{
  "best_metric": 0.14452199637889862,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.3410214168039538,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026359143327841845,
      "grad_norm": 1.8601206541061401,
      "learning_rate": 5e-05,
      "loss": 2.4226,
      "step": 1
    },
    {
      "epoch": 0.026359143327841845,
      "eval_loss": 3.6227452754974365,
      "eval_runtime": 1.4231,
      "eval_samples_per_second": 35.133,
      "eval_steps_per_second": 9.135,
      "step": 1
    },
    {
      "epoch": 0.05271828665568369,
      "grad_norm": 2.712977647781372,
      "learning_rate": 0.0001,
      "loss": 2.7322,
      "step": 2
    },
    {
      "epoch": 0.07907742998352553,
      "grad_norm": 2.995701313018799,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.863,
      "step": 3
    },
    {
      "epoch": 0.10543657331136738,
      "grad_norm": 2.591517448425293,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.5187,
      "step": 4
    },
    {
      "epoch": 0.13179571663920922,
      "grad_norm": 2.660490036010742,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.4241,
      "step": 5
    },
    {
      "epoch": 0.15815485996705106,
      "grad_norm": 3.0284202098846436,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.3539,
      "step": 6
    },
    {
      "epoch": 0.18451400329489293,
      "grad_norm": 2.9272782802581787,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.3781,
      "step": 7
    },
    {
      "epoch": 0.21087314662273476,
      "grad_norm": 3.144031047821045,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.4167,
      "step": 8
    },
    {
      "epoch": 0.2372322899505766,
      "grad_norm": 4.086214542388916,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.7137,
      "step": 9
    },
    {
      "epoch": 0.26359143327841844,
      "grad_norm": 2.8824853897094727,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.7711,
      "step": 10
    },
    {
      "epoch": 0.2899505766062603,
      "grad_norm": 2.724992036819458,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.1975,
      "step": 11
    },
    {
      "epoch": 0.3163097199341021,
      "grad_norm": 2.2948362827301025,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.0604,
      "step": 12
    },
    {
      "epoch": 0.342668863261944,
      "grad_norm": 1.9579156637191772,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.9955,
      "step": 13
    },
    {
      "epoch": 0.36902800658978585,
      "grad_norm": 2.0095114707946777,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.9541,
      "step": 14
    },
    {
      "epoch": 0.3953871499176277,
      "grad_norm": 1.7275015115737915,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.0973,
      "step": 15
    },
    {
      "epoch": 0.42174629324546953,
      "grad_norm": 1.7991496324539185,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.0671,
      "step": 16
    },
    {
      "epoch": 0.44810543657331137,
      "grad_norm": 1.8410500288009644,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.1164,
      "step": 17
    },
    {
      "epoch": 0.4744645799011532,
      "grad_norm": 2.8816111087799072,
      "learning_rate": 7.75e-05,
      "loss": 1.248,
      "step": 18
    },
    {
      "epoch": 0.500823723228995,
      "grad_norm": 2.3085739612579346,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.1982,
      "step": 19
    },
    {
      "epoch": 0.5271828665568369,
      "grad_norm": 1.7693697214126587,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.6194,
      "step": 20
    },
    {
      "epoch": 0.5535420098846787,
      "grad_norm": 1.4358562231063843,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.4544,
      "step": 21
    },
    {
      "epoch": 0.5799011532125206,
      "grad_norm": 1.3855178356170654,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.4381,
      "step": 22
    },
    {
      "epoch": 0.6062602965403624,
      "grad_norm": 1.1838105916976929,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4334,
      "step": 23
    },
    {
      "epoch": 0.6326194398682042,
      "grad_norm": 1.4618736505508423,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.4849,
      "step": 24
    },
    {
      "epoch": 0.6589785831960461,
      "grad_norm": 2.4405136108398438,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.5773,
      "step": 25
    },
    {
      "epoch": 0.6589785831960461,
      "eval_loss": 0.49585384130477905,
      "eval_runtime": 0.7471,
      "eval_samples_per_second": 66.923,
      "eval_steps_per_second": 17.4,
      "step": 25
    },
    {
      "epoch": 0.685337726523888,
      "grad_norm": 2.4734058380126953,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.598,
      "step": 26
    },
    {
      "epoch": 0.7116968698517299,
      "grad_norm": 3.428785562515259,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.672,
      "step": 27
    },
    {
      "epoch": 0.7380560131795717,
      "grad_norm": 2.8462884426116943,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.6942,
      "step": 28
    },
    {
      "epoch": 0.7644151565074135,
      "grad_norm": 2.8353283405303955,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.534,
      "step": 29
    },
    {
      "epoch": 0.7907742998352554,
      "grad_norm": 1.8473469018936157,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.1867,
      "step": 30
    },
    {
      "epoch": 0.8171334431630972,
      "grad_norm": 1.3983721733093262,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.1956,
      "step": 31
    },
    {
      "epoch": 0.8434925864909391,
      "grad_norm": 1.2318115234375,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.2022,
      "step": 32
    },
    {
      "epoch": 0.8698517298187809,
      "grad_norm": 0.9489920735359192,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.1785,
      "step": 33
    },
    {
      "epoch": 0.8962108731466227,
      "grad_norm": 1.4298465251922607,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.2614,
      "step": 34
    },
    {
      "epoch": 0.9225700164744646,
      "grad_norm": 1.7149752378463745,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.3176,
      "step": 35
    },
    {
      "epoch": 0.9489291598023064,
      "grad_norm": 2.3903605937957764,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.389,
      "step": 36
    },
    {
      "epoch": 0.9752883031301482,
      "grad_norm": 3.662409543991089,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.4364,
      "step": 37
    },
    {
      "epoch": 1.0247116968698518,
      "grad_norm": 4.705199718475342,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.6616,
      "step": 38
    },
    {
      "epoch": 1.0510708401976936,
      "grad_norm": 0.9721773266792297,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.1232,
      "step": 39
    },
    {
      "epoch": 1.0774299835255354,
      "grad_norm": 0.9221625924110413,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.1,
      "step": 40
    },
    {
      "epoch": 1.1037891268533773,
      "grad_norm": 1.6013553142547607,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.1023,
      "step": 41
    },
    {
      "epoch": 1.130148270181219,
      "grad_norm": 1.0896989107131958,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.093,
      "step": 42
    },
    {
      "epoch": 1.156507413509061,
      "grad_norm": 1.2368277311325073,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.1512,
      "step": 43
    },
    {
      "epoch": 1.1828665568369028,
      "grad_norm": 1.908003807067871,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.2024,
      "step": 44
    },
    {
      "epoch": 1.2092257001647446,
      "grad_norm": 2.1720011234283447,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.2848,
      "step": 45
    },
    {
      "epoch": 1.2355848434925865,
      "grad_norm": 3.783008575439453,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.3299,
      "step": 46
    },
    {
      "epoch": 1.2619439868204283,
      "grad_norm": 2.4560554027557373,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.2846,
      "step": 47
    },
    {
      "epoch": 1.2883031301482701,
      "grad_norm": 1.1371558904647827,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0989,
      "step": 48
    },
    {
      "epoch": 1.314662273476112,
      "grad_norm": 0.7374827861785889,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0588,
      "step": 49
    },
    {
      "epoch": 1.3410214168039538,
      "grad_norm": 0.9319198727607727,
      "learning_rate": 1e-05,
      "loss": 0.0628,
      "step": 50
    },
    {
      "epoch": 1.3410214168039538,
      "eval_loss": 0.14452199637889862,
      "eval_runtime": 0.747,
      "eval_samples_per_second": 66.931,
      "eval_steps_per_second": 17.402,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}