{
  "best_metric": 0.24534127116203308,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01704012950498424,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034080259009968474,
      "grad_norm": 10.045832633972168,
      "learning_rate": 2e-05,
      "loss": 0.6867,
      "step": 1
    },
    {
      "epoch": 0.00034080259009968474,
      "eval_loss": 1.7972990274429321,
      "eval_runtime": 42.891,
      "eval_samples_per_second": 115.222,
      "eval_steps_per_second": 14.409,
      "step": 1
    },
    {
      "epoch": 0.0006816051801993695,
      "grad_norm": 16.62306785583496,
      "learning_rate": 4e-05,
      "loss": 0.808,
      "step": 2
    },
    {
      "epoch": 0.0010224077702990543,
      "grad_norm": 13.757551193237305,
      "learning_rate": 6e-05,
      "loss": 0.642,
      "step": 3
    },
    {
      "epoch": 0.001363210360398739,
      "grad_norm": 10.937745094299316,
      "learning_rate": 8e-05,
      "loss": 0.3912,
      "step": 4
    },
    {
      "epoch": 0.0017040129504984239,
      "grad_norm": 3.4071125984191895,
      "learning_rate": 0.0001,
      "loss": 0.1793,
      "step": 5
    },
    {
      "epoch": 0.0020448155405981086,
      "grad_norm": 2.5787136554718018,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.184,
      "step": 6
    },
    {
      "epoch": 0.0023856181306977932,
      "grad_norm": 1.7575210332870483,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1167,
      "step": 7
    },
    {
      "epoch": 0.002726420720797478,
      "grad_norm": 1.8779293298721313,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1493,
      "step": 8
    },
    {
      "epoch": 0.0030672233108971626,
      "grad_norm": 1.6708754301071167,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1705,
      "step": 9
    },
    {
      "epoch": 0.0034080259009968477,
      "grad_norm": 1.7135310173034668,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1628,
      "step": 10
    },
    {
      "epoch": 0.0037488284910965324,
      "grad_norm": 1.5308074951171875,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.144,
      "step": 11
    },
    {
      "epoch": 0.004089631081196217,
      "grad_norm": 1.7468814849853516,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.149,
      "step": 12
    },
    {
      "epoch": 0.004430433671295902,
      "grad_norm": 1.689357042312622,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1619,
      "step": 13
    },
    {
      "epoch": 0.0047712362613955865,
      "grad_norm": 2.216909885406494,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1863,
      "step": 14
    },
    {
      "epoch": 0.005112038851495271,
      "grad_norm": 3.2676494121551514,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.179,
      "step": 15
    },
    {
      "epoch": 0.005452841441594956,
      "grad_norm": 1.6037553548812866,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1509,
      "step": 16
    },
    {
      "epoch": 0.0057936440316946405,
      "grad_norm": 1.7801467180252075,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.177,
      "step": 17
    },
    {
      "epoch": 0.006134446621794325,
      "grad_norm": 4.736143112182617,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2079,
      "step": 18
    },
    {
      "epoch": 0.006475249211894011,
      "grad_norm": 1.4752039909362793,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.16,
      "step": 19
    },
    {
      "epoch": 0.0068160518019936955,
      "grad_norm": 1.4957607984542847,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2165,
      "step": 20
    },
    {
      "epoch": 0.00715685439209338,
      "grad_norm": 1.4677075147628784,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1744,
      "step": 21
    },
    {
      "epoch": 0.007497656982193065,
      "grad_norm": 1.628738522529602,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2143,
      "step": 22
    },
    {
      "epoch": 0.007838459572292749,
      "grad_norm": 1.7998496294021606,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2257,
      "step": 23
    },
    {
      "epoch": 0.008179262162392434,
      "grad_norm": 1.4488158226013184,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.158,
      "step": 24
    },
    {
      "epoch": 0.00852006475249212,
      "grad_norm": 1.4470431804656982,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1776,
      "step": 25
    },
    {
      "epoch": 0.00852006475249212,
      "eval_loss": 0.2562970817089081,
      "eval_runtime": 42.9251,
