{
  "best_metric": 0.29708796739578247,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.08255082034877721,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016510164069755444,
      "grad_norm": 3.0247745513916016,
      "learning_rate": 5e-05,
      "loss": 0.4272,
      "step": 1
    },
    {
      "epoch": 0.0016510164069755444,
      "eval_loss": 0.5801298022270203,
      "eval_runtime": 152.3421,
      "eval_samples_per_second": 26.788,
      "eval_steps_per_second": 3.354,
      "step": 1
    },
    {
      "epoch": 0.0033020328139510887,
      "grad_norm": 0.26526594161987305,
      "learning_rate": 0.0001,
      "loss": 0.5465,
      "step": 2
    },
    {
      "epoch": 0.004953049220926633,
      "grad_norm": 0.2640111446380615,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.5798,
      "step": 3
    },
    {
      "epoch": 0.006604065627902177,
      "grad_norm": 0.2363673597574234,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.5595,
      "step": 4
    },
    {
      "epoch": 0.008255082034877721,
      "grad_norm": 0.211054265499115,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5095,
      "step": 5
    },
    {
      "epoch": 0.009906098441853266,
      "grad_norm": 0.18822599947452545,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5189,
      "step": 6
    },
    {
      "epoch": 0.01155711484882881,
      "grad_norm": 0.20426109433174133,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5167,
      "step": 7
    },
    {
      "epoch": 0.013208131255804355,
      "grad_norm": 0.2221483439207077,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4754,
      "step": 8
    },
    {
      "epoch": 0.014859147662779898,
      "grad_norm": 0.18756835162639618,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.4448,
      "step": 9
    },
    {
      "epoch": 0.016510164069755442,
      "grad_norm": 0.16543976962566376,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.416,
      "step": 10
    },
    {
      "epoch": 0.018161180476730987,
      "grad_norm": 0.7194027900695801,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2621,
      "step": 11
    },
    {
      "epoch": 0.019812196883706532,
      "grad_norm": 0.17668159306049347,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1983,
      "step": 12
    },
    {
      "epoch": 0.021463213290682077,
      "grad_norm": 0.1292767971754074,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.2998,
      "step": 13
    },
    {
      "epoch": 0.02311422969765762,
      "grad_norm": 0.15346571803092957,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3568,
      "step": 14
    },
    {
      "epoch": 0.024765246104633164,
      "grad_norm": 0.1705729067325592,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.3867,
      "step": 15
    },
    {
      "epoch": 0.02641626251160871,
      "grad_norm": 0.1557266265153885,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4098,
      "step": 16
    },
    {
      "epoch": 0.028067278918584255,
      "grad_norm": 0.13209468126296997,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4109,
      "step": 17
    },
    {
      "epoch": 0.029718295325559797,
      "grad_norm": 0.11559902131557465,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3883,
      "step": 18
    },
    {
      "epoch": 0.03136931173253534,
      "grad_norm": 0.09431163221597672,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.3791,
      "step": 19
    },
    {
      "epoch": 0.033020328139510884,
      "grad_norm": 0.09266266971826553,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3857,
      "step": 20
    },
    {
      "epoch": 0.03467134454648643,
      "grad_norm": 0.10236460715532303,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3849,
      "step": 21
    },
    {
      "epoch": 0.036322360953461974,
      "grad_norm": 0.10628839582204819,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3592,
      "step": 22
    },
    {
      "epoch": 0.03797337736043752,
      "grad_norm": 0.1099647805094719,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.2481,
      "step": 23
    },
    {
      "epoch": 0.039624393767413064,
      "grad_norm": 0.10537803918123245,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1525,
      "step": 24
    },
    {
      "epoch": 0.041275410174388606,
      "grad_norm": 0.16766606271266937,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.2986,
      "step": 25
    },
    {
      "epoch": 0.041275410174388606,
      "eval_loss": 0.3243732452392578,
