{
  "best_metric": 1.8203463554382324,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07213055630691552,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014426111261383104,
      "grad_norm": 0.1684134304523468,
      "learning_rate": 5e-05,
      "loss": 1.8894,
      "step": 1
    },
    {
      "epoch": 0.0014426111261383104,
      "eval_loss": 1.9437681436538696,
      "eval_runtime": 3.8946,
      "eval_samples_per_second": 12.838,
      "eval_steps_per_second": 3.338,
      "step": 1
    },
    {
      "epoch": 0.002885222252276621,
      "grad_norm": 0.16422972083091736,
      "learning_rate": 0.0001,
      "loss": 1.9315,
      "step": 2
    },
    {
      "epoch": 0.004327833378414931,
      "grad_norm": 0.13707830011844635,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.9532,
      "step": 3
    },
    {
      "epoch": 0.005770444504553242,
      "grad_norm": 0.14224322140216827,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.9392,
      "step": 4
    },
    {
      "epoch": 0.007213055630691551,
      "grad_norm": 0.20727574825286865,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.9078,
      "step": 5
    },
    {
      "epoch": 0.008655666756829862,
      "grad_norm": 0.16922233998775482,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.9654,
      "step": 6
    },
    {
      "epoch": 0.010098277882968172,
      "grad_norm": 0.14379426836967468,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.9432,
      "step": 7
    },
    {
      "epoch": 0.011540889009106483,
      "grad_norm": 0.13675129413604736,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.9009,
      "step": 8
    },
    {
      "epoch": 0.012983500135244793,
      "grad_norm": 0.14494813978672028,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.8594,
      "step": 9
    },
    {
      "epoch": 0.014426111261383103,
      "grad_norm": 0.15567150712013245,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.8123,
      "step": 10
    },
    {
      "epoch": 0.015868722387521413,
      "grad_norm": 0.21382679045200348,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.722,
      "step": 11
    },
    {
      "epoch": 0.017311333513659724,
      "grad_norm": 0.33638474345207214,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.8336,
      "step": 12
    },
    {
      "epoch": 0.018753944639798036,
      "grad_norm": 0.14598216116428375,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.8457,
      "step": 13
    },
    {
      "epoch": 0.020196555765936344,
      "grad_norm": 0.11723075062036514,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.8374,
      "step": 14
    },
    {
      "epoch": 0.021639166892074655,
      "grad_norm": 0.1011219397187233,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.8727,
      "step": 15
    },
    {
      "epoch": 0.023081778018212967,
      "grad_norm": 0.10686147212982178,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.8905,
      "step": 16
    },
    {
      "epoch": 0.024524389144351275,
      "grad_norm": 0.11371371150016785,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.924,
      "step": 17
    },
    {
      "epoch": 0.025967000270489586,
      "grad_norm": 0.11590010672807693,
      "learning_rate": 7.75e-05,
      "loss": 1.9072,
      "step": 18
    },
    {
      "epoch": 0.027409611396627898,
      "grad_norm": 0.11954373121261597,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.8765,
      "step": 19
    },
    {
      "epoch": 0.028852222522766206,
      "grad_norm": 0.12388017028570175,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.8908,
      "step": 20
    },
    {
      "epoch": 0.030294833648904517,
      "grad_norm": 0.12735781073570251,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.8977,
      "step": 21
    },
    {
      "epoch": 0.031737444775042825,
      "grad_norm": 0.13432680070400238,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.7937,
      "step": 22
    },
    {
      "epoch": 0.03318005590118114,
      "grad_norm": 0.15230567753314972,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.7903,
      "step": 23
    },
    {
      "epoch": 0.03462266702731945,
      "grad_norm": 0.2033848613500595,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.7245,
      "step": 24
    },
    {
      "epoch": 0.03606527815345776,
      "grad_norm": 0.46424463391304016,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.8071,
      "step": 25
    },
    {
      "epoch": 0.03606527815345776,
      "eval_loss": 1.8355886936187744,
      "eval_runtime": 1.9357,
