{
  "best_metric": 1.0543670654296875,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.4103405826836274,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008206811653672548,
      "eval_loss": 1.1878700256347656,
      "eval_runtime": 18.2929,
      "eval_samples_per_second": 28.098,
      "eval_steps_per_second": 7.052,
      "step": 1
    },
    {
      "epoch": 0.008206811653672548,
      "grad_norm": 0.729353129863739,
      "learning_rate": 4.12e-05,
      "loss": 1.1518,
      "step": 10
    },
    {
      "epoch": 0.016413623307345096,
      "grad_norm": 0.9635369777679443,
      "learning_rate": 8.24e-05,
      "loss": 1.1163,
      "step": 20
    },
    {
      "epoch": 0.024620434961017644,
      "grad_norm": 1.069427251815796,
      "learning_rate": 0.0001236,
      "loss": 0.9047,
      "step": 30
    },
    {
      "epoch": 0.03282724661469019,
      "grad_norm": 1.3648443222045898,
      "learning_rate": 0.0001648,
      "loss": 1.0777,
      "step": 40
    },
    {
      "epoch": 0.04103405826836274,
      "grad_norm": 2.9773006439208984,
      "learning_rate": 0.000206,
      "loss": 1.0481,
      "step": 50
    },
    {
      "epoch": 0.04103405826836274,
      "eval_loss": 1.144477367401123,
      "eval_runtime": 18.2417,
      "eval_samples_per_second": 28.177,
      "eval_steps_per_second": 7.072,
      "step": 50
    },
    {
      "epoch": 0.04924086992203529,
      "grad_norm": 0.6259267330169678,
      "learning_rate": 0.0002057490971767619,
      "loss": 1.1447,
      "step": 60
    },
    {
      "epoch": 0.057447681575707836,
      "grad_norm": 0.7413045167922974,
      "learning_rate": 0.00020499761108038175,
      "loss": 1.0183,
      "step": 70
    },
    {
      "epoch": 0.06565449322938038,
      "grad_norm": 0.8103037476539612,
      "learning_rate": 0.00020374920287558198,
      "loss": 1.0053,
      "step": 80
    },
    {
      "epoch": 0.07386130488305294,
      "grad_norm": 1.245359182357788,
      "learning_rate": 0.00020200995468164684,
      "loss": 0.975,
      "step": 90
    },
    {
      "epoch": 0.08206811653672548,
      "grad_norm": 3.7838215827941895,
      "learning_rate": 0.00019978833994094855,
      "loss": 1.0289,
      "step": 100
    },
    {
      "epoch": 0.08206811653672548,
      "eval_loss": 1.1723737716674805,
      "eval_runtime": 15.3947,
      "eval_samples_per_second": 33.388,
      "eval_steps_per_second": 8.38,
      "step": 100
    },
    {
      "epoch": 0.09027492819039803,
      "grad_norm": 0.5712428689002991,
      "learning_rate": 0.00019709518213718787,
      "loss": 1.1583,
      "step": 110
    },
    {
      "epoch": 0.09848173984407058,
      "grad_norm": 0.7540761828422546,
      "learning_rate": 0.00019394360206446948,
      "loss": 0.9766,
      "step": 120
    },
    {
      "epoch": 0.10668855149774313,
      "grad_norm": 0.9592521786689758,
      "learning_rate": 0.00019034895390411186,
      "loss": 0.8982,
      "step": 130
    },
    {
      "epoch": 0.11489536315141567,
      "grad_norm": 1.3090097904205322,
      "learning_rate": 0.0001863287504206196,
      "loss": 1.0175,
      "step": 140
    },
    {
      "epoch": 0.12310217480508823,
      "grad_norm": 3.294684648513794,
      "learning_rate": 0.00018190257764125471,
      "loss": 1.0706,
      "step": 150
    },
    {
      "epoch": 0.12310217480508823,
      "eval_loss": 1.1268848180770874,
      "eval_runtime": 15.3842,
      "eval_samples_per_second": 33.411,
      "eval_steps_per_second": 8.385,
      "step": 150
    },
    {
      "epoch": 0.13130898645876077,
      "grad_norm": 0.576910138130188,
      "learning_rate": 0.00017709199943488106,
      "loss": 1.1748,
      "step": 160
    },
    {
