{
  "best_metric": 1.925268292427063,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.034638032559750606,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006927606511950121,
      "grad_norm": 3.7394962310791016,
      "learning_rate": 2e-05,
      "loss": 1.8865,
      "step": 1
    },
    {
      "epoch": 0.0006927606511950121,
      "eval_loss": 3.4180867671966553,
      "eval_runtime": 105.9943,
      "eval_samples_per_second": 22.935,
      "eval_steps_per_second": 2.868,
      "step": 1
    },
    {
      "epoch": 0.0013855213023900243,
      "grad_norm": 4.808347702026367,
      "learning_rate": 4e-05,
      "loss": 2.8326,
      "step": 2
    },
    {
      "epoch": 0.0020782819535850364,
      "grad_norm": 4.704452991485596,
      "learning_rate": 6e-05,
      "loss": 2.8005,
      "step": 3
    },
    {
      "epoch": 0.0027710426047800486,
      "grad_norm": 3.6126086711883545,
      "learning_rate": 8e-05,
      "loss": 2.6763,
      "step": 4
    },
    {
      "epoch": 0.0034638032559750607,
      "grad_norm": 2.551593065261841,
      "learning_rate": 0.0001,
      "loss": 2.3357,
      "step": 5
    },
    {
      "epoch": 0.004156563907170073,
      "grad_norm": 3.7117197513580322,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2963,
      "step": 6
    },
    {
      "epoch": 0.0048493245583650845,
      "grad_norm": 4.015963077545166,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.4067,
      "step": 7
    },
    {
      "epoch": 0.005542085209560097,
      "grad_norm": 2.8288285732269287,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.2358,
      "step": 8
    },
    {
      "epoch": 0.006234845860755109,
      "grad_norm": 1.7908943891525269,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.2186,
      "step": 9
    },
    {
      "epoch": 0.006927606511950121,
      "grad_norm": 1.5709354877471924,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.0185,
      "step": 10
    },
    {
      "epoch": 0.007620367163145133,
      "grad_norm": 1.5967903137207031,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.8455,
      "step": 11
    },
    {
      "epoch": 0.008313127814340146,
      "grad_norm": 1.84505033493042,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9486,
      "step": 12
    },
    {
      "epoch": 0.009005888465535157,
      "grad_norm": 1.5930143594741821,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8592,
      "step": 13
    },
    {
      "epoch": 0.009698649116730169,
      "grad_norm": 1.6891001462936401,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8737,
      "step": 14
    },
    {
      "epoch": 0.010391409767925183,
      "grad_norm": 1.6946450471878052,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.034,
      "step": 15
    },
    {
      "epoch": 0.011084170419120194,
      "grad_norm": 1.7690061330795288,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.8169,
      "step": 16
    },
    {
      "epoch": 0.011776931070315206,
      "grad_norm": 1.732709527015686,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8341,
      "step": 17
    },
    {
      "epoch": 0.012469691721510218,
      "grad_norm": 1.678829312324524,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8869,
      "step": 18
    },
    {
      "epoch": 0.013162452372705231,
      "grad_norm": 1.8001278638839722,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.0451,
      "step": 19
    },
    {
      "epoch": 0.013855213023900243,
      "grad_norm": 1.6319921016693115,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8867,
      "step": 20
    },
    {
      "epoch": 0.014547973675095255,
      "grad_norm": 1.8165608644485474,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9055,
      "step": 21
    },
    {
      "epoch": 0.015240734326290266,
      "grad_norm": 1.745072364807129,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.7492,
      "step": 22
    },
    {
      "epoch": 0.01593349497748528,
      "grad_norm": 1.8668386936187744,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9167,
      "step": 23
    },
    {
      "epoch": 0.01662625562868029,
      "grad_norm": 2.039052963256836,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.0707,
      "step": 24
    },
    {
      "epoch": 0.017319016279875303,
      "grad_norm": 1.9726697206497192,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.8683,
      "step": 25
    },
    {
      "epoch": 0.017319016279875303,
      "eval_loss": 2.0045647621154785,
      "eval_runtime": 107.4606,
