{
  "best_metric": 11.908963203430176,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.21804306350504224,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004360861270100845,
      "grad_norm": 0.08034911006689072,
      "learning_rate": 5e-05,
      "loss": 11.9156,
      "step": 1
    },
    {
      "epoch": 0.004360861270100845,
      "eval_loss": 11.920380592346191,
      "eval_runtime": 0.2123,
      "eval_samples_per_second": 235.563,
      "eval_steps_per_second": 61.246,
      "step": 1
    },
    {
      "epoch": 0.00872172254020169,
      "grad_norm": 0.07949778437614441,
      "learning_rate": 0.0001,
      "loss": 11.9169,
      "step": 2
    },
    {
      "epoch": 0.013082583810302535,
      "grad_norm": 0.07817766815423965,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9179,
      "step": 3
    },
    {
      "epoch": 0.01744344508040338,
      "grad_norm": 0.07690611481666565,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9215,
      "step": 4
    },
    {
      "epoch": 0.021804306350504225,
      "grad_norm": 0.07045928388834,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9254,
      "step": 5
    },
    {
      "epoch": 0.02616516762060507,
      "grad_norm": 0.07899348437786102,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9221,
      "step": 6
    },
    {
      "epoch": 0.030526028890705915,
      "grad_norm": 0.08397746086120605,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9258,
      "step": 7
    },
    {
      "epoch": 0.03488689016080676,
      "grad_norm": 0.08348705619573593,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9224,
      "step": 8
    },
    {
      "epoch": 0.039247751430907606,
      "grad_norm": 0.09135878831148148,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9217,
      "step": 9
    },
    {
      "epoch": 0.04360861270100845,
      "grad_norm": 0.09215676039457321,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9224,
      "step": 10
    },
    {
      "epoch": 0.047969473971109296,
      "grad_norm": 0.10351918637752533,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9199,
      "step": 11
    },
    {
      "epoch": 0.05233033524121014,
      "grad_norm": 0.10987162590026855,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9224,
      "step": 12
    },
    {
      "epoch": 0.056691196511310986,
      "grad_norm": 0.1353227198123932,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9184,
      "step": 13
    },
    {
      "epoch": 0.06105205778141183,
      "grad_norm": 0.11148161441087723,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9219,
      "step": 14
    },
    {
      "epoch": 0.06541291905151267,
      "grad_norm": 0.10726375132799149,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9239,
      "step": 15
    },
    {
      "epoch": 0.06977378032161352,
      "grad_norm": 0.10883919894695282,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9251,
      "step": 16
    },
    {
      "epoch": 0.07413464159171436,
      "grad_norm": 0.11692698299884796,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9207,
      "step": 17
    },
    {
      "epoch": 0.07849550286181521,
      "grad_norm": 0.11752425879240036,
      "learning_rate": 7.75e-05,
      "loss": 11.9187,
      "step": 18
    },
    {
      "epoch": 0.08285636413191605,
      "grad_norm": 0.11515916883945465,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.922,
      "step": 19
    },
    {
      "epoch": 0.0872172254020169,
      "grad_norm": 0.11031749844551086,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9155,
      "step": 20
    },
    {
      "epoch": 0.09157808667211774,
      "grad_norm": 0.12162190675735474,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9183,
      "step": 21
    },
    {
      "epoch": 0.09593894794221859,
      "grad_norm": 0.12862041592597961,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9163,
      "step": 22
    },
    {
      "epoch": 0.10029980921231943,
      "grad_norm": 0.1362481713294983,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.919,
      "step": 23
    },
    {
      "epoch": 0.10466067048242028,
      "grad_norm": 0.12212856858968735,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9207,
      "step": 24
    },
    {
      "epoch": 0.10902153175252112,
      "grad_norm": 0.21995852887630463,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9164,
      "step": 25
    },
    {
      "epoch": 0.10902153175252112,
      "eval_loss": 11.913113594055176,
      "eval_runtime": 0.2034,
      "eval_samples_per_second": 245.83,
      "eval_steps_per_second": 63.916,
      "step": 25
    },
    {
      "epoch": 0.11338239302262197,
      "grad_norm": 0.1562476009130478,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9116,
      "step": 26
    },
    {
      "epoch": 0.11774325429272281,
      "grad_norm": 0.15570887923240662,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9109,
      "step": 27
    },
    {
      "epoch": 0.12210411556282366,
      "grad_norm": 0.1476237177848816,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9189,
      "step": 28
    },
    {
      "epoch": 0.1264649768329245,
      "grad_norm": 0.1496644765138626,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9131,
      "step": 29
    },
    {
      "epoch": 0.13082583810302534,
      "grad_norm": 0.15726502239704132,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9141,
      "step": 30
    },
    {
      "epoch": 0.1351866993731262,
      "grad_norm": 0.15136896073818207,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9193,
      "step": 31
    },
    {
      "epoch": 0.13954756064322704,
      "grad_norm": 0.15999847650527954,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9142,
      "step": 32
    },
    {
      "epoch": 0.1439084219133279,
      "grad_norm": 0.16553688049316406,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9171,
      "step": 33
    },
    {
      "epoch": 0.14826928318342872,
      "grad_norm": 0.15596571564674377,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9163,
      "step": 34
    },
    {
      "epoch": 0.15263014445352957,
      "grad_norm": 0.15343689918518066,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9164,
      "step": 35
    },
    {
      "epoch": 0.15699100572363042,
      "grad_norm": 0.17582526803016663,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9145,
      "step": 36
    },
    {
      "epoch": 0.16135186699373127,
      "grad_norm": 0.17929713428020477,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9146,
      "step": 37
    },
    {
      "epoch": 0.1657127282638321,
      "grad_norm": 0.19357652962207794,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9083,
      "step": 38
    },
    {
      "epoch": 0.17007358953393295,
      "grad_norm": 0.1828354001045227,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9121,
      "step": 39
    },
    {
      "epoch": 0.1744344508040338,
      "grad_norm": 0.18384677171707153,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.913,
      "step": 40
    },
    {
      "epoch": 0.17879531207413465,
      "grad_norm": 0.17018263041973114,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9136,
      "step": 41
    },
    {
      "epoch": 0.18315617334423548,
      "grad_norm": 0.17318980395793915,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9156,
      "step": 42
    },
    {
      "epoch": 0.18751703461433633,
      "grad_norm": 0.16648034751415253,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.9142,
      "step": 43
    },
    {
      "epoch": 0.19187789588443718,
      "grad_norm": 0.18412597477436066,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9127,
      "step": 44
    },
    {
      "epoch": 0.19623875715453803,
      "grad_norm": 0.1855076551437378,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9169,
      "step": 45
    },
    {
      "epoch": 0.20059961842463886,
      "grad_norm": 0.1759565770626068,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9099,
      "step": 46
    },
    {
      "epoch": 0.2049604796947397,
      "grad_norm": 0.16490474343299866,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9105,
      "step": 47
    },
    {
      "epoch": 0.20932134096484056,
      "grad_norm": 0.18263190984725952,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9083,
      "step": 48
    },
    {
      "epoch": 0.2136822022349414,
      "grad_norm": 0.1636153906583786,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.9141,
      "step": 49
    },
    {
      "epoch": 0.21804306350504224,
      "grad_norm": 0.2649901509284973,
      "learning_rate": 1e-05,
      "loss": 11.9085,
      "step": 50
    },
    {
      "epoch": 0.21804306350504224,
      "eval_loss": 11.908963203430176,
      "eval_runtime": 0.2104,
      "eval_samples_per_second": 237.603,
      "eval_steps_per_second": 61.777,
      "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": 1042494259200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}