{
  "best_metric": 2.0474109649658203,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.4373881932021466,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 5.248751640319824,
      "learning_rate": 5e-05,
      "loss": 3.6868,
      "step": 1
    },
    {
      "epoch": 0.028622540250447227,
      "eval_loss": 4.301292896270752,
      "eval_runtime": 3.1203,
      "eval_samples_per_second": 16.024,
      "eval_steps_per_second": 4.166,
      "step": 1
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 6.061405658721924,
      "learning_rate": 0.0001,
      "loss": 4.0639,
      "step": 2
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 6.37395715713501,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.0684,
      "step": 3
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 4.967219352722168,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.9482,
      "step": 4
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 5.621387481689453,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.9168,
      "step": 5
    },
    {
      "epoch": 0.17173524150268335,
      "grad_norm": 5.811436653137207,
      "learning_rate": 9.846666218300807e-05,
      "loss": 3.7124,
      "step": 6
    },
    {
      "epoch": 0.2003577817531306,
      "grad_norm": 3.5655829906463623,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.6918,
      "step": 7
    },
    {
      "epoch": 0.22898032200357782,
      "grad_norm": 3.6272494792938232,
      "learning_rate": 9.657457896300791e-05,
      "loss": 3.2377,
      "step": 8
    },
    {
      "epoch": 0.25760286225402507,
      "grad_norm": 3.868758201599121,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.5924,
      "step": 9
    },
    {
      "epoch": 0.28622540250447226,
      "grad_norm": 3.9583933353424072,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.7414,
      "step": 10
    },
    {
      "epoch": 0.3148479427549195,
      "grad_norm": 3.04331374168396,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.5412,
      "step": 11
    },
    {
      "epoch": 0.3434704830053667,
      "grad_norm": 2.6324641704559326,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.6722,
      "step": 12
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 3.1993017196655273,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.4788,
      "step": 13
    },
    {
      "epoch": 0.4007155635062612,
      "grad_norm": 4.412987232208252,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.5753,
      "step": 14
    },
    {
      "epoch": 0.4293381037567084,
      "grad_norm": 2.759384870529175,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.2801,
      "step": 15
    },
    {
      "epoch": 0.45796064400715564,
      "grad_norm": 2.776599884033203,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.9648,
      "step": 16
    },
    {
      "epoch": 0.4865831842576029,
      "grad_norm": 2.704115152359009,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.9062,
      "step": 17
    },
    {
      "epoch": 0.5152057245080501,
      "grad_norm": 2.887990951538086,
      "learning_rate": 7.75e-05,
      "loss": 2.0811,
      "step": 18
    },
    {
      "epoch": 0.5438282647584973,
      "grad_norm": 2.348613977432251,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.37,
      "step": 19
    },
    {
      "epoch": 0.5724508050089445,
      "grad_norm": 1.8327924013137817,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.2327,
      "step": 20
    },
    {
      "epoch": 0.6010733452593918,
      "grad_norm": 2.2849843502044678,
      "learning_rate": 6.946477593864228e-05,
      "loss": 2.0083,
      "step": 21
    },
    {
      "epoch": 0.629695885509839,
      "grad_norm": 3.5792484283447266,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.0399,
      "step": 22
    },
    {
      "epoch": 0.6583184257602862,
      "grad_norm": 3.0380265712738037,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.1598,
      "step": 23
    },
    {
      "epoch": 0.6869409660107334,
      "grad_norm": 2.6669726371765137,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.321,
      "step": 24
    },
    {
      "epoch": 0.7155635062611807,
      "grad_norm": 2.3873627185821533,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.8646,
      "step": 25
    },
    {
      "epoch": 0.7155635062611807,
      "eval_loss": 2.232006311416626,
      "eval_runtime": 2.1627,
      "eval_samples_per_second": 23.119,