      "eval_samples_per_second": 22.622,
      "eval_steps_per_second": 2.829,
      "step": 25
    },
    {
      "epoch": 0.018011776931070315,
      "grad_norm": 1.9637459516525269,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.9693,
      "step": 26
    },
    {
      "epoch": 0.018704537582265326,
      "grad_norm": 2.19867205619812,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.1042,
      "step": 27
    },
    {
      "epoch": 0.019397298233460338,
      "grad_norm": 3.29902720451355,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.1187,
      "step": 28
    },
    {
      "epoch": 0.02009005888465535,
      "grad_norm": 2.207946538925171,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.051,
      "step": 29
    },
    {
      "epoch": 0.020782819535850365,
      "grad_norm": 2.3919827938079834,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.0283,
      "step": 30
    },
    {
      "epoch": 0.021475580187045377,
      "grad_norm": 2.635960102081299,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.0517,
      "step": 31
    },
    {
      "epoch": 0.02216834083824039,
      "grad_norm": 2.4019076824188232,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0454,
      "step": 32
    },
    {
      "epoch": 0.0228611014894354,
      "grad_norm": 2.715149164199829,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.1534,
      "step": 33
    },
    {
      "epoch": 0.023553862140630412,
      "grad_norm": 2.745685338973999,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.0358,
      "step": 34
    },
    {
      "epoch": 0.024246622791825424,
      "grad_norm": 3.077956199645996,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.9545,
      "step": 35
    },
    {
      "epoch": 0.024939383443020435,
      "grad_norm": 3.0853688716888428,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9959,
      "step": 36
    },
    {
      "epoch": 0.025632144094215447,
      "grad_norm": 3.2483320236206055,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.2629,
      "step": 37
    },
    {
      "epoch": 0.026324904745410462,
      "grad_norm": 4.238058567047119,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.1954,
      "step": 38
    },
    {
      "epoch": 0.027017665396605474,
      "grad_norm": 3.7182886600494385,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9383,
      "step": 39
    },
    {
      "epoch": 0.027710426047800486,
      "grad_norm": 3.5216612815856934,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8053,
      "step": 40
    },
    {
      "epoch": 0.028403186698995497,
      "grad_norm": 3.81185245513916,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.023,
      "step": 41
    },
    {
      "epoch": 0.02909594735019051,
      "grad_norm": 5.425981044769287,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.2643,
      "step": 42
    },
    {
      "epoch": 0.02978870800138552,
      "grad_norm": 5.006731033325195,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.8187,
      "step": 43
    },
    {
      "epoch": 0.030481468652580532,
      "grad_norm": 5.460813522338867,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.3796,
      "step": 44
    },
    {
      "epoch": 0.031174229303775544,
      "grad_norm": 5.395287036895752,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.0059,
      "step": 45
    },
    {
      "epoch": 0.03186698995497056,
      "grad_norm": 5.910126686096191,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.2614,
      "step": 46
    },
    {
      "epoch": 0.03255975060616557,
      "grad_norm": 8.539700508117676,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2344,
      "step": 47
    },
    {
      "epoch": 0.03325251125736058,
      "grad_norm": 7.000600337982178,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.1331,
      "step": 48
    },
    {
      "epoch": 0.03394527190855559,
      "grad_norm": 8.374863624572754,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.8368,
      "step": 49
    },
    {
      "epoch": 0.034638032559750606,
      "grad_norm": 15.601841926574707,
      "learning_rate": 0.0,
      "loss": 2.3394,
      "step": 50
    },
    {
      "epoch": 0.034638032559750606,
      "eval_loss": 1.925268292427063,
      "eval_runtime": 107.3932,
      "eval_samples_per_second": 22.636,
      "eval_steps_per_second": 2.831,
      "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": 5,
        "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": 3.927746687061197e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}