{
  "best_metric": 2.0883843898773193,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1532567049808429,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030651340996168583,
      "grad_norm": 27.896610260009766,
      "learning_rate": 5e-05,
      "loss": 1.8825,
      "step": 1
    },
    {
      "epoch": 0.0030651340996168583,
      "eval_loss": 2.378786563873291,
      "eval_runtime": 64.153,
      "eval_samples_per_second": 34.262,
      "eval_steps_per_second": 4.287,
      "step": 1
    },
    {
      "epoch": 0.006130268199233717,
      "grad_norm": 32.84800720214844,
      "learning_rate": 0.0001,
      "loss": 2.1452,
      "step": 2
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 25.192340850830078,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.2998,
      "step": 3
    },
    {
      "epoch": 0.012260536398467433,
      "grad_norm": 15.766855239868164,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.2404,
      "step": 4
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 14.772031784057617,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.1976,
      "step": 5
    },
    {
      "epoch": 0.01839080459770115,
      "grad_norm": 14.457837104797363,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1336,
      "step": 6
    },
    {
      "epoch": 0.021455938697318006,
      "grad_norm": 13.174428939819336,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.1395,
      "step": 7
    },
    {
      "epoch": 0.024521072796934867,
      "grad_norm": 9.743951797485352,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1148,
      "step": 8
    },
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 10.328970909118652,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.116,
      "step": 9
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 10.842561721801758,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2137,
      "step": 10
    },
    {
      "epoch": 0.03371647509578544,
      "grad_norm": 12.265542030334473,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.2578,
      "step": 11
    },
    {
      "epoch": 0.0367816091954023,
      "grad_norm": 15.659526824951172,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.178,
      "step": 12
    },
    {
      "epoch": 0.03984674329501916,
      "grad_norm": 21.36080551147461,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.0713,
      "step": 13
    },
    {
      "epoch": 0.04291187739463601,
      "grad_norm": 29.808998107910156,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9459,
      "step": 14
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 15.340879440307617,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.0594,
      "step": 15
    },
    {
      "epoch": 0.04904214559386973,
      "grad_norm": 10.302526473999023,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.2324,
      "step": 16
    },
    {
      "epoch": 0.05210727969348659,
      "grad_norm": 8.83031940460205,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.1758,
      "step": 17
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 9.309374809265137,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.1735,
      "step": 18
    },
    {
      "epoch": 0.05823754789272031,
      "grad_norm": 11.40832233428955,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.0792,
      "step": 19
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 10.577889442443848,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1069,
      "step": 20
    },
    {
      "epoch": 0.06436781609195402,
      "grad_norm": 10.584429740905762,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.1862,
      "step": 21
    },
    {
      "epoch": 0.06743295019157088,
      "grad_norm": 11.981637001037598,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.1701,
      "step": 22
    },
    {
      "epoch": 0.07049808429118774,
      "grad_norm": 10.353193283081055,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.1409,
      "step": 23
    },
    {
      "epoch": 0.0735632183908046,
      "grad_norm": 11.31971263885498,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.1658,
      "step": 24
    },
    {
      "epoch": 0.07662835249042145,
      "grad_norm": 31.334794998168945,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.2213,
      "step": 25
    },
    {
      "epoch": 0.07662835249042145,
      "eval_loss": 2.11344051361084,
      "eval_runtime": 64.1924,
      "eval_samples_per_second": 34.241,
      "eval_steps_per_second": 4.284,
      "step": 25
    },
    {
      "epoch": 0.07969348659003832,
      "grad_norm": 10.44955062866211,
      "learning_rate": 5e-05,
      "loss": 1.7908,
      "step": 26
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 12.578252792358398,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.9414,
      "step": 27
    },
    {
      "epoch": 0.08582375478927202,
      "grad_norm": 9.608701705932617,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.0924,
      "step": 28
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 7.790093421936035,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.2228,
      "step": 29
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 7.69633674621582,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.1789,
      "step": 30
    },
    {
      "epoch": 0.0950191570881226,
      "grad_norm": 7.641820430755615,
      "learning_rate": 3.392802673484193e-05,
      "loss": 2.0621,
      "step": 31
    },
    {
      "epoch": 0.09808429118773947,
      "grad_norm": 8.215332984924316,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0805,
      "step": 32
    },
    {
      "epoch": 0.10114942528735632,
      "grad_norm": 9.230628967285156,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 2.1271,
      "step": 33
    },
    {
      "epoch": 0.10421455938697317,
      "grad_norm": 9.802064895629883,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.095,
      "step": 34
    },
    {
      "epoch": 0.10727969348659004,
      "grad_norm": 10.70319652557373,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 2.1541,
      "step": 35
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 11.505803108215332,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 2.1866,
      "step": 36
    },
    {
      "epoch": 0.11340996168582375,
      "grad_norm": 13.376690864562988,
      "learning_rate": 1.703270924499656e-05,
      "loss": 2.0843,
      "step": 37
    },
    {
      "epoch": 0.11647509578544062,
      "grad_norm": 17.37229347229004,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0862,
      "step": 38
    },
    {
      "epoch": 0.11954022988505747,
      "grad_norm": 5.753267288208008,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.8831,
      "step": 39
    },
    {
      "epoch": 0.12260536398467432,
      "grad_norm": 5.676209449768066,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.9978,
      "step": 40
    },
    {
      "epoch": 0.12567049808429118,
      "grad_norm": 5.601908206939697,
      "learning_rate": 8.426519384872733e-06,
      "loss": 2.1699,
      "step": 41
    },
    {
      "epoch": 0.12873563218390804,
      "grad_norm": 6.1585259437561035,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1751,
      "step": 42
    },
    {
      "epoch": 0.1318007662835249,
      "grad_norm": 6.675445079803467,
      "learning_rate": 5.156362923365588e-06,
      "loss": 2.1657,
      "step": 43
    },
    {
      "epoch": 0.13486590038314175,
      "grad_norm": 7.457511901855469,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.1494,
      "step": 44
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 8.19306755065918,
      "learning_rate": 2.653493525244721e-06,
      "loss": 2.0715,
      "step": 45
    },
    {
      "epoch": 0.1409961685823755,
      "grad_norm": 8.111923217773438,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.1786,
      "step": 46
    },
    {
      "epoch": 0.14406130268199233,
      "grad_norm": 9.426108360290527,
      "learning_rate": 9.607359798384785e-07,
      "loss": 2.1819,
      "step": 47
    },
    {
      "epoch": 0.1471264367816092,
      "grad_norm": 9.696084022521973,
      "learning_rate": 4.277569313094809e-07,
      "loss": 2.1805,
      "step": 48
    },
    {
      "epoch": 0.15019157088122606,
      "grad_norm": 12.12969970703125,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 2.1362,
      "step": 49
    },
    {
      "epoch": 0.1532567049808429,
      "grad_norm": 18.35208511352539,
      "learning_rate": 0.0,
      "loss": 2.0582,
      "step": 50
    },
    {
      "epoch": 0.1532567049808429,
      "eval_loss": 2.0883843898773193,
      "eval_runtime": 64.1696,
      "eval_samples_per_second": 34.253,
      "eval_steps_per_second": 4.286,
      "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": 5.658027780734976e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}