      "epoch": 0.1395157981124333,
      "grad_norm": 0.7526901960372925,
      "learning_rate": 0.00017192045245496238,
      "loss": 1.0722,
      "step": 170
    },
    {
      "epoch": 0.14772260976610588,
      "grad_norm": 0.8360763788223267,
      "learning_rate": 0.00016641313195854277,
      "loss": 0.9735,
      "step": 180
    },
    {
      "epoch": 0.15592942141977842,
      "grad_norm": 1.3225890398025513,
      "learning_rate": 0.0001605968690574869,
      "loss": 1.023,
      "step": 190
    },
    {
      "epoch": 0.16413623307345096,
      "grad_norm": 2.138566017150879,
      "learning_rate": 0.0001545,
      "loss": 0.9754,
      "step": 200
    },
    {
      "epoch": 0.16413623307345096,
      "eval_loss": 1.113610863685608,
      "eval_runtime": 15.3089,
      "eval_samples_per_second": 33.575,
      "eval_steps_per_second": 8.426,
      "step": 200
    },
    {
      "epoch": 0.1723430447271235,
      "grad_norm": 0.5698345303535461,
      "learning_rate": 0.00014815222811927496,
      "loss": 1.0794,
      "step": 210
    },
    {
      "epoch": 0.18054985638079607,
      "grad_norm": 0.649773120880127,
      "learning_rate": 0.00014158447912183896,
      "loss": 1.1388,
      "step": 220
    },
    {
      "epoch": 0.1887566680344686,
      "grad_norm": 0.837361216545105,
      "learning_rate": 0.00013482875042061958,
      "loss": 0.8766,
      "step": 230
    },
    {
      "epoch": 0.19696347968814115,
      "grad_norm": 1.3855682611465454,
      "learning_rate": 0.00012791795524676576,
      "loss": 1.0241,
      "step": 240
    },
    {
      "epoch": 0.2051702913418137,
      "grad_norm": 2.690157651901245,
      "learning_rate": 0.00012088576229969385,
      "loss": 1.1411,
      "step": 250
    },
    {
      "epoch": 0.2051702913418137,
      "eval_loss": 1.0915905237197876,
      "eval_runtime": 15.3729,
      "eval_samples_per_second": 33.435,
      "eval_steps_per_second": 8.391,
      "step": 250
    },
    {
      "epoch": 0.21337710299548626,
      "grad_norm": 0.5115095376968384,
      "learning_rate": 0.0001137664317165683,
      "loss": 1.1718,
      "step": 260
    },
    {
      "epoch": 0.2215839146491588,
      "grad_norm": 0.6826813817024231,
      "learning_rate": 0.00010659464816035761,
      "loss": 0.9738,
      "step": 270
    },
    {
      "epoch": 0.22979072630283134,
      "grad_norm": 0.9111493825912476,
      "learning_rate": 9.940535183964242e-05,
      "loss": 0.9628,
      "step": 280
    },
    {
      "epoch": 0.23799753795650389,
      "grad_norm": 1.078299880027771,
      "learning_rate": 9.22335682834317e-05,
      "loss": 0.9982,
      "step": 290
    },
    {
      "epoch": 0.24620434961017645,
      "grad_norm": 2.671276569366455,
      "learning_rate": 8.511423770030617e-05,
      "loss": 1.0608,
      "step": 300
    },
    {
      "epoch": 0.24620434961017645,
      "eval_loss": 1.0737028121948242,
      "eval_runtime": 15.3598,
      "eval_samples_per_second": 33.464,
      "eval_steps_per_second": 8.399,
      "step": 300
    },
    {
      "epoch": 0.254411161263849,
      "grad_norm": 0.5804088711738586,
      "learning_rate": 7.808204475323423e-05,
      "loss": 1.1385,
      "step": 310
    },
    {
      "epoch": 0.26261797291752154,
      "grad_norm": 0.6363312005996704,
      "learning_rate": 7.117124957938042e-05,
      "loss": 1.1077,
      "step": 320
    },
    {
      "epoch": 0.2708247845711941,
      "grad_norm": 0.8315023183822632,
      "learning_rate": 6.441552087816105e-05,
      "loss": 0.9457,
      "step": 330
    },
    {
      "epoch": 0.2790315962248666,
      "grad_norm": 1.0781985521316528,
      "learning_rate": 5.784777188072502e-05,
      "loss": 1.0429,
      "step": 340
