{
  "best_metric": 0.5226322412490845,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.09402914903620123,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018805829807240243,
      "eval_loss": 1.0244735479354858,
      "eval_runtime": 110.7584,
      "eval_samples_per_second": 20.215,
      "eval_steps_per_second": 5.056,
      "step": 1
    },
    {
      "epoch": 0.0018805829807240243,
      "grad_norm": 1.312527060508728,
      "learning_rate": 4.24e-05,
      "loss": 1.1622,
      "step": 10
    },
    {
      "epoch": 0.0037611659614480487,
      "grad_norm": 1.2194122076034546,
      "learning_rate": 8.48e-05,
      "loss": 0.7124,
      "step": 20
    },
    {
      "epoch": 0.005641748942172073,
      "grad_norm": 0.9045761823654175,
      "learning_rate": 0.0001272,
      "loss": 0.558,
      "step": 30
    },
    {
      "epoch": 0.007522331922896097,
      "grad_norm": 0.840013325214386,
      "learning_rate": 0.0001696,
      "loss": 0.5548,
      "step": 40
    },
    {
      "epoch": 0.009402914903620122,
      "grad_norm": 1.0572164058685303,
      "learning_rate": 0.000212,
      "loss": 0.6082,
      "step": 50
    },
    {
      "epoch": 0.009402914903620122,
      "eval_loss": 0.6099416613578796,
      "eval_runtime": 110.8667,
      "eval_samples_per_second": 20.195,
      "eval_steps_per_second": 5.051,
      "step": 50
    },
    {
      "epoch": 0.011283497884344146,
      "grad_norm": 0.8899786472320557,
      "learning_rate": 0.00021174178932754136,
      "loss": 0.8371,
      "step": 60
    },
    {
      "epoch": 0.013164080865068171,
      "grad_norm": 0.8299662470817566,
      "learning_rate": 0.00021096841528660647,
      "loss": 0.5882,
      "step": 70
    },
    {
      "epoch": 0.015044663845792195,
      "grad_norm": 0.7784881591796875,
      "learning_rate": 0.0002096836456777834,
      "loss": 0.5139,
      "step": 80
    },
    {
      "epoch": 0.01692524682651622,
      "grad_norm": 1.0369268655776978,
      "learning_rate": 0.00020789373976946182,
      "loss": 0.5615,
      "step": 90
    },
    {
      "epoch": 0.018805829807240243,
      "grad_norm": 0.8029696941375732,
      "learning_rate": 0.0002056074178033063,
      "loss": 0.477,
      "step": 100
    },
    {
      "epoch": 0.018805829807240243,
      "eval_loss": 0.5923790335655212,
      "eval_runtime": 110.746,
      "eval_samples_per_second": 20.217,
      "eval_steps_per_second": 5.057,
      "step": 100
    },
    {
      "epoch": 0.020686412787964268,
      "grad_norm": 0.7454051971435547,
      "learning_rate": 0.00020283581851011567,
      "loss": 0.7692,
      "step": 110
    },
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 0.7566020488739014,
      "learning_rate": 0.00019959244484304625,
      "loss": 0.6041,
      "step": 120
    },
    {
      "epoch": 0.024447578749412318,
      "grad_norm": 0.8764553070068359,
      "learning_rate": 0.00019589309819258114,
      "loss": 0.4961,
      "step": 130
    },
    {
      "epoch": 0.026328161730136343,
      "grad_norm": 0.8373245596885681,
      "learning_rate": 0.00019175580140374444,
      "loss": 0.547,
      "step": 140
    },
    {
      "epoch": 0.028208744710860368,
      "grad_norm": 0.7634709477424622,
      "learning_rate": 0.00018720071097061167,
      "loss": 0.4938,
      "step": 150
    },
    {
      "epoch": 0.028208744710860368,
      "eval_loss": 0.5824873447418213,
      "eval_runtime": 110.6291,
      "eval_samples_per_second": 20.239,
      "eval_steps_per_second": 5.062,
      "step": 150
    },
    {
      "epoch": 0.03008932769158439,
      "grad_norm": 0.7595392465591431,
      "learning_rate": 0.00018225001883589702,
      "loss": 0.6898,
      "step": 160
    },
    {
