{
  "best_metric": 0.9443409442901611,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7504690431519699,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0150093808630394,
      "grad_norm": 0.9516903162002563,
      "learning_rate": 5e-05,
      "loss": 1.2897,
      "step": 1
    },
    {
      "epoch": 0.0150093808630394,
      "eval_loss": 1.5068179368972778,
      "eval_runtime": 13.9154,
      "eval_samples_per_second": 32.266,
      "eval_steps_per_second": 4.096,
      "step": 1
    },
    {
      "epoch": 0.0300187617260788,
      "grad_norm": 1.0713194608688354,
      "learning_rate": 0.0001,
      "loss": 1.4698,
      "step": 2
    },
    {
      "epoch": 0.0450281425891182,
      "grad_norm": 0.9374421834945679,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.4201,
      "step": 3
    },
    {
      "epoch": 0.0600375234521576,
      "grad_norm": 0.5490052700042725,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2867,
      "step": 4
    },
    {
      "epoch": 0.075046904315197,
      "grad_norm": 0.6242175698280334,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.3143,
      "step": 5
    },
    {
      "epoch": 0.0900562851782364,
      "grad_norm": 0.723852813243866,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.2065,
      "step": 6
    },
    {
      "epoch": 0.1050656660412758,
      "grad_norm": 0.6209497451782227,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1807,
      "step": 7
    },
    {
      "epoch": 0.1200750469043152,
      "grad_norm": 0.4316489100456238,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1357,
      "step": 8
    },
    {
      "epoch": 0.1350844277673546,
      "grad_norm": 0.31692197918891907,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.117,
      "step": 9
    },
    {
      "epoch": 0.150093808630394,
      "grad_norm": 0.3322769105434418,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0356,
      "step": 10
    },
    {
      "epoch": 0.1651031894934334,
      "grad_norm": 0.31195032596588135,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0036,
      "step": 11
    },
    {
      "epoch": 0.1801125703564728,
      "grad_norm": 0.32804766297340393,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.9494,
      "step": 12
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.2507679760456085,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8764,
      "step": 13
    },
    {
      "epoch": 0.2101313320825516,
      "grad_norm": 0.2695164084434509,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9968,
      "step": 14
    },
    {
      "epoch": 0.225140712945591,
      "grad_norm": 0.2693517804145813,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.0027,
      "step": 15
    },
    {
      "epoch": 0.2401500938086304,
      "grad_norm": 0.2577652633190155,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0005,
      "step": 16
    },
    {
      "epoch": 0.2551594746716698,
      "grad_norm": 0.25722965598106384,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.9922,
      "step": 17
    },
    {
      "epoch": 0.2701688555347092,
      "grad_norm": 0.2348056137561798,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9875,
      "step": 18
    },
    {
      "epoch": 0.2851782363977486,
      "grad_norm": 0.21418173611164093,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.0247,
      "step": 19
    },
    {
      "epoch": 0.300187617260788,
      "grad_norm": 0.19569775462150574,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0216,
      "step": 20
    },
    {
      "epoch": 0.3151969981238274,
      "grad_norm": 0.19758202135562897,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9754,
      "step": 21
    },
    {
      "epoch": 0.3302063789868668,
      "grad_norm": 0.19964873790740967,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9694,
      "step": 22
    },
    {
      "epoch": 0.3452157598499062,
      "grad_norm": 0.19713839888572693,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.9228,
      "step": 23
    },
    {
      "epoch": 0.3602251407129456,
      "grad_norm": 0.19586385786533356,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.94,
      "step": 24
    },
    {
      "epoch": 0.37523452157598497,
      "grad_norm": 0.2172546237707138,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.8919,
      "step": 25
    },
    {
      "epoch": 0.37523452157598497,
      "eval_loss": 0.9667521715164185,
      "eval_runtime": 13.9184,
      "eval_samples_per_second": 32.26,
      "eval_steps_per_second": 4.095,
      "step": 25
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.2630976736545563,
      "learning_rate": 5e-05,
      "loss": 0.881,
      "step": 26
    },
    {
      "epoch": 0.4052532833020638,
      "grad_norm": 0.26560088992118835,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.9961,
      "step": 27
    },
    {
      "epoch": 0.4202626641651032,
      "grad_norm": 0.23215793073177338,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.008,
      "step": 28
    },
    {
      "epoch": 0.4352720450281426,
      "grad_norm": 0.2006905972957611,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9938,
      "step": 29
    },
    {
      "epoch": 0.450281425891182,
      "grad_norm": 0.2019686996936798,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.9836,
      "step": 30
    },
    {
      "epoch": 0.4652908067542214,
      "grad_norm": 0.20353145897388458,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.967,
      "step": 31
    },
    {
      "epoch": 0.4803001876172608,
      "grad_norm": 0.2187284678220749,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9788,
      "step": 32
    },
    {
      "epoch": 0.49530956848030017,
      "grad_norm": 0.23200970888137817,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.9042,
      "step": 33
    },
    {
      "epoch": 0.5103189493433395,
      "grad_norm": 0.21799759566783905,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9099,
      "step": 34
    },
    {
      "epoch": 0.525328330206379,
      "grad_norm": 0.2261268049478531,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.9489,
      "step": 35
    },
    {
      "epoch": 0.5403377110694184,
      "grad_norm": 0.2131943255662918,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8895,
      "step": 36
    },
    {
      "epoch": 0.5553470919324578,
      "grad_norm": 0.23032636940479279,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8981,
      "step": 37
    },
    {
      "epoch": 0.5703564727954972,
      "grad_norm": 0.1798233836889267,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8644,
      "step": 38
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.23366278409957886,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.9421,
      "step": 39
    },
    {
      "epoch": 0.600375234521576,
      "grad_norm": 0.22759605944156647,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.0072,
      "step": 40
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.20452305674552917,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.9861,
      "step": 41
    },
    {
      "epoch": 0.6303939962476548,
      "grad_norm": 0.21224012970924377,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9324,
      "step": 42
    },
    {
      "epoch": 0.6454033771106942,
      "grad_norm": 0.19800162315368652,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.9566,
      "step": 43
    },
    {
      "epoch": 0.6604127579737336,
      "grad_norm": 0.18474912643432617,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9571,
      "step": 44
    },
    {
      "epoch": 0.6754221388367729,
      "grad_norm": 0.17070691287517548,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.9385,
      "step": 45
    },
    {
      "epoch": 0.6904315196998124,
      "grad_norm": 0.17717796564102173,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.9539,
      "step": 46
    },
    {
      "epoch": 0.7054409005628518,
      "grad_norm": 0.18040595948696136,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.9689,
      "step": 47
    },
    {
      "epoch": 0.7204502814258912,
      "grad_norm": 0.17790913581848145,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8991,
      "step": 48
    },
    {
      "epoch": 0.7354596622889306,
      "grad_norm": 0.19197432696819305,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.8769,
      "step": 49
    },
    {
      "epoch": 0.7504690431519699,
      "grad_norm": 0.24990469217300415,
      "learning_rate": 0.0,
      "loss": 0.8438,
      "step": 50
    },
    {
      "epoch": 0.7504690431519699,
      "eval_loss": 0.9443409442901611,
      "eval_runtime": 13.9336,
      "eval_samples_per_second": 32.224,
      "eval_steps_per_second": 4.091,
      "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": 5.968186696531968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}