      "eval_runtime": 152.2878,
      "eval_samples_per_second": 26.798,
      "eval_steps_per_second": 3.355,
      "step": 25
    },
    {
      "epoch": 0.042926426581364155,
      "grad_norm": 0.10008738189935684,
      "learning_rate": 5e-05,
      "loss": 0.2265,
      "step": 26
    },
    {
      "epoch": 0.0445774429883397,
      "grad_norm": 0.11355409026145935,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.3318,
      "step": 27
    },
    {
      "epoch": 0.04622845939531524,
      "grad_norm": 0.09922956675291061,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.3443,
      "step": 28
    },
    {
      "epoch": 0.04787947580229079,
      "grad_norm": 0.08054020255804062,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.3249,
      "step": 29
    },
    {
      "epoch": 0.04953049220926633,
      "grad_norm": 0.08450499176979065,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.3489,
      "step": 30
    },
    {
      "epoch": 0.05118150861624187,
      "grad_norm": 0.09624389559030533,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.3536,
      "step": 31
    },
    {
      "epoch": 0.05283252502321742,
      "grad_norm": 0.10854283720254898,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3573,
      "step": 32
    },
    {
      "epoch": 0.05448354143019296,
      "grad_norm": 0.09736617654561996,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.3333,
      "step": 33
    },
    {
      "epoch": 0.05613455783716851,
      "grad_norm": 0.0933280810713768,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.329,
      "step": 34
    },
    {
      "epoch": 0.05778557424414405,
      "grad_norm": 0.10208204388618469,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.2832,
      "step": 35
    },
    {
      "epoch": 0.05943659065111959,
      "grad_norm": 0.08625288307666779,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1621,
      "step": 36
    },
    {
      "epoch": 0.06108760705809514,
      "grad_norm": 0.08310309797525406,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.1118,
      "step": 37
    },
    {
      "epoch": 0.06273862346507068,
      "grad_norm": 0.08370844274759293,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2181,
      "step": 38
    },
    {
      "epoch": 0.06438963987204623,
      "grad_norm": 0.08878277242183685,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.2772,
      "step": 39
    },
    {
      "epoch": 0.06604065627902177,
      "grad_norm": 0.09928658604621887,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.3036,
      "step": 40
    },
    {
      "epoch": 0.06769167268599732,
      "grad_norm": 0.08427450805902481,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.3139,
      "step": 41
    },
    {
      "epoch": 0.06934268909297286,
      "grad_norm": 0.08152101188898087,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3079,
      "step": 42
    },
    {
      "epoch": 0.0709937054999484,
      "grad_norm": 0.09090898931026459,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.3204,
      "step": 43
    },
    {
      "epoch": 0.07264472190692395,
      "grad_norm": 0.08596403151750565,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3383,
      "step": 44
    },
    {
      "epoch": 0.07429573831389949,
      "grad_norm": 0.07474559545516968,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.3143,
      "step": 45
    },
    {
      "epoch": 0.07594675472087505,
      "grad_norm": 0.07625479996204376,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.3256,
      "step": 46
    },
    {
      "epoch": 0.07759777112785059,
      "grad_norm": 0.08517799526453018,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.3103,
      "step": 47
    },
    {
      "epoch": 0.07924878753482613,
      "grad_norm": 0.08896566182374954,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.2409,
      "step": 48
    },
    {
      "epoch": 0.08089980394180167,
      "grad_norm": 0.07853224873542786,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.1056,
      "step": 49
    },
    {
      "epoch": 0.08255082034877721,
      "grad_norm": 0.21440893411636353,
      "learning_rate": 0.0,
      "loss": 0.3215,
      "step": 50
    },
    {
      "epoch": 0.08255082034877721,
      "eval_loss": 0.29708796739578247,
      "eval_runtime": 152.8033,
      "eval_samples_per_second": 26.708,
      "eval_steps_per_second": 3.344,
      "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": 6.299421435609743e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}