{
  "best_metric": 0.3419298231601715,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.20090406830738322,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004018081366147665,
      "grad_norm": 287.27130126953125,
      "learning_rate": 5e-05,
      "loss": 139.1807,
      "step": 1
    },
    {
      "epoch": 0.004018081366147665,
      "eval_loss": 9.032082557678223,
      "eval_runtime": 1.7503,
      "eval_samples_per_second": 28.566,
      "eval_steps_per_second": 7.427,
      "step": 1
    },
    {
      "epoch": 0.00803616273229533,
      "grad_norm": 305.86358642578125,
      "learning_rate": 0.0001,
      "loss": 165.2526,
      "step": 2
    },
    {
      "epoch": 0.012054244098442994,
      "grad_norm": 249.86029052734375,
      "learning_rate": 9.990365154573717e-05,
      "loss": 149.9486,
      "step": 3
    },
    {
      "epoch": 0.01607232546459066,
      "grad_norm": 182.3063507080078,
      "learning_rate": 9.961501876182148e-05,
      "loss": 107.888,
      "step": 4
    },
    {
      "epoch": 0.020090406830738324,
      "grad_norm": 156.85470581054688,
      "learning_rate": 9.913533761814537e-05,
      "loss": 85.3992,
      "step": 5
    },
    {
      "epoch": 0.024108488196885988,
      "grad_norm": 142.10797119140625,
      "learning_rate": 9.846666218300807e-05,
      "loss": 55.6505,
      "step": 6
    },
    {
      "epoch": 0.02812656956303365,
      "grad_norm": 138.2862091064453,
      "learning_rate": 9.761185582727977e-05,
      "loss": 29.6688,
      "step": 7
    },
    {
      "epoch": 0.03214465092918132,
      "grad_norm": 100.1500473022461,
      "learning_rate": 9.657457896300791e-05,
      "loss": 15.3734,
      "step": 8
    },
    {
      "epoch": 0.03616273229532898,
      "grad_norm": 71.64418029785156,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.9717,
      "step": 9
    },
    {
      "epoch": 0.04018081366147665,
      "grad_norm": 45.37214660644531,
      "learning_rate": 9.397114317029975e-05,
      "loss": 5.748,
      "step": 10
    },
    {
      "epoch": 0.04419889502762431,
      "grad_norm": 152.17193603515625,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.2065,
      "step": 11
    },
    {
      "epoch": 0.048216976393771975,
      "grad_norm": 98.67989349365234,
      "learning_rate": 9.070090031310558e-05,
      "loss": 8.2616,
      "step": 12
    },
    {
      "epoch": 0.052235057759919636,
      "grad_norm": 97.24883270263672,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.4244,
      "step": 13
    },
    {
      "epoch": 0.0562531391260673,
      "grad_norm": 156.29473876953125,
      "learning_rate": 8.681980515339464e-05,
      "loss": 12.3799,
      "step": 14
    },
    {
      "epoch": 0.06027122049221497,
      "grad_norm": 88.79014587402344,
      "learning_rate": 8.467056167950311e-05,
      "loss": 8.6108,
      "step": 15
    },
    {
      "epoch": 0.06428930185836264,
      "grad_norm": 79.97587585449219,
      "learning_rate": 8.239426430539243e-05,
      "loss": 6.9669,
      "step": 16
    },
    {
      "epoch": 0.0683073832245103,
      "grad_norm": 44.946285247802734,
      "learning_rate": 8.000066048588211e-05,
      "loss": 5.8716,
      "step": 17
    },
    {
      "epoch": 0.07232546459065796,
      "grad_norm": 23.077661514282227,
      "learning_rate": 7.75e-05,
      "loss": 5.0874,
      "step": 18
    },
    {
      "epoch": 0.07634354595680562,
      "grad_norm": 32.691253662109375,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.7134,
      "step": 19
    },
    {
      "epoch": 0.0803616273229533,
      "grad_norm": 24.590879440307617,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.2107,
      "step": 20
    },
    {
      "epoch": 0.08437970868910095,
      "grad_norm": 17.236364364624023,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.8954,
      "step": 21
    },
    {
      "epoch": 0.08839779005524862,
      "grad_norm": 17.663654327392578,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.9302,
      "step": 22
    },
    {
      "epoch": 0.09241587142139629,
      "grad_norm": 14.92285442352295,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.8741,
      "step": 23
    },
    {
      "epoch": 0.09643395278754395,
      "grad_norm": 23.026290893554688,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.8543,
      "step": 24
    },
    {
      "epoch": 0.10045203415369161,
      "grad_norm": 16.016550064086914,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.2728,
      "step": 25
    },
    {
      "epoch": 0.10045203415369161,
      "eval_loss": 0.3901463747024536,
