{
  "best_metric": 4.0566020011901855,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.8368794326241136,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 2.586822271347046,
      "learning_rate": 5e-05,
      "loss": 4.1672,
      "step": 1
    },
    {
      "epoch": 0.05673758865248227,
      "eval_loss": 5.348921298980713,
      "eval_runtime": 0.7607,
      "eval_samples_per_second": 65.729,
      "eval_steps_per_second": 17.089,
      "step": 1
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 1.7952625751495361,
      "learning_rate": 0.0001,
      "loss": 4.8155,
      "step": 2
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 2.756178855895996,
      "learning_rate": 9.990365154573717e-05,
      "loss": 5.1549,
      "step": 3
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 1.784156322479248,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.3464,
      "step": 4
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 1.1289031505584717,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.1491,
      "step": 5
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.7896755337715149,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.4614,
      "step": 6
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 1.8199571371078491,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.7628,
      "step": 7
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 1.6895242929458618,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.0487,
      "step": 8
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.8855019807815552,
      "learning_rate": 9.535927336897098e-05,
      "loss": 3.9814,
      "step": 9
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.7606056332588196,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.2191,
      "step": 10
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 0.9291881322860718,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5182,
      "step": 11
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 1.0299668312072754,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.6901,
      "step": 12
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 0.7398636341094971,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.9687,
      "step": 13
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 0.6730865836143494,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.0977,
      "step": 14
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.7163558006286621,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.2233,
      "step": 15
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 1.0399569272994995,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.4876,
      "step": 16
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 1.471024990081787,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.9817,
      "step": 17
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 1.0902940034866333,
      "learning_rate": 7.75e-05,
      "loss": 5.8845,
      "step": 18
    },
    {
      "epoch": 1.0780141843971631,
      "grad_norm": 0.6265584826469421,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.5806,
      "step": 19
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.8567792773246765,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.1657,
      "step": 20
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.8748295307159424,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.4572,
      "step": 21
    },
    {
      "epoch": 1.24822695035461,
      "grad_norm": 1.2382404804229736,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.7632,
      "step": 22
    },
    {
      "epoch": 1.3049645390070923,
      "grad_norm": 0.8837085962295532,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.1933,
      "step": 23
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.647677481174469,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.0614,
      "step": 24
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.8481875658035278,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.2391,
      "step": 25
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 4.23311710357666,
      "eval_runtime": 0.2754,
      "eval_samples_per_second": 181.552,
      "eval_steps_per_second": 47.204,
      "step": 25
    },
    {
      "epoch": 1.475177304964539,
      "grad_norm": 0.7314615845680237,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.7435,
      "step": 26
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 1.0433201789855957,
      "learning_rate": 5.205685918464356e-05,
      "loss": 5.0956,
      "step": 27
    },
    {
      "epoch": 1.5886524822695036,
      "grad_norm": 0.746428906917572,
      "learning_rate": 4.912632135009769e-05,
      "loss": 3.7831,
      "step": 28
    },
    {
      "epoch": 1.645390070921986,
      "grad_norm": 0.6522514820098877,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 4.0897,
      "step": 29
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.7004417777061462,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.0653,
      "step": 30
    },
    {
      "epoch": 1.7588652482269502,
      "grad_norm": 1.14938485622406,
      "learning_rate": 4.053522406135775e-05,
      "loss": 4.9702,
      "step": 31
    },
    {
      "epoch": 1.8156028368794326,
      "grad_norm": 0.6156283617019653,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.7304,
      "step": 32
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 0.7247022986412048,
      "learning_rate": 3.509700894014496e-05,
      "loss": 4.0414,
      "step": 33
    },
    {
      "epoch": 1.9290780141843973,
      "grad_norm": 1.0603649616241455,
      "learning_rate": 3.250000000000001e-05,
      "loss": 4.3681,
      "step": 34
    },
    {
      "epoch": 1.9858156028368794,
      "grad_norm": 0.9114518761634827,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 4.6263,
      "step": 35
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 0.7863532304763794,
      "learning_rate": 2.760573569460757e-05,
      "loss": 4.4911,
      "step": 36
    },
    {
      "epoch": 2.099290780141844,
      "grad_norm": 0.5520997047424316,
      "learning_rate": 2.53294383204969e-05,
      "loss": 3.6769,
      "step": 37
    },
    {
      "epoch": 2.1560283687943262,
      "grad_norm": 0.6328124403953552,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.9725,
      "step": 38
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 1.0409072637557983,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 4.3605,
      "step": 39
    },
    {
      "epoch": 2.269503546099291,
      "grad_norm": 0.9518616795539856,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 3.566,
      "step": 40
    },
    {
      "epoch": 2.326241134751773,
      "grad_norm": 0.5669155716896057,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.8253,
      "step": 41
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 0.582383930683136,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.8881,
      "step": 42
    },
    {
      "epoch": 2.4397163120567376,
      "grad_norm": 0.7730618715286255,
      "learning_rate": 1.464072663102903e-05,
      "loss": 4.1901,
      "step": 43
    },
    {
      "epoch": 2.49645390070922,
      "grad_norm": 0.5056310892105103,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.2627,
      "step": 44
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.6426616311073303,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 4.1911,
      "step": 45
    },
    {
      "epoch": 2.6099290780141846,
      "grad_norm": 0.5883984565734863,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.8893,
      "step": 46
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.7146794199943542,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.0799,
      "step": 47
    },
    {
      "epoch": 2.723404255319149,
      "grad_norm": 0.47517043352127075,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.7926,
      "step": 48
    },
    {
      "epoch": 2.780141843971631,
      "grad_norm": 1.140823483467102,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 5.6299,
      "step": 49
    },
    {
      "epoch": 2.8368794326241136,
      "grad_norm": 0.5396044254302979,
      "learning_rate": 1e-05,
      "loss": 3.7497,
      "step": 50
    },
    {
      "epoch": 2.8368794326241136,
      "eval_loss": 4.0566020011901855,
      "eval_runtime": 0.2873,
      "eval_samples_per_second": 174.023,
      "eval_steps_per_second": 45.246,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.13737243557888e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}