{
  "best_metric": 0.53005450963974,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.17061611374407584,
  "eval_steps": 150,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003791469194312796,
      "eval_loss": 1.7795168161392212,
      "eval_runtime": 209.8549,
      "eval_samples_per_second": 21.167,
      "eval_steps_per_second": 5.294,
      "step": 1
    },
    {
      "epoch": 0.0037914691943127963,
      "grad_norm": 2.3918707370758057,
      "learning_rate": 2e-05,
      "loss": 2.1878,
      "step": 10
    },
    {
      "epoch": 0.007582938388625593,
      "grad_norm": 1.775721788406372,
      "learning_rate": 4e-05,
      "loss": 1.257,
      "step": 20
    },
    {
      "epoch": 0.011374407582938388,
      "grad_norm": 1.3155328035354614,
      "learning_rate": 6e-05,
      "loss": 0.7683,
      "step": 30
    },
    {
      "epoch": 0.015165876777251185,
      "grad_norm": 1.3514695167541504,
      "learning_rate": 8e-05,
      "loss": 0.5549,
      "step": 40
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 1.1452535390853882,
      "learning_rate": 0.0001,
      "loss": 0.3957,
      "step": 50
    },
    {
      "epoch": 0.022748815165876776,
      "grad_norm": 1.4056144952774048,
      "learning_rate": 9.999631611658893e-05,
      "loss": 1.3166,
      "step": 60
    },
    {
      "epoch": 0.026540284360189573,
      "grad_norm": 1.0476895570755005,
      "learning_rate": 9.998526500919558e-05,
      "loss": 0.6856,
      "step": 70
    },
    {
      "epoch": 0.03033175355450237,
      "grad_norm": 1.057721495628357,
      "learning_rate": 9.996684830625961e-05,
      "loss": 0.5876,
      "step": 80
    },
    {
      "epoch": 0.034123222748815164,
      "grad_norm": 0.8883450627326965,
      "learning_rate": 9.99410687215805e-05,
      "loss": 0.5092,
      "step": 90
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 1.0792176723480225,
      "learning_rate": 9.990793005391757e-05,
      "loss": 0.3727,
      "step": 100
    },
    {
      "epoch": 0.04170616113744076,
      "grad_norm": 0.9899026155471802,
      "learning_rate": 9.986743718643037e-05,
      "loss": 1.0962,
      "step": 110
    },
    {
      "epoch": 0.04549763033175355,
      "grad_norm": 0.9852607250213623,
      "learning_rate": 9.981959608595904e-05,
      "loss": 0.6074,
      "step": 120
    },
    {
      "epoch": 0.04928909952606635,
      "grad_norm": 0.8935758471488953,
      "learning_rate": 9.976441380214499e-05,
      "loss": 0.5443,
      "step": 130
    },
    {
      "epoch": 0.05308056872037915,
      "grad_norm": 0.8601885437965393,
      "learning_rate": 9.970189846639224e-05,
      "loss": 0.4588,
      "step": 140
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 0.8278557658195496,
      "learning_rate": 9.963205929066912e-05,
      "loss": 0.3571,
      "step": 150
    },
    {
      "epoch": 0.05687203791469194,
      "eval_loss": 0.6163225173950195,
      "eval_runtime": 211.3771,
      "eval_samples_per_second": 21.015,
      "eval_steps_per_second": 5.256,
      "step": 150
    },
    {
      "epoch": 0.06066350710900474,
      "grad_norm": 0.9639042019844055,
      "learning_rate": 9.955490656615086e-05,
      "loss": 0.9907,
      "step": 160
    },
    {
      "epoch": 0.06445497630331753,
      "grad_norm": 1.0571763515472412,
      "learning_rate": 9.947045166170315e-05,
      "loss": 0.6059,
      "step": 170
    },
    {
      "epoch": 0.06824644549763033,
      "grad_norm": 0.8203420639038086,
      "learning_rate": 9.937870702220684e-05,
      "loss": 0.5407,
      "step": 180
    },
    {
      "epoch": 0.07203791469194312,
      "grad_norm": 0.7809204459190369,
      "learning_rate": 9.927968616672416e-05,
      "loss": 0.4592,
      "step": 190
    },
    {
      "epoch": 0.07582938388625593,
      "grad_norm": 0.6434981226921082,
      "learning_rate": 9.917340368650657e-05,
      "loss": 0.3295,
      "step": 200
    },
    {
      "epoch": 0.07962085308056872,
      "grad_norm": 0.8934921026229858,
      "learning_rate": 9.905987524284471e-05,
      "loss": 0.9521,
      "step": 210
    },
    {
      "epoch": 0.08341232227488152,
      "grad_norm": 0.8254252672195435,
      "learning_rate": 9.89391175647606e-05,
      "loss": 0.5738,
      "step": 220
    },
    {
      "epoch": 0.08720379146919431,
      "grad_norm": 0.840071976184845,
      "learning_rate": 9.881114844654249e-05,
      "loss": 0.5222,