      "epoch": 0.031969910672308414,
      "grad_norm": 0.759728193283081,
      "learning_rate": 0.00017692784427403898,
      "loss": 0.597,
      "step": 170
    },
    {
      "epoch": 0.03385049365303244,
      "grad_norm": 0.7240564823150635,
      "learning_rate": 0.00017126011638451976,
      "loss": 0.5055,
      "step": 180
    },
    {
      "epoch": 0.035731076633756464,
      "grad_norm": 0.8146303296089172,
      "learning_rate": 0.00016527444776789915,
      "loss": 0.5259,
      "step": 190
    },
    {
      "epoch": 0.037611659614480486,
      "grad_norm": 0.9344813823699951,
      "learning_rate": 0.00015900000000000002,
      "loss": 0.4835,
      "step": 200
    },
    {
      "epoch": 0.037611659614480486,
      "eval_loss": 0.5645079612731934,
      "eval_runtime": 110.3239,
      "eval_samples_per_second": 20.295,
      "eval_steps_per_second": 5.076,
      "step": 200
    },
    {
      "epoch": 0.039492242595204514,
      "grad_norm": 0.7228832244873047,
      "learning_rate": 0.0001524673415596422,
      "loss": 0.7051,
      "step": 210
    },
    {
      "epoch": 0.041372825575928536,
      "grad_norm": 0.7438748478889465,
      "learning_rate": 0.00014570829890208668,
      "loss": 0.5814,
      "step": 220
    },
    {
      "epoch": 0.043253408556652564,
      "grad_norm": 0.8777850866317749,
      "learning_rate": 0.00013875580140374443,
      "loss": 0.5303,
      "step": 230
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.7555531859397888,
      "learning_rate": 0.00013164372093356477,
      "loss": 0.4952,
      "step": 240
    },
    {
      "epoch": 0.047014574518100614,
      "grad_norm": 0.8109617233276367,
      "learning_rate": 0.00012440670683269464,
      "loss": 0.4875,
      "step": 250
    },
    {
      "epoch": 0.047014574518100614,
      "eval_loss": 0.5527585744857788,
      "eval_runtime": 110.855,
      "eval_samples_per_second": 20.198,
      "eval_steps_per_second": 5.052,
      "step": 250
    },
    {
      "epoch": 0.048895157498824636,
      "grad_norm": 0.7539621591567993,
      "learning_rate": 0.00011708001710637128,
      "loss": 0.6915,
      "step": 260
    },
    {
      "epoch": 0.05077574047954866,
      "grad_norm": 0.7228267788887024,
      "learning_rate": 0.00010969934665046512,
      "loss": 0.5286,
      "step": 270
    },
    {
      "epoch": 0.052656323460272686,
      "grad_norm": 0.774669885635376,
      "learning_rate": 0.00010230065334953492,
      "loss": 0.5363,
      "step": 280
    },
    {
      "epoch": 0.05453690644099671,
      "grad_norm": 0.7888806462287903,
      "learning_rate": 9.491998289362875e-05,
      "loss": 0.5055,
      "step": 290
    },
    {
      "epoch": 0.056417489421720736,
      "grad_norm": 1.0556362867355347,
      "learning_rate": 8.759329316730539e-05,
      "loss": 0.499,
      "step": 300
    },
    {
      "epoch": 0.056417489421720736,
      "eval_loss": 0.5459651947021484,
      "eval_runtime": 110.2865,
      "eval_samples_per_second": 20.302,
      "eval_steps_per_second": 5.078,
      "step": 300
    },
    {
      "epoch": 0.05829807240244476,
      "grad_norm": 0.7479456067085266,
      "learning_rate": 8.035627906643523e-05,
      "loss": 0.7484,
      "step": 310
    },
    {
      "epoch": 0.06017865538316878,
      "grad_norm": 0.852773129940033,
      "learning_rate": 7.324419859625559e-05,
      "loss": 0.588,
      "step": 320
    },
    {
      "epoch": 0.06205923836389281,
      "grad_norm": 0.653623640537262,
      "learning_rate": 6.629170109791332e-05,
      "loss": 0.5215,
      "step": 330
    },
    {
      "epoch": 0.06393982134461683,
      "grad_norm": 0.9154057502746582,
      "learning_rate": 5.9532658440357784e-05,
