{
  "best_metric": 0.5870347023010254,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02222716159146477,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004445432318292954,
      "grad_norm": 0.9642857313156128,
      "learning_rate": 5e-05,
      "loss": 0.9731,
      "step": 1
    },
    {
      "epoch": 0.0004445432318292954,
      "eval_loss": 1.0506365299224854,
      "eval_runtime": 3.8354,
      "eval_samples_per_second": 13.036,
      "eval_steps_per_second": 3.389,
      "