      "eval_runtime": 1.7509,
      "eval_samples_per_second": 28.557,
      "eval_steps_per_second": 7.425,
      "step": 25
    },
    {
      "epoch": 0.10447011551983927,
      "grad_norm": 173.174072265625,
      "learning_rate": 5.500000000000001e-05,
      "loss": 14.3707,
      "step": 26
    },
    {
      "epoch": 0.10848819688598695,
      "grad_norm": 147.3890380859375,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.0976,
      "step": 27
    },
    {
      "epoch": 0.1125062782521346,
      "grad_norm": 114.66434478759766,
      "learning_rate": 4.912632135009769e-05,
      "loss": 9.7754,
      "step": 28
    },
    {
      "epoch": 0.11652435961828227,
      "grad_norm": 78.83654022216797,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 5.5902,
      "step": 29
    },
    {
      "epoch": 0.12054244098442994,
      "grad_norm": 31.42974090576172,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.6766,
      "step": 30
    },
    {
      "epoch": 0.1245605223505776,
      "grad_norm": 38.81559371948242,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.143,
      "step": 31
    },
    {
      "epoch": 0.12857860371672528,
      "grad_norm": 60.23033142089844,
      "learning_rate": 3.777924554357096e-05,
      "loss": 2.8414,
      "step": 32
    },
    {
      "epoch": 0.13259668508287292,
      "grad_norm": 35.685691833496094,
      "learning_rate": 3.509700894014496e-05,
      "loss": 2.1602,
      "step": 33
    },
    {
      "epoch": 0.1366147664490206,
      "grad_norm": 34.83101272583008,
      "learning_rate": 3.250000000000001e-05,
      "loss": 2.1482,
      "step": 34
    },
    {
      "epoch": 0.14063284781516824,
      "grad_norm": 14.176968574523926,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.5788,
      "step": 35
    },
    {
      "epoch": 0.14465092918131592,
      "grad_norm": 25.032855987548828,
      "learning_rate": 2.760573569460757e-05,
      "loss": 2.0398,
      "step": 36
    },
    {
      "epoch": 0.1486690105474636,
      "grad_norm": 12.065668106079102,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.62,
      "step": 37
    },
    {
      "epoch": 0.15268709191361124,
      "grad_norm": 44.62394714355469,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.2944,
      "step": 38
    },
    {
      "epoch": 0.1567051732797589,
      "grad_norm": 71.64360809326172,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 6.0688,
      "step": 39
    },
    {
      "epoch": 0.1607232546459066,
      "grad_norm": 58.64244079589844,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 6.0727,
      "step": 40
    },
    {
      "epoch": 0.16474133601205423,
      "grad_norm": 92.85259246826172,
      "learning_rate": 1.758386744638546e-05,
      "loss": 6.1197,
      "step": 41
    },
    {
      "epoch": 0.1687594173782019,
      "grad_norm": 80.76541137695312,
      "learning_rate": 1.602885682970026e-05,
      "loss": 5.2377,
      "step": 42
    },
    {
      "epoch": 0.17277749874434958,
      "grad_norm": 63.15403747558594,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.6449,
      "step": 43
    },
    {
      "epoch": 0.17679558011049723,
      "grad_norm": 66.09992980957031,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.4156,
      "step": 44
    },
    {
      "epoch": 0.1808136614766449,
      "grad_norm": 36.22022247314453,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.6311,
      "step": 45
    },
    {
      "epoch": 0.18483174284279258,
      "grad_norm": 56.1572265625,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 2.4557,
      "step": 46
    },
    {
      "epoch": 0.18884982420894023,
      "grad_norm": 35.4969482421875,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.9909,
      "step": 47
    },
    {
      "epoch": 0.1928679055750879,
      "grad_norm": 28.917226791381836,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.7636,
      "step": 48
    },
    {
      "epoch": 0.19688598694123555,
      "grad_norm": 49.72064971923828,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 2.4829,
      "step": 49
    },
    {
      "epoch": 0.20090406830738322,
      "grad_norm": 85.38445281982422,
      "learning_rate": 1e-05,
      "loss": 3.6811,
      "step": 50
    },
    {
      "epoch": 0.20090406830738322,
      "eval_loss": 0.3419298231601715,
      "eval_runtime": 1.7502,
      "eval_samples_per_second": 28.569,
      "eval_steps_per_second": 7.428,
      "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": 2.967137622687744e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}