{
  "best_metric": 0.8101484775543213,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6762468300929839,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013524936601859678,
      "grad_norm": 64.65589904785156,
      "learning_rate": 5e-05,
      "loss": 8.1779,
      "step": 1
    },
    {
      "epoch": 0.013524936601859678,
      "eval_loss": 7.860408306121826,
      "eval_runtime": 24.8589,
      "eval_samples_per_second": 20.073,
      "eval_steps_per_second": 2.534,
      "step": 1
    },
    {
      "epoch": 0.027049873203719356,
      "grad_norm": 67.79522705078125,
      "learning_rate": 0.0001,
      "loss": 8.0079,
      "step": 2
    },
    {
      "epoch": 0.04057480980557904,
      "grad_norm": 71.02486419677734,
      "learning_rate": 9.989294616193017e-05,
      "loss": 7.6616,
      "step": 3
    },
    {
      "epoch": 0.05409974640743871,
      "grad_norm": 87.24286651611328,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.8381,
      "step": 4
    },
    {
      "epoch": 0.0676246830092984,
      "grad_norm": 99.07132720947266,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.6078,
      "step": 5
    },
    {
      "epoch": 0.08114961961115807,
      "grad_norm": 115.70046997070312,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.1373,
      "step": 6
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 101.22488403320312,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.6829,
      "step": 7
    },
    {
      "epoch": 0.10819949281487742,
      "grad_norm": 73.90310668945312,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6014,
      "step": 8
    },
    {
      "epoch": 0.12172442941673711,
      "grad_norm": 44.66142272949219,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.1215,
      "step": 9
    },
    {
      "epoch": 0.1352493660185968,
      "grad_norm": 43.206581115722656,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9301,
      "step": 10
    },
    {
      "epoch": 0.14877430262045646,
      "grad_norm": 42.45280456542969,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.9033,
      "step": 11
    },
    {
      "epoch": 0.16229923922231615,
      "grad_norm": 38.4478759765625,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.8445,
      "step": 12
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 38.29458236694336,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.9356,
      "step": 13
    },
    {
      "epoch": 0.1893491124260355,
      "grad_norm": 28.304309844970703,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.875,
      "step": 14
    },
    {
      "epoch": 0.2028740490278952,
      "grad_norm": 33.775325775146484,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8547,
      "step": 15
    },
    {
      "epoch": 0.21639898562975485,
      "grad_norm": 45.00499725341797,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8752,
      "step": 16
    },
    {
      "epoch": 0.22992392223161454,
      "grad_norm": 39.23467254638672,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8878,
      "step": 17
    },
    {
      "epoch": 0.24344885883347422,
      "grad_norm": 32.94371795654297,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8384,
      "step": 18
    },
    {
      "epoch": 0.2569737954353339,
      "grad_norm": 30.189590454101562,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8236,
      "step": 19
    },
    {
      "epoch": 0.2704987320371936,
      "grad_norm": 13.199180603027344,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8041,
      "step": 20
    },
    {
      "epoch": 0.28402366863905326,
      "grad_norm": 19.364147186279297,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8324,
      "step": 21
    },
    {
      "epoch": 0.2975486052409129,
      "grad_norm": 18.093721389770508,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8108,
      "step": 22
    },
    {
      "epoch": 0.31107354184277264,
      "grad_norm": 22.71017074584961,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8244,
      "step": 23
    },
    {
      "epoch": 0.3245984784446323,
      "grad_norm": 19.10126304626465,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8027,
      "step": 24
    },
    {
      "epoch": 0.33812341504649196,
      "grad_norm": 29.179006576538086,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.814,
      "step": 25
    },
    {
      "epoch": 0.33812341504649196,
      "eval_loss": 0.8287287354469299,
      "eval_runtime": 50.1993,
      "eval_samples_per_second": 9.94,
      "eval_steps_per_second": 1.255,
      "step": 25
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 22.157114028930664,
      "learning_rate": 5e-05,
      "loss": 0.8506,
      "step": 26
    },
    {
      "epoch": 0.36517328825021134,
      "grad_norm": 20.86341667175293,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.8551,
      "step": 27
    },
    {
      "epoch": 0.378698224852071,
      "grad_norm": 16.98979377746582,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.8119,
      "step": 28
    },
    {
      "epoch": 0.39222316145393066,
      "grad_norm": 23.05814552307129,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.8349,
      "step": 29
    },
    {
      "epoch": 0.4057480980557904,
      "grad_norm": 11.545186996459961,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8151,
      "step": 30
    },
    {
      "epoch": 0.41927303465765003,
      "grad_norm": 15.064045906066895,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.815,
      "step": 31
    },
    {
      "epoch": 0.4327979712595097,
      "grad_norm": 7.394914627075195,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8191,
      "step": 32
    },
    {
      "epoch": 0.4463229078613694,
      "grad_norm": 14.583250045776367,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.8224,
      "step": 33
    },
    {
      "epoch": 0.45984784446322907,
      "grad_norm": 16.12276268005371,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8024,
      "step": 34
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 7.712066173553467,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.8027,
      "step": 35
    },
    {
      "epoch": 0.48689771766694845,
      "grad_norm": 10.313910484313965,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8061,
      "step": 36
    },
    {
      "epoch": 0.5004226542688082,
      "grad_norm": 11.785128593444824,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8099,
      "step": 37
    },
    {
      "epoch": 0.5139475908706678,
      "grad_norm": 14.758973121643066,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.853,
      "step": 38
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 16.421119689941406,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.8459,
      "step": 39
    },
    {
      "epoch": 0.5409974640743872,
      "grad_norm": 14.737407684326172,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.812,
      "step": 40
    },
    {
      "epoch": 0.5545224006762468,
      "grad_norm": 20.14451026916504,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8267,
      "step": 41
    },
    {
      "epoch": 0.5680473372781065,
      "grad_norm": 21.863866806030273,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8285,
      "step": 42
    },
    {
      "epoch": 0.5815722738799662,
      "grad_norm": 11.37204360961914,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.8141,
      "step": 43
    },
    {
      "epoch": 0.5950972104818258,
      "grad_norm": 5.559212684631348,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7995,
      "step": 44
    },
    {
      "epoch": 0.6086221470836856,
      "grad_norm": 10.355339050292969,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.796,
      "step": 45
    },
    {
      "epoch": 0.6221470836855453,
      "grad_norm": 10.827974319458008,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.8014,
      "step": 46
    },
    {
      "epoch": 0.6356720202874049,
      "grad_norm": 11.881269454956055,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.8132,
      "step": 47
    },
    {
      "epoch": 0.6491969568892646,
      "grad_norm": 13.85914421081543,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8165,
      "step": 48
    },
    {
      "epoch": 0.6627218934911243,
      "grad_norm": 16.662988662719727,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.8126,
      "step": 49
    },
    {
      "epoch": 0.6762468300929839,
      "grad_norm": 9.382196426391602,
      "learning_rate": 0.0,
      "loss": 0.8089,
      "step": 50
    },
    {
      "epoch": 0.6762468300929839,
      "eval_loss": 0.8101484775543213,
      "eval_runtime": 33.7248,
      "eval_samples_per_second": 14.796,
      "eval_steps_per_second": 1.868,
      "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": 5.262429617389568e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}