{
  "best_metric": 0.7736887335777283,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.14958863126402394,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029917726252804786,
      "grad_norm": 0.8385376930236816,
      "learning_rate": 5e-05,
      "loss": 0.8104,
      "step": 1
    },
    {
      "epoch": 0.0029917726252804786,
      "eval_loss": 3.519901752471924,
      "eval_runtime": 4.7778,
      "eval_samples_per_second": 10.465,
      "eval_steps_per_second": 2.721,
      "step": 1
    },
    {
      "epoch": 0.005983545250560957,
      "grad_norm": 1.8511754274368286,
      "learning_rate": 0.0001,
      "loss": 1.2348,
      "step": 2
    },
    {
      "epoch": 0.008975317875841436,
      "grad_norm": 2.2680823802948,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.2108,
      "step": 3
    },
    {
      "epoch": 0.011967090501121914,
      "grad_norm": 2.4987900257110596,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.4011,
      "step": 4
    },
    {
      "epoch": 0.014958863126402393,
      "grad_norm": 4.1585211753845215,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.2129,
      "step": 5
    },
    {
      "epoch": 0.01795063575168287,
      "grad_norm": 4.16989278793335,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.2658,
      "step": 6
    },
    {
      "epoch": 0.020942408376963352,
      "grad_norm": 2.7705466747283936,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.1406,
      "step": 7
    },
    {
      "epoch": 0.02393418100224383,
      "grad_norm": 3.152975082397461,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.1352,
      "step": 8
    },
    {
      "epoch": 0.02692595362752431,
      "grad_norm": 2.8932056427001953,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.077,
      "step": 9
    },
    {
      "epoch": 0.029917726252804786,
      "grad_norm": 2.3467397689819336,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.0407,
      "step": 10
    },
    {
      "epoch": 0.032909498878085267,
      "grad_norm": 2.217741012573242,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.0096,
      "step": 11
    },
    {
      "epoch": 0.03590127150336574,
      "grad_norm": 2.116528272628784,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.9408,
      "step": 12
    },
    {
      "epoch": 0.03889304412864622,
      "grad_norm": 3.282927989959717,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.9675,
      "step": 13
    },
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 1.8240456581115723,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.5492,
      "step": 14
    },
    {
      "epoch": 0.04487658937920718,
      "grad_norm": 1.5142714977264404,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.7577,
      "step": 15
    },
    {
      "epoch": 0.04786836200448766,
      "grad_norm": 1.4267750978469849,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.7114,
      "step": 16
    },
    {
      "epoch": 0.050860134629768135,
      "grad_norm": 1.4969170093536377,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.6643,
      "step": 17
    },
    {
      "epoch": 0.05385190725504862,
      "grad_norm": 1.4697543382644653,
      "learning_rate": 7.75e-05,
      "loss": 0.7818,
      "step": 18
    },
    {
      "epoch": 0.056843679880329095,
      "grad_norm": 1.229280948638916,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.8943,
      "step": 19
    },
    {
      "epoch": 0.05983545250560957,
      "grad_norm": 1.4670908451080322,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.914,
      "step": 20
    },
    {
      "epoch": 0.06282722513089005,
      "grad_norm": 1.1838334798812866,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.7716,
      "step": 21
    },
    {
      "epoch": 0.06581899775617053,
      "grad_norm": 1.4977772235870361,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.8973,
      "step": 22
    },
    {
      "epoch": 0.068810770381451,
      "grad_norm": 1.396195888519287,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.9745,
      "step": 23
    },
    {
      "epoch": 0.07180254300673149,
      "grad_norm": 1.3455644845962524,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.9369,
      "step": 24
    },
    {
      "epoch": 0.07479431563201197,
      "grad_norm": 1.4627197980880737,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.0178,
      "step": 25
    },
    {
      "epoch": 0.07479431563201197,
      "eval_loss": 0.780426561832428,
      "eval_runtime": 4.8394,
      "eval_samples_per_second": 10.332,
      "eval_steps_per_second": 2.686,
      "step": 25
    },
    {
      "epoch": 0.07778608825729244,
      "grad_norm": 1.333006739616394,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.6628,
      "step": 26
    },
    {
      "epoch": 0.08077786088257292,
      "grad_norm": 1.7285902500152588,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.6592,
      "step": 27
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 1.4240301847457886,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.7008,
      "step": 28
    },
    {
      "epoch": 0.08676140613313388,
      "grad_norm": 1.1722900867462158,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.7124,
      "step": 29
    },
    {
      "epoch": 0.08975317875841436,
      "grad_norm": 1.2526230812072754,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.7312,
      "step": 30
    },
    {
      "epoch": 0.09274495138369485,
      "grad_norm": 1.2709276676177979,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.7181,
      "step": 31
    },
    {
      "epoch": 0.09573672400897532,
      "grad_norm": 1.7405914068222046,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.805,
      "step": 32
    },
    {
      "epoch": 0.0987284966342558,
      "grad_norm": 1.881058931350708,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.8546,
      "step": 33
    },
    {
      "epoch": 0.10172026925953627,
      "grad_norm": 1.591508388519287,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.9129,
      "step": 34
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 1.4230870008468628,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.8932,
      "step": 35
    },
    {
      "epoch": 0.10770381451009724,
      "grad_norm": 1.7755883932113647,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.8137,
      "step": 36
    },
    {
      "epoch": 0.11069558713537771,
      "grad_norm": 1.4336092472076416,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.8812,
      "step": 37
    },
    {
      "epoch": 0.11368735976065819,
      "grad_norm": 0.6839767098426819,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.746,
      "step": 38
    },
    {
      "epoch": 0.11667913238593867,
      "grad_norm": 0.883723795413971,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.4953,
      "step": 39
    },
    {
      "epoch": 0.11967090501121914,
      "grad_norm": 1.1034191846847534,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.5899,
      "step": 40
    },
    {
      "epoch": 0.12266267763649963,
      "grad_norm": 1.3411037921905518,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.5957,
      "step": 41
    },
    {
      "epoch": 0.1256544502617801,
      "grad_norm": 1.173579216003418,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.5889,
      "step": 42
    },
    {
      "epoch": 0.1286462228870606,
      "grad_norm": 1.076574683189392,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.7514,
      "step": 43
    },
    {
      "epoch": 0.13163799551234107,
      "grad_norm": 1.0555602312088013,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.6741,
      "step": 44
    },
    {
      "epoch": 0.13462976813762154,
      "grad_norm": 1.1221964359283447,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.6866,
      "step": 45
    },
    {
      "epoch": 0.137621540762902,
      "grad_norm": 1.205617070198059,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.8152,
      "step": 46
    },
    {
      "epoch": 0.1406133133881825,
      "grad_norm": 1.2014487981796265,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.7961,
      "step": 47
    },
    {
      "epoch": 0.14360508601346297,
      "grad_norm": 1.2235502004623413,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.8346,
      "step": 48
    },
    {
      "epoch": 0.14659685863874344,
      "grad_norm": 1.4418388605117798,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.8465,
      "step": 49
    },
    {
      "epoch": 0.14958863126402394,
      "grad_norm": 1.4110114574432373,
      "learning_rate": 1e-05,
      "loss": 0.9157,
      "step": 50
    },
    {
      "epoch": 0.14958863126402394,
      "eval_loss": 0.7736887335777283,
      "eval_runtime": 4.8278,
      "eval_samples_per_second": 10.357,
      "eval_steps_per_second": 2.693,
      "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": 6.174479344467968e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}