      "eval_samples_per_second": 25.83,
      "eval_steps_per_second": 6.716,
      "step": 25
    },
    {
      "epoch": 0.03750788927959607,
      "grad_norm": 0.10298145562410355,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.8078,
      "step": 26
    },
    {
      "epoch": 0.03895050040573438,
      "grad_norm": 0.10137005150318146,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.862,
      "step": 27
    },
    {
      "epoch": 0.04039311153187269,
      "grad_norm": 0.09813342988491058,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.8658,
      "step": 28
    },
    {
      "epoch": 0.041835722658011,
      "grad_norm": 0.09569625556468964,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.8727,
      "step": 29
    },
    {
      "epoch": 0.04327833378414931,
      "grad_norm": 0.10388051718473434,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.9105,
      "step": 30
    },
    {
      "epoch": 0.04472094491028762,
      "grad_norm": 0.11411387473344803,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.8886,
      "step": 31
    },
    {
      "epoch": 0.04616355603642593,
      "grad_norm": 0.11510927975177765,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.8952,
      "step": 32
    },
    {
      "epoch": 0.047606167162564245,
      "grad_norm": 0.12182475626468658,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.829,
      "step": 33
    },
    {
      "epoch": 0.04904877828870255,
      "grad_norm": 0.12330226600170135,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.8445,
      "step": 34
    },
    {
      "epoch": 0.05049138941484086,
      "grad_norm": 0.14157316088676453,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.7933,
      "step": 35
    },
    {
      "epoch": 0.05193400054097917,
      "grad_norm": 0.16847024857997894,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.7073,
      "step": 36
    },
    {
      "epoch": 0.053376611667117484,
      "grad_norm": 0.24314510822296143,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.7666,
      "step": 37
    },
    {
      "epoch": 0.054819222793255795,
      "grad_norm": 0.11479772627353668,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.8474,
      "step": 38
    },
    {
      "epoch": 0.05626183391939411,
      "grad_norm": 0.08777700364589691,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.8271,
      "step": 39
    },
    {
      "epoch": 0.05770444504553241,
      "grad_norm": 0.08493473380804062,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.8627,
      "step": 40
    },
    {
      "epoch": 0.05914705617167072,
      "grad_norm": 0.08421003818511963,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.8604,
      "step": 41
    },
    {
      "epoch": 0.060589667297809034,
      "grad_norm": 0.09325694292783737,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.8878,
      "step": 42
    },
    {
      "epoch": 0.062032278423947346,
      "grad_norm": 0.10094712674617767,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.8749,
      "step": 43
    },
    {
      "epoch": 0.06347488955008565,
      "grad_norm": 0.10834968835115433,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.8902,
      "step": 44
    },
    {
      "epoch": 0.06491750067622397,
      "grad_norm": 0.11347313970327377,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.8737,
      "step": 45
    },
    {
      "epoch": 0.06636011180236227,
      "grad_norm": 0.11705321073532104,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.8224,
      "step": 46
    },
    {
      "epoch": 0.06780272292850059,
      "grad_norm": 0.1233745887875557,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.796,
      "step": 47
    },
    {
      "epoch": 0.0692453340546389,
      "grad_norm": 0.14696474373340607,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.7285,
      "step": 48
    },
    {
      "epoch": 0.0706879451807772,
      "grad_norm": 0.19961224496364594,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.7172,
      "step": 49
    },
    {
      "epoch": 0.07213055630691552,
      "grad_norm": 0.42078298330307007,
      "learning_rate": 1e-05,
      "loss": 1.76,
      "step": 50
    },
    {
      "epoch": 0.07213055630691552,
      "eval_loss": 1.8203463554382324,
      "eval_runtime": 2.1794,
      "eval_samples_per_second": 22.942,
      "eval_steps_per_second": 5.965,
      "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": 1,
        "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": 7.519785357819249e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}