{
  "best_metric": 11.910526275634766,
  "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": 0.06942545622587204,
      "learning_rate": 5e-05,
      "loss": 11.9156,
      "step": 1
    },
    {
      "epoch": 0.004360861270100845,
      "eval_loss": 11.920380592346191,
      "eval_runtime": 0.2559,
      "eval_samples_per_second": 195.424,
      "eval_steps_per_second": 50.81,
      "step": 1
    },
    {
      "epoch": 0.00872172254020169,
      "grad_norm": 0.0677046850323677,
      "learning_rate": 0.0001,
      "loss": 11.9169,
      "step": 2
    },
    {
      "epoch": 0.013082583810302535,
      "grad_norm": 0.06589915603399277,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9179,
      "step": 3
    },
    {
      "epoch": 0.01744344508040338,
      "grad_norm": 0.06446269154548645,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9215,
      "step": 4
    },
    {
      "epoch": 0.021804306350504225,
      "grad_norm": 0.0613664910197258,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9254,
      "step": 5
    },
    {
      "epoch": 0.02616516762060507,
      "grad_norm": 0.06827270239591599,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9222,
      "step": 6
    },
    {
      "epoch": 0.030526028890705915,
      "grad_norm": 0.07137487083673477,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9259,
      "step": 7
    },
    {
      "epoch": 0.03488689016080676,
      "grad_norm": 0.07111971825361252,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9225,
      "step": 8
    },
    {
      "epoch": 0.039247751430907606,
      "grad_norm": 0.07524242997169495,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9219,
      "step": 9
    },
    {
      "epoch": 0.04360861270100845,
      "grad_norm": 0.07738083600997925,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9226,
      "step": 10
    },
    {
      "epoch": 0.047969473971109296,
      "grad_norm": 0.09262727946043015,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9201,
      "step": 11
    },
    {
      "epoch": 0.05233033524121014,
      "grad_norm": 0.10376936197280884,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9225,
      "step": 12
    },
    {
      "epoch": 0.056691196511310986,
      "grad_norm": 0.12678593397140503,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9185,
      "step": 13
    },
    {
      "epoch": 0.06105205778141183,
      "grad_norm": 0.08671963214874268,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9223,
      "step": 14
    },
    {
      "epoch": 0.06541291905151267,
      "grad_norm": 0.08421024680137634,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9243,
      "step": 15
    },
    {
      "epoch": 0.06977378032161352,
      "grad_norm": 0.08584074676036835,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9255,
      "step": 16
    },
    {
      "epoch": 0.07413464159171436,
      "grad_norm": 0.09203244745731354,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9212,
      "step": 17
    },
    {
      "epoch": 0.07849550286181521,
      "grad_norm": 0.09214450418949127,
      "learning_rate": 7.75e-05,
      "loss": 11.9192,
      "step": 18
    },
    {
      "epoch": 0.08285636413191605,
      "grad_norm": 0.0906297042965889,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9225,
      "step": 19
    },
    {
      "epoch": 0.0872172254020169,
      "grad_norm": 0.08888444304466248,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.916,
      "step": 20
    },
    {
      "epoch": 0.09157808667211774,
      "grad_norm": 0.10246984660625458,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9187,
      "step": 21
    },
    {
      "epoch": 0.09593894794221859,
      "grad_norm": 0.101742684841156,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.917,
      "step": 22
    },
    {
      "epoch": 0.10029980921231943,
      "grad_norm": 0.11650920659303665,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9194,
      "step": 23
    },
    {
      "epoch": 0.10466067048242028,
      "grad_norm": 0.10982304066419601,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9211,
      "step": 24
    },
    {
      "epoch": 0.10902153175252112,
      "grad_norm": 0.2074359953403473,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9161,
      "step": 25
    },
    {
      "epoch": 0.10902153175252112,
      "eval_loss": 11.914083480834961,
      "eval_runtime": 0.2645,
      "eval_samples_per_second": 189.049,
      "eval_steps_per_second": 49.153,
      "step": 25
    },
    {
      "epoch": 0.11338239302262197,
      "grad_norm": 0.1174607127904892,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9126,
      "step": 26
    },
    {
      "epoch": 0.11774325429272281,
      "grad_norm": 0.11482725292444229,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9119,
      "step": 27
    },
    {
      "epoch": 0.12210411556282366,
      "grad_norm": 0.11343596875667572,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9197,
      "step": 28
    },
    {
      "epoch": 0.1264649768329245,
      "grad_norm": 0.11668799072504044,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9139,
      "step": 29
    },
    {
      "epoch": 0.13082583810302534,
      "grad_norm": 0.12418890744447708,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.915,
      "step": 30
    },
    {
      "epoch": 0.1351866993731262,
      "grad_norm": 0.1196955218911171,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9202,
      "step": 31
    },
    {
      "epoch": 0.13954756064322704,
      "grad_norm": 0.12244880199432373,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9153,
      "step": 32
    },
    {
      "epoch": 0.1439084219133279,
      "grad_norm": 0.12886793911457062,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9183,
      "step": 33
    },
    {
      "epoch": 0.14826928318342872,
      "grad_norm": 0.13539661467075348,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9169,
      "step": 34
    },
    {
      "epoch": 0.15263014445352957,
      "grad_norm": 0.12643979489803314,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9173,
      "step": 35
    },
    {
      "epoch": 0.15699100572363042,
      "grad_norm": 0.15959049761295319,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.915,
      "step": 36
    },
    {
      "epoch": 0.16135186699373127,
      "grad_norm": 0.16403581202030182,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9144,
      "step": 37
    },
    {
      "epoch": 0.1657127282638321,
      "grad_norm": 0.17608655989170074,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.909,
      "step": 38
    },
    {
      "epoch": 0.17007358953393295,
      "grad_norm": 0.13675826787948608,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9135,
      "step": 39
    },
    {
      "epoch": 0.1744344508040338,
      "grad_norm": 0.13929931819438934,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.9144,
      "step": 40
    },
    {
      "epoch": 0.17879531207413465,
      "grad_norm": 0.13613401353359222,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9147,
      "step": 41
    },
    {
      "epoch": 0.18315617334423548,
      "grad_norm": 0.13010174036026,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9169,
      "step": 42
    },
    {
      "epoch": 0.18751703461433633,
      "grad_norm": 0.12880177795886993,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.9154,
      "step": 43
    },
    {
      "epoch": 0.19187789588443718,
      "grad_norm": 0.14026358723640442,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9142,
      "step": 44
    },
    {
      "epoch": 0.19623875715453803,
      "grad_norm": 0.14814183115959167,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9181,
      "step": 45
    },
    {
      "epoch": 0.20059961842463886,
      "grad_norm": 0.13746632635593414,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9112,
      "step": 46
    },
    {
      "epoch": 0.2049604796947397,
      "grad_norm": 0.13578639924526215,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9114,
      "step": 47
    },
    {
      "epoch": 0.20932134096484056,
      "grad_norm": 0.157059907913208,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9092,
      "step": 48
    },
    {
      "epoch": 0.2136822022349414,
      "grad_norm": 0.14988134801387787,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.9142,
      "step": 49
    },
    {
      "epoch": 0.21804306350504224,
      "grad_norm": 0.24737708270549774,
      "learning_rate": 1e-05,
      "loss": 11.9087,
      "step": 50
    },
    {
      "epoch": 0.21804306350504224,
      "eval_loss": 11.910526275634766,
      "eval_runtime": 0.2494,
      "eval_samples_per_second": 200.488,
      "eval_steps_per_second": 52.127,
      "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
}