_norm": 0.6073664426803589,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0924,
      "step": 42
    },
    {
      "epoch": 0.14554685847260418,
      "grad_norm": 0.7909665107727051,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0403,
      "step": 43
    },
    {
      "epoch": 0.14893166913475778,
      "grad_norm": 0.770443320274353,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1223,
      "step": 44
    },
    {
      "epoch": 0.15231647979691135,
      "grad_norm": 1.2650684118270874,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.2309,
      "step": 45
    },
    {
      "epoch": 0.15570129045906494,
      "grad_norm": 0.41604822874069214,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.012,
      "step": 46
    },
    {
      "epoch": 0.15908610112121854,
      "grad_norm": 0.7316561937332153,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0359,
      "step": 47
    },
    {
      "epoch": 0.1624709117833721,
      "grad_norm": 0.4568137526512146,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0163,
      "step": 48
    },
    {
      "epoch": 0.1658557224455257,
      "grad_norm": 0.2808038890361786,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0097,
      "step": 49
    },
    {
      "epoch": 0.16924053310767928,
      "grad_norm": 0.4326798617839813,
      "learning_rate": 0.0,
      "loss": 0.013,
      "step": 50
    },
    {
      "epoch": 0.16924053310767928,
      "eval_loss": 0.1403578221797943,
      "eval_runtime": 75.1826,
      "eval_samples_per_second": 26.469,
      "eval_steps_per_second": 3.312,
      "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": 2.229252309123072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}