      "eval_steps_per_second": 6.011,
      "step": 25
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 2.1446194648742676,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.9902,
      "step": 26
    },
    {
      "epoch": 0.7728085867620751,
      "grad_norm": 2.8417482376098633,
      "learning_rate": 5.205685918464356e-05,
      "loss": 2.203,
      "step": 27
    },
    {
      "epoch": 0.8014311270125224,
      "grad_norm": 2.5901710987091064,
      "learning_rate": 4.912632135009769e-05,
      "loss": 2.0875,
      "step": 28
    },
    {
      "epoch": 0.8300536672629696,
      "grad_norm": 1.9818401336669922,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 2.006,
      "step": 29
    },
    {
      "epoch": 0.8586762075134168,
      "grad_norm": 1.845893383026123,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.9511,
      "step": 30
    },
    {
      "epoch": 0.8872987477638641,
      "grad_norm": 2.940427780151367,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.9509,
      "step": 31
    },
    {
      "epoch": 0.9159212880143113,
      "grad_norm": 2.590958833694458,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.9384,
      "step": 32
    },
    {
      "epoch": 0.9445438282647585,
      "grad_norm": 2.4626338481903076,
      "learning_rate": 3.509700894014496e-05,
      "loss": 2.2763,
      "step": 33
    },
    {
      "epoch": 0.9731663685152058,
      "grad_norm": 2.399420738220215,
      "learning_rate": 3.250000000000001e-05,
      "loss": 2.3558,
      "step": 34
    },
    {
      "epoch": 1.0080500894454383,
      "grad_norm": 2.7684226036071777,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 2.4598,
      "step": 35
    },
    {
      "epoch": 1.0366726296958855,
      "grad_norm": 1.9706850051879883,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.9572,
      "step": 36
    },
    {
      "epoch": 1.0652951699463327,
      "grad_norm": 1.638630747795105,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.8983,
      "step": 37
    },
    {
      "epoch": 1.0939177101967799,
      "grad_norm": 1.4581589698791504,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.9597,
      "step": 38
    },
    {
      "epoch": 1.1225402504472273,
      "grad_norm": 1.6679154634475708,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.8376,
      "step": 39
    },
    {
      "epoch": 1.1511627906976745,
      "grad_norm": 2.3730578422546387,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.8044,
      "step": 40
    },
    {
      "epoch": 1.1797853309481217,
      "grad_norm": 2.496169328689575,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.8078,
      "step": 41
    },
    {
      "epoch": 1.2084078711985689,
      "grad_norm": 1.8919925689697266,
      "learning_rate": 1.602885682970026e-05,
      "loss": 2.2044,
      "step": 42
    },
    {
      "epoch": 1.237030411449016,
      "grad_norm": 1.7182238101959229,
      "learning_rate": 1.464072663102903e-05,
      "loss": 2.2614,
      "step": 43
    },
    {
      "epoch": 1.2656529516994635,
      "grad_norm": 2.199777603149414,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.9487,
      "step": 44
    },
    {
      "epoch": 1.2942754919499104,
      "grad_norm": 1.936216950416565,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.8915,
      "step": 45
    },
    {
      "epoch": 1.3228980322003578,
      "grad_norm": 1.9741896390914917,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.8249,
      "step": 46
    },
    {
      "epoch": 1.351520572450805,
      "grad_norm": 1.594980001449585,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.8828,
      "step": 47
    },
    {
      "epoch": 1.3801431127012522,
      "grad_norm": 1.923370599746704,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.6503,
      "step": 48
    },
    {
      "epoch": 1.4087656529516994,
      "grad_norm": 2.650059938430786,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.6745,
      "step": 49
    },
    {
      "epoch": 1.4373881932021466,
      "grad_norm": 1.9627615213394165,
      "learning_rate": 1e-05,
      "loss": 1.8041,
      "step": 50
    },
    {
      "epoch": 1.4373881932021466,
      "eval_loss": 2.0474109649658203,
      "eval_runtime": 2.0993,
      "eval_samples_per_second": 23.817,
      "eval_steps_per_second": 6.192,
      "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": 5.002120628745011e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}