    },
    {
      "epoch": 0.2872384078785392,
      "grad_norm": 3.285376787185669,
      "learning_rate": 5.150000000000002e-05,
      "loss": 1.0404,
      "step": 350
    },
    {
      "epoch": 0.2872384078785392,
      "eval_loss": 1.0614588260650635,
      "eval_runtime": 15.4388,
      "eval_samples_per_second": 33.293,
      "eval_steps_per_second": 8.356,
      "step": 350
    },
    {
      "epoch": 0.29544521953221176,
      "grad_norm": 0.626628577709198,
      "learning_rate": 4.540313094251309e-05,
      "loss": 1.1582,
      "step": 360
    },
    {
      "epoch": 0.3036520311858843,
      "grad_norm": 0.6858929395675659,
      "learning_rate": 3.958686804145719e-05,
      "loss": 0.9412,
      "step": 370
    },
    {
      "epoch": 0.31185884283955684,
      "grad_norm": 0.8179978132247925,
      "learning_rate": 3.4079547545037634e-05,
      "loss": 0.9513,
      "step": 380
    },
    {
      "epoch": 0.3200656544932294,
      "grad_norm": 1.1536400318145752,
      "learning_rate": 2.8908000565118947e-05,
      "loss": 1.0401,
      "step": 390
    },
    {
      "epoch": 0.3282724661469019,
      "grad_norm": 3.0569396018981934,
      "learning_rate": 2.4097422358745275e-05,
      "loss": 0.9828,
      "step": 400
    },
    {
      "epoch": 0.3282724661469019,
      "eval_loss": 1.0560269355773926,
      "eval_runtime": 15.4762,
      "eval_samples_per_second": 33.212,
      "eval_steps_per_second": 8.335,
      "step": 400
    },
    {
      "epoch": 0.33647927780057446,
      "grad_norm": 0.5393869280815125,
      "learning_rate": 1.9671249579380422e-05,
      "loss": 1.0985,
      "step": 410
    },
    {
      "epoch": 0.344686089454247,
      "grad_norm": 0.682307779788971,
      "learning_rate": 1.5651046095888127e-05,
      "loss": 0.9939,
      "step": 420
    },
    {
      "epoch": 0.3528929011079196,
      "grad_norm": 0.7832779884338379,
      "learning_rate": 1.205639793553052e-05,
      "loss": 0.9002,
      "step": 430
    },
    {
      "epoch": 0.36109971276159214,
      "grad_norm": 1.3836650848388672,
      "learning_rate": 8.904817862812098e-06,
      "loss": 1.0236,
      "step": 440
    },
    {
      "epoch": 0.3693065244152647,
      "grad_norm": 2.9043712615966797,
      "learning_rate": 6.211660059051443e-06,
      "loss": 0.9821,
      "step": 450
    },
    {
      "epoch": 0.3693065244152647,
      "eval_loss": 1.0554460287094116,
      "eval_runtime": 15.4638,
      "eval_samples_per_second": 33.239,
      "eval_steps_per_second": 8.342,
      "step": 450
    },
    {
      "epoch": 0.3775133360689372,
      "grad_norm": 0.5127935409545898,
      "learning_rate": 3.990045318353154e-06,
      "loss": 1.1652,
      "step": 460
    },
    {
      "epoch": 0.38572014772260976,
      "grad_norm": 0.6893414855003357,
      "learning_rate": 2.250797124418014e-06,
      "loss": 0.9786,
      "step": 470
    },
    {
      "epoch": 0.3939269593762823,
      "grad_norm": 0.8294914364814758,
      "learning_rate": 1.0023889196182526e-06,
      "loss": 0.9483,
      "step": 480
    },
    {
      "epoch": 0.40213377102995485,
      "grad_norm": 2.3308422565460205,
      "learning_rate": 2.5090282323810766e-07,
      "loss": 0.9799,
      "step": 490
    },
    {
      "epoch": 0.4103405826836274,
      "grad_norm": 3.107800006866455,
      "learning_rate": 0.0,
      "loss": 1.0891,
      "step": 500
    },
    {
      "epoch": 0.4103405826836274,
      "eval_loss": 1.0543670654296875,
      "eval_runtime": 15.5961,
      "eval_samples_per_second": 32.957,
      "eval_steps_per_second": 8.271,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 2.056393621241856e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}