      "step": 230
    },
    {
      "epoch": 0.0909952606635071,
      "grad_norm": 0.8142471313476562,
      "learning_rate": 9.867598674512288e-05,
      "loss": 0.4142,
      "step": 240
    },
    {
      "epoch": 0.0947867298578199,
      "grad_norm": 0.6625562310218811,
      "learning_rate": 9.853365237729976e-05,
      "loss": 0.3158,
      "step": 250
    },
    {
      "epoch": 0.0985781990521327,
      "grad_norm": 0.9738134145736694,
      "learning_rate": 9.838416631680176e-05,
      "loss": 0.9377,
      "step": 260
    },
    {
      "epoch": 0.1023696682464455,
      "grad_norm": 0.919395387172699,
      "learning_rate": 9.822755059119765e-05,
      "loss": 0.5472,
      "step": 270
    },
    {
      "epoch": 0.1061611374407583,
      "grad_norm": 0.9126551151275635,
      "learning_rate": 9.806382827865035e-05,
      "loss": 0.4959,
      "step": 280
    },
    {
      "epoch": 0.10995260663507109,
      "grad_norm": 0.7662134766578674,
      "learning_rate": 9.78930235045163e-05,
      "loss": 0.4471,
      "step": 290
    },
    {
      "epoch": 0.11374407582938388,
      "grad_norm": 0.6991143226623535,
      "learning_rate": 9.771516143779049e-05,
      "loss": 0.345,
      "step": 300
    },
    {
      "epoch": 0.11374407582938388,
      "eval_loss": 0.5615507960319519,
      "eval_runtime": 210.9515,
      "eval_samples_per_second": 21.057,
      "eval_steps_per_second": 5.267,
      "step": 300
    },
    {
      "epoch": 0.11753554502369669,
      "grad_norm": 0.8847883343696594,
      "learning_rate": 9.753026828739756e-05,
      "loss": 0.9371,
      "step": 310
    },
    {
      "epoch": 0.12132701421800948,
      "grad_norm": 0.840414822101593,
      "learning_rate": 9.733837129832993e-05,
      "loss": 0.5609,
      "step": 320
    },
    {
      "epoch": 0.12511848341232226,
      "grad_norm": 0.8552011251449585,
      "learning_rate": 9.713949874763296e-05,
      "loss": 0.4904,
      "step": 330
    },
    {
      "epoch": 0.12890995260663507,
      "grad_norm": 0.7504507899284363,
      "learning_rate": 9.693367994023828e-05,
      "loss": 0.4276,
      "step": 340
    },
    {
      "epoch": 0.13270142180094788,
      "grad_norm": 0.7728025317192078,
      "learning_rate": 9.672094520464552e-05,
      "loss": 0.3153,
      "step": 350
    },
    {
      "epoch": 0.13649289099526066,
      "grad_norm": 0.8927388191223145,
      "learning_rate": 9.650132588845318e-05,
      "loss": 0.8539,
      "step": 360
    },
    {
      "epoch": 0.14028436018957346,
      "grad_norm": 0.9280526638031006,
      "learning_rate": 9.627485435373948e-05,
      "loss": 0.5319,
      "step": 370
    },
    {
      "epoch": 0.14407582938388624,
      "grad_norm": 0.8443691730499268,
      "learning_rate": 9.604156397229367e-05,
      "loss": 0.4799,
      "step": 380
    },
    {
      "epoch": 0.14786729857819905,
      "grad_norm": 0.8244546055793762,
      "learning_rate": 9.580148912069836e-05,
      "loss": 0.4255,
      "step": 390
    },
    {
      "epoch": 0.15165876777251186,
      "grad_norm": 0.587851881980896,
      "learning_rate": 9.555466517526405e-05,
      "loss": 0.3149,
      "step": 400
    },
    {
      "epoch": 0.15545023696682464,
      "grad_norm": 0.9294399619102478,
      "learning_rate": 9.53011285068163e-05,
      "loss": 0.8398,
      "step": 410
    },
    {
      "epoch": 0.15924170616113745,
      "grad_norm": 0.8756105303764343,
      "learning_rate": 9.50409164753362e-05,
      "loss": 0.5178,
      "step": 420
    },
    {
      "epoch": 0.16303317535545023,
      "grad_norm": 0.7490562796592712,
      "learning_rate": 9.477406742445516e-05,
      "loss": 0.4677,
      "step": 430
    },
    {
      "epoch": 0.16682464454976303,
      "grad_norm": 0.8731195330619812,
      "learning_rate": 9.450062067580488e-05,
      "loss": 0.4073,
      "step": 440
    },
    {
      "epoch": 0.17061611374407584,
      "grad_norm": 0.7838053107261658,
      "learning_rate": 9.422061652322298e-05,
      "loss": 0.2986,
      "step": 450
    },
    {
      "epoch": 0.17061611374407584,
      "eval_loss": 0.53005450963974,
      "eval_runtime": 211.0482,
      "eval_samples_per_second": 21.047,
      "eval_steps_per_second": 5.264,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 2638,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.9862471318359245e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}