      "eval_samples_per_second": 115.131,
      "eval_steps_per_second": 14.397,
      "step": 25
    },
    {
      "epoch": 0.008860867342591804,
      "grad_norm": 1.486140489578247,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2159,
      "step": 26
    },
    {
      "epoch": 0.00920166993269149,
      "grad_norm": 1.8835890293121338,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2349,
      "step": 27
    },
    {
      "epoch": 0.009542472522791173,
      "grad_norm": 1.8669521808624268,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2159,
      "step": 28
    },
    {
      "epoch": 0.009883275112890859,
      "grad_norm": 1.622249722480774,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2197,
      "step": 29
    },
    {
      "epoch": 0.010224077702990542,
      "grad_norm": 2.078935384750366,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2029,
      "step": 30
    },
    {
      "epoch": 0.010564880293090228,
      "grad_norm": 1.943671703338623,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2141,
      "step": 31
    },
    {
      "epoch": 0.010905682883189912,
      "grad_norm": 1.981119990348816,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2017,
      "step": 32
    },
    {
      "epoch": 0.011246485473289597,
      "grad_norm": 2.3581714630126953,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2743,
      "step": 33
    },
    {
      "epoch": 0.011587288063389281,
      "grad_norm": 2.593571662902832,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.3099,
      "step": 34
    },
    {
      "epoch": 0.011928090653488967,
      "grad_norm": 1.9463130235671997,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2304,
      "step": 35
    },
    {
      "epoch": 0.01226889324358865,
      "grad_norm": 2.119544744491577,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2791,
      "step": 36
    },
    {
      "epoch": 0.012609695833688336,
      "grad_norm": 2.3796632289886475,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.3268,
      "step": 37
    },
    {
      "epoch": 0.012950498423788022,
      "grad_norm": 3.150411605834961,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4008,
      "step": 38
    },
    {
      "epoch": 0.013291301013887705,
      "grad_norm": 2.5175278186798096,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3034,
      "step": 39
    },
    {
      "epoch": 0.013632103603987391,
      "grad_norm": 2.4369542598724365,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3142,
      "step": 40
    },
    {
      "epoch": 0.013972906194087075,
      "grad_norm": 3.3217461109161377,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3605,
      "step": 41
    },
    {
      "epoch": 0.01431370878418676,
      "grad_norm": 2.68766188621521,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3525,
      "step": 42
    },
    {
      "epoch": 0.014654511374286444,
      "grad_norm": 3.276628017425537,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.4045,
      "step": 43
    },
    {
      "epoch": 0.01499531396438613,
      "grad_norm": 3.3158345222473145,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.4197,
      "step": 44
    },
    {
      "epoch": 0.015336116554485813,
      "grad_norm": 3.3790440559387207,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4011,
      "step": 45
    },
    {
      "epoch": 0.015676919144585497,
      "grad_norm": 3.6487362384796143,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4834,
      "step": 46
    },
    {
      "epoch": 0.016017721734685183,
      "grad_norm": 3.7635161876678467,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.45,
      "step": 47
    },
    {
      "epoch": 0.01635852432478487,
      "grad_norm": 3.297227621078491,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4442,
      "step": 48
    },
    {
      "epoch": 0.016699326914884554,
      "grad_norm": 4.7598795890808105,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.6405,
      "step": 49
    },
    {
      "epoch": 0.01704012950498424,
      "grad_norm": 4.400386810302734,
      "learning_rate": 0.0,
      "loss": 0.6194,
      "step": 50
    },
    {
      "epoch": 0.01704012950498424,
      "eval_loss": 0.24534127116203308,
      "eval_runtime": 42.9768,
      "eval_samples_per_second": 114.992,
      "eval_steps_per_second": 14.38,
      "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": 1932120607948800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}