{
  "best_metric": 0.12468638271093369,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.033818058843422386,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006763611768684477,
      "grad_norm": 19.953027725219727,
      "learning_rate": 2e-05,
      "loss": 6.0493,
      "step": 1
    },
    {
      "epoch": 0.0006763611768684477,
      "eval_loss": 6.812752723693848,
      "eval_runtime": 86.823,
      "eval_samples_per_second": 28.679,
      "eval_steps_per_second": 3.594,
      "step": 1
    },
    {
      "epoch": 0.0013527223537368955,
      "grad_norm": 19.822851181030273,
      "learning_rate": 4e-05,
      "loss": 6.7751,
      "step": 2
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": 18.000389099121094,
      "learning_rate": 6e-05,
      "loss": 6.2494,
      "step": 3
    },
    {
      "epoch": 0.002705444707473791,
      "grad_norm": 10.388223648071289,
      "learning_rate": 8e-05,
      "loss": 4.9237,
      "step": 4
    },
    {
      "epoch": 0.0033818058843422386,
      "grad_norm": 9.123045921325684,
      "learning_rate": 0.0001,
      "loss": 3.996,
      "step": 5
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": 10.209385871887207,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.0874,
      "step": 6
    },
    {
      "epoch": 0.0047345282380791345,
      "grad_norm": 16.488920211791992,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.2616,
      "step": 7
    },
    {
      "epoch": 0.005410889414947582,
      "grad_norm": 7.900961875915527,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3593,
      "step": 8
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": 2.970784902572632,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9435,
      "step": 9
    },
    {
      "epoch": 0.006763611768684477,
      "grad_norm": 2.4928297996520996,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8558,
      "step": 10
    },
    {
      "epoch": 0.0074399729455529254,
      "grad_norm": 2.281029462814331,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6945,
      "step": 11
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": 2.2933847904205322,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5551,
      "step": 12
    },
    {
      "epoch": 0.00879269529928982,
      "grad_norm": 3.229548931121826,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5805,
      "step": 13
    },
    {
      "epoch": 0.009469056476158269,
      "grad_norm": 2.7482800483703613,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4344,
      "step": 14
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": 2.084956645965576,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2831,
      "step": 15
    },
    {
      "epoch": 0.010821778829895164,
      "grad_norm": 2.2843692302703857,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2555,
      "step": 16
    },
    {
      "epoch": 0.011498140006763611,
      "grad_norm": 2.4289393424987793,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2187,
      "step": 17
    },
    {
      "epoch": 0.01217450118363206,
      "grad_norm": 1.5535458326339722,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1884,
      "step": 18
    },
    {
      "epoch": 0.012850862360500507,
      "grad_norm": 3.9618098735809326,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.4397,
      "step": 19
    },
    {
      "epoch": 0.013527223537368955,
      "grad_norm": 7.029224872589111,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.333,
      "step": 20
    },
    {
      "epoch": 0.014203584714237404,
      "grad_norm": 1.9972093105316162,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.247,
      "step": 21
    },
    {
      "epoch": 0.014879945891105851,
      "grad_norm": 1.6639236211776733,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2382,
      "step": 22
    },
    {
      "epoch": 0.015556307067974298,
      "grad_norm": 0.9688037037849426,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1244,
      "step": 23
    },
    {
      "epoch": 0.016232668244842745,
      "grad_norm": 1.9547988176345825,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1513,
      "step": 24
    },
    {
      "epoch": 0.016909029421711193,
      "grad_norm": 2.206631898880005,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.221,
      "step": 25
    },
    {
      "epoch": 0.016909029421711193,
      "eval_loss": 0.2763649821281433,
      "eval_runtime": 87.6991,
      "eval_samples_per_second": 28.393,
      "eval_steps_per_second": 3.558,
      "step": 25
    },
    {
      "epoch": 0.01758539059857964,
      "grad_norm": 2.093113660812378,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.25,
      "step": 26
    },
    {
      "epoch": 0.01826175177544809,
      "grad_norm": 1.6162835359573364,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2373,
      "step": 27
    },
    {
      "epoch": 0.018938112952316538,
      "grad_norm": 1.4689679145812988,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1982,
      "step": 28
    },
    {
      "epoch": 0.019614474129184985,
      "grad_norm": 0.8921065926551819,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.156,
      "step": 29
    },
    {
      "epoch": 0.020290835306053433,
      "grad_norm": 0.7960008978843689,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1295,
      "step": 30
    },
    {
      "epoch": 0.02096719648292188,
      "grad_norm": 0.8615506291389465,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1504,
      "step": 31
    },
    {
      "epoch": 0.021643557659790327,
      "grad_norm": 0.9851981997489929,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1528,
      "step": 32
    },
    {
      "epoch": 0.022319918836658775,
      "grad_norm": 0.8852011561393738,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.163,
      "step": 33
    },
    {
      "epoch": 0.022996280013527222,
      "grad_norm": 0.9167941212654114,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1478,
      "step": 34
    },
    {
      "epoch": 0.023672641190395673,
      "grad_norm": 0.6924282312393188,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1175,
      "step": 35
    },
    {
      "epoch": 0.02434900236726412,
      "grad_norm": 0.7075855135917664,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0975,
      "step": 36
    },
    {
      "epoch": 0.025025363544132567,
      "grad_norm": 0.8667000532150269,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0851,
      "step": 37
    },
    {
      "epoch": 0.025701724721001015,
      "grad_norm": 0.6054403781890869,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0999,
      "step": 38
    },
    {
      "epoch": 0.026378085897869462,
      "grad_norm": 0.723283588886261,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1018,
      "step": 39
    },
    {
      "epoch": 0.02705444707473791,
      "grad_norm": 0.8060293793678284,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0908,
      "step": 40
    },
    {
      "epoch": 0.027730808251606356,
      "grad_norm": 1.0525263547897339,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.126,
      "step": 41
    },
    {
      "epoch": 0.028407169428474807,
      "grad_norm": 0.8337423205375671,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1003,
      "step": 42
    },
    {
      "epoch": 0.029083530605343254,
      "grad_norm": 0.7337478995323181,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1106,
      "step": 43
    },
    {
      "epoch": 0.029759891782211702,
      "grad_norm": 0.8262754678726196,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1441,
      "step": 44
    },
    {
      "epoch": 0.03043625295908015,
      "grad_norm": 0.834556519985199,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1245,
      "step": 45
    },
    {
      "epoch": 0.031112614135948596,
      "grad_norm": 1.1409804821014404,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1717,
      "step": 46
    },
    {
      "epoch": 0.03178897531281705,
      "grad_norm": 0.7930788397789001,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1191,
      "step": 47
    },
    {
      "epoch": 0.03246533648968549,
      "grad_norm": 0.903258740901947,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1307,
      "step": 48
    },
    {
      "epoch": 0.03314169766655394,
      "grad_norm": 1.2521153688430786,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.169,
      "step": 49
    },
    {
      "epoch": 0.033818058843422386,
      "grad_norm": 1.3574105501174927,
      "learning_rate": 0.0,
      "loss": 0.172,
      "step": 50
    },
    {
      "epoch": 0.033818058843422386,
      "eval_loss": 0.12468638271093369,
      "eval_runtime": 87.9013,
      "eval_samples_per_second": 28.327,
      "eval_steps_per_second": 3.549,
      "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": 2.1554035106512896e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}