      "loss": 0.4859,
      "step": 340
    },
    {
      "epoch": 0.06582040432534085,
      "grad_norm": 0.7963242530822754,
      "learning_rate": 5.300000000000002e-05,
      "loss": 0.4577,
      "step": 350
    },
    {
      "epoch": 0.06582040432534085,
      "eval_loss": 0.5348652005195618,
      "eval_runtime": 110.893,
      "eval_samples_per_second": 20.191,
      "eval_steps_per_second": 5.05,
      "step": 350
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.721904456615448,
      "learning_rate": 4.672555223210085e-05,
      "loss": 0.6492,
      "step": 360
    },
    {
      "epoch": 0.06958157028678891,
      "grad_norm": 0.5901376605033875,
      "learning_rate": 4.073988361548022e-05,
      "loss": 0.5297,
      "step": 370
    },
    {
      "epoch": 0.07146215326751293,
      "grad_norm": 0.7072864770889282,
      "learning_rate": 3.507215572596106e-05,
      "loss": 0.516,
      "step": 380
    },
    {
      "epoch": 0.07334273624823695,
      "grad_norm": 0.7061730623245239,
      "learning_rate": 2.9749981164102997e-05,
      "loss": 0.507,
      "step": 390
    },
    {
      "epoch": 0.07522331922896097,
      "grad_norm": 0.810987114906311,
      "learning_rate": 2.479928902938834e-05,
      "loss": 0.4757,
      "step": 400
    },
    {
      "epoch": 0.07522331922896097,
      "eval_loss": 0.528462827205658,
      "eval_runtime": 110.7354,
      "eval_samples_per_second": 20.219,
      "eval_steps_per_second": 5.057,
      "step": 400
    },
    {
      "epoch": 0.07710390220968501,
      "grad_norm": 1.0959731340408325,
      "learning_rate": 2.024419859625558e-05,
      "loss": 0.7066,
      "step": 410
    },
    {
      "epoch": 0.07898448519040903,
      "grad_norm": 0.6210688948631287,
      "learning_rate": 1.610690180741885e-05,
      "loss": 0.5475,
      "step": 420
    },
    {
      "epoch": 0.08086506817113305,
      "grad_norm": 0.6310533881187439,
      "learning_rate": 1.240755515695374e-05,
      "loss": 0.4826,
      "step": 430
    },
    {
      "epoch": 0.08274565115185707,
      "grad_norm": 0.6733012199401855,
      "learning_rate": 9.164181489884296e-06,
      "loss": 0.4465,
      "step": 440
    },
    {
      "epoch": 0.0846262341325811,
      "grad_norm": 0.8576263785362244,
      "learning_rate": 6.392582196693718e-06,
      "loss": 0.47,
      "step": 450
    },
    {
      "epoch": 0.0846262341325811,
      "eval_loss": 0.524067223072052,
      "eval_runtime": 110.922,
      "eval_samples_per_second": 20.185,
      "eval_steps_per_second": 5.049,
      "step": 450
    },
    {
      "epoch": 0.08650681711330513,
      "grad_norm": 0.9640802145004272,
      "learning_rate": 4.106260230538197e-06,
      "loss": 0.6474,
      "step": 460
    },
    {
      "epoch": 0.08838740009402915,
      "grad_norm": 0.6373594403266907,
      "learning_rate": 2.316354322216597e-06,
      "loss": 0.5344,
      "step": 470
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.6497265696525574,
      "learning_rate": 1.0315847133935416e-06,
      "loss": 0.5107,
      "step": 480
    },
    {
      "epoch": 0.0921485660554772,
      "grad_norm": 0.7859962582588196,
      "learning_rate": 2.582106724586351e-07,
      "loss": 0.4527,
      "step": 490
    },
    {
      "epoch": 0.09402914903620123,
      "grad_norm": 0.8895713090896606,
      "learning_rate": 0.0,
      "loss": 0.4403,
      "step": 500
    },
    {
      "epoch": 0.09402914903620123,
      "eval_loss": 0.5226322412490845,
      "eval_runtime": 110.6062,
      "eval_samples_per_second": 20.243,
      "eval_steps_per_second": 5.063,
      "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": 5.442856891396915e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}