{
  "best_metric": 6.333108103717677e-06,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12101043715020421,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002420208743004084,
      "grad_norm": 131.33819580078125,
      "learning_rate": 5e-05,
      "loss": 111.0611,
      "step": 1
    },
    {
      "epoch": 0.002420208743004084,
      "eval_loss": 7.585880279541016,
      "eval_runtime": 2.9108,
      "eval_samples_per_second": 17.178,
      "eval_steps_per_second": 4.466,
      "step": 1
    },
    {
      "epoch": 0.004840417486008168,
      "grad_norm": 132.7710723876953,
      "learning_rate": 0.0001,
      "loss": 112.1903,
      "step": 2
    },
    {
      "epoch": 0.007260626229012252,
      "grad_norm": 125.43817901611328,
      "learning_rate": 9.990365154573717e-05,
      "loss": 106.0719,
      "step": 3
    },
    {
      "epoch": 0.009680834972016336,
      "grad_norm": 119.73974609375,
      "learning_rate": 9.961501876182148e-05,
      "loss": 83.2367,
      "step": 4
    },
    {
      "epoch": 0.01210104371502042,
      "grad_norm": 112.78900909423828,
      "learning_rate": 9.913533761814537e-05,
      "loss": 61.5406,
      "step": 5
    },
    {
      "epoch": 0.014521252458024504,
      "grad_norm": 125.04703521728516,
      "learning_rate": 9.846666218300807e-05,
      "loss": 38.4313,
      "step": 6
    },
    {
      "epoch": 0.016941461201028588,
      "grad_norm": 96.21353149414062,
      "learning_rate": 9.761185582727977e-05,
      "loss": 25.4436,
      "step": 7
    },
    {
      "epoch": 0.019361669944032673,
      "grad_norm": 72.18242645263672,
      "learning_rate": 9.657457896300791e-05,
      "loss": 14.8805,
      "step": 8
    },
    {
      "epoch": 0.02178187868703676,
      "grad_norm": 42.342674255371094,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.2297,
      "step": 9
    },
    {
      "epoch": 0.02420208743004084,
      "grad_norm": 18.25030517578125,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.5625,
      "step": 10
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 10.75106143951416,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.1359,
      "step": 11
    },
    {
      "epoch": 0.029042504916049008,
      "grad_norm": 8.85315990447998,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.4542,
      "step": 12
    },
    {
      "epoch": 0.03146271365905309,
      "grad_norm": 6.057021141052246,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.2374,
      "step": 13
    },
    {
      "epoch": 0.033882922402057175,
      "grad_norm": 3.520845413208008,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0789,
      "step": 14
    },
    {
      "epoch": 0.036303131145061264,
      "grad_norm": 0.16829857230186462,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0067,
      "step": 15
    },
    {
      "epoch": 0.038723339888065346,
      "grad_norm": 0.02904125675559044,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0015,
      "step": 16
    },
    {
      "epoch": 0.04114354863106943,
      "grad_norm": 0.049647390842437744,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0017,
      "step": 17
    },
    {
      "epoch": 0.04356375737407352,
      "grad_norm": 0.04762301966547966,
      "learning_rate": 7.75e-05,
      "loss": 0.0015,
      "step": 18
    },
    {
      "epoch": 0.0459839661170776,
      "grad_norm": 0.02013726718723774,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0007,
      "step": 19
    },
    {
      "epoch": 0.04840417486008168,
      "grad_norm": 0.012627098709344864,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0005,
      "step": 20
    },
    {
      "epoch": 0.05082438360308577,
      "grad_norm": 0.007175073027610779,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0003,
      "step": 21
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 0.010423569008708,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0004,
      "step": 22
    },
    {
      "epoch": 0.055664801089093933,
      "grad_norm": 0.010328639298677444,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0004,
      "step": 23
    },
    {
      "epoch": 0.058085009832098015,
      "grad_norm": 0.0085712019354105,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0003,
      "step": 24
    },
    {
      "epoch": 0.060505218575102104,
      "grad_norm": 0.014741580933332443,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0006,
      "step": 25
    },
    {
      "epoch": 0.060505218575102104,
      "eval_loss": 1.1880485544679686e-05,
      "eval_runtime": 2.97,
      "eval_samples_per_second": 16.835,
      "eval_steps_per_second": 4.377,
      "step": 25
    },
    {
      "epoch": 0.06292542731810619,
      "grad_norm": 5.236049175262451,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.7224,
      "step": 26
    },
    {
      "epoch": 0.06534563606111027,
      "grad_norm": 0.0036764470860362053,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0001,
      "step": 27
    },
    {
      "epoch": 0.06776584480411435,
      "grad_norm": 0.0036135385744273663,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0001,
      "step": 28
    },
    {
      "epoch": 0.07018605354711843,
      "grad_norm": 0.013541589491069317,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0002,
      "step": 29
    },
    {
      "epoch": 0.07260626229012253,
      "grad_norm": 0.003832306945696473,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0002,
      "step": 30
    },
    {
      "epoch": 0.07502647103312661,
      "grad_norm": 0.0027044774033129215,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.07744667977613069,
      "grad_norm": 0.017098935320973396,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0002,
      "step": 32
    },
    {
      "epoch": 0.07986688851913477,
      "grad_norm": 9.107158660888672,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.1233,
      "step": 33
    },
    {
      "epoch": 0.08228709726213886,
      "grad_norm": 0.002680846955627203,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0001,
      "step": 34
    },
    {
      "epoch": 0.08470730600514294,
      "grad_norm": 0.003972608130425215,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0002,
      "step": 35
    },
    {
      "epoch": 0.08712751474814703,
      "grad_norm": 0.003575769951567054,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.08954772349115112,
      "grad_norm": 0.003803999163210392,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0002,
      "step": 37
    },
    {
      "epoch": 0.0919679322341552,
      "grad_norm": 72.67724609375,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.2959,
      "step": 38
    },
    {
      "epoch": 0.09438814097715928,
      "grad_norm": 0.00248934724368155,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0001,
      "step": 39
    },
    {
      "epoch": 0.09680834972016336,
      "grad_norm": 0.002764883218333125,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.09922855846316744,
      "grad_norm": 0.0022895580623298883,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0001,
      "step": 41
    },
    {
      "epoch": 0.10164876720617154,
      "grad_norm": 0.002441002056002617,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.10406897594917562,
      "grad_norm": 0.0023592477664351463,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0001,
      "step": 43
    },
    {
      "epoch": 0.1064891846921797,
      "grad_norm": 0.0023515636567026377,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0001,
      "step": 44
    },
    {
      "epoch": 0.10890939343518379,
      "grad_norm": 0.002235549269244075,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.11132960217818787,
      "grad_norm": 0.00230324175208807,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.11374981092119195,
      "grad_norm": 0.019611643627285957,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0002,
      "step": 47
    },
    {
      "epoch": 0.11617001966419603,
      "grad_norm": 0.0029431243892759085,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.11859022840720013,
      "grad_norm": 13.474868774414062,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0712,
      "step": 49
    },
    {
      "epoch": 0.12101043715020421,
      "grad_norm": 0.3831072747707367,
      "learning_rate": 1e-05,
      "loss": 0.0015,
      "step": 50
    },
    {
      "epoch": 0.12101043715020421,
      "eval_loss": 6.333108103717677e-06,
      "eval_runtime": 2.9429,
      "eval_samples_per_second": 16.99,
      "eval_steps_per_second": 4.417,
      "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": 5.262443296860406e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}