{
  "best_metric": 0.0005636036512441933,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.007326141504423158,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014652283008846317,
      "grad_norm": 67.46258544921875,
      "learning_rate": 5e-05,
      "loss": 7.3346,
      "step": 1
    },
    {
      "epoch": 0.00014652283008846317,
      "eval_loss": 7.334836959838867,
      "eval_runtime": 2450.429,
      "eval_samples_per_second": 18.763,
      "eval_steps_per_second": 2.346,
      "step": 1
    },
    {
      "epoch": 0.00029304566017692633,
      "grad_norm": 67.42963409423828,
      "learning_rate": 0.0001,
      "loss": 7.3346,
      "step": 2
    },
    {
      "epoch": 0.0004395684902653895,
      "grad_norm": 17.986305236816406,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.2234,
      "step": 3
    },
    {
      "epoch": 0.0005860913203538527,
      "grad_norm": 10.093182563781738,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9459,
      "step": 4
    },
    {
      "epoch": 0.0007326141504423158,
      "grad_norm": 4.0528645515441895,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2877,
      "step": 5
    },
    {
      "epoch": 0.000879136980530779,
      "grad_norm": 1.00792396068573,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0218,
      "step": 6
    },
    {
      "epoch": 0.001025659810619242,
      "grad_norm": 0.8242140412330627,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0026,
      "step": 7
    },
    {
      "epoch": 0.0011721826407077053,
      "grad_norm": 0.01713043637573719,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0002,
      "step": 8
    },
    {
      "epoch": 0.0013187054707961684,
      "grad_norm": 0.0027765310369431973,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0014652283008846315,
      "grad_norm": 0.005665022414177656,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0016117511309730948,
      "grad_norm": 0.017976634204387665,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.001758273961061558,
      "grad_norm": 0.006979241501539946,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.001904796791150021,
      "grad_norm": 0.0015923851169645786,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.002051319621238484,
      "grad_norm": 0.0010537989437580109,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0021978424513269474,
      "grad_norm": 0.0012975798454135656,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0023443652814154107,
      "grad_norm": 0.0013601743848994374,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0024908881115038735,
      "grad_norm": 0.0014510821783915162,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.002637410941592337,
      "grad_norm": 0.0015000648563727736,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0027839337716808,
      "grad_norm": 0.0012648840202018619,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.002930456601769263,
      "grad_norm": 0.0009284365805797279,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0030769794318577263,
      "grad_norm": 0.0007029483676888049,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0032235022619461896,
      "grad_norm": 0.0004989892477169633,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0033700250920346525,
      "grad_norm": 0.0003535033611115068,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.003516547922123116,
      "grad_norm": 0.0002854061604011804,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.003663070752211579,
      "grad_norm": 0.0002517289249226451,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.003663070752211579,
      "eval_loss": 0.0005636036512441933,
      "eval_runtime": 2444.0569,
      "eval_samples_per_second": 18.812,
      "eval_steps_per_second": 2.352,
      "step": 25
    },
    {
      "epoch": 0.003809593582300042,
      "grad_norm": 0.00020020699594169855,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.003956116412388505,
      "grad_norm": 0.0001780200400389731,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004102639242476968,
      "grad_norm": 0.0001607375015737489,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.004249162072565432,
      "grad_norm": 0.00013710453640669584,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.004395684902653895,
      "grad_norm": 0.0001292604283662513,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.004542207732742358,
      "grad_norm": 0.00011346691462676972,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.004688730562830821,
      "grad_norm": 0.00010570303857093677,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.004835253392919284,
      "grad_norm": 0.00010658427345333621,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.004981776223007747,
      "grad_norm": 9.98374744085595e-05,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.005128299053096211,
      "grad_norm": 9.281656821258366e-05,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.005274821883184674,
      "grad_norm": 9.025217150337994e-05,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0054213447132731366,
      "grad_norm": 8.29451673780568e-05,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0055678675433616,
      "grad_norm": 8.419723599217832e-05,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.005714390373450063,
      "grad_norm": 7.673307118238881e-05,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.005860913203538526,
      "grad_norm": 8.379003702430055e-05,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00600743603362699,
      "grad_norm": 7.67179299145937e-05,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.006153958863715453,
      "grad_norm": 6.99859592714347e-05,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0063004816938039155,
      "grad_norm": 7.247132452903315e-05,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.006447004523892379,
      "grad_norm": 7.783375622238964e-05,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.006593527353980842,
      "grad_norm": 7.111630111467093e-05,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.006740050184069305,
      "grad_norm": 7.533140160376206e-05,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.006886573014157769,
      "grad_norm": 6.724232662236318e-05,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.007033095844246232,
      "grad_norm": 7.709606143180281e-05,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0071796186743346944,
      "grad_norm": 7.161575194913894e-05,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.007326141504423158,
      "grad_norm": 7.662274583708495e-05,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.007326141504423158,
      "eval_loss": 0.0005830689915455878,
      "eval_runtime": 2447.872,
      "eval_samples_per_second": 18.783,
      "eval_steps_per_second": 2.348,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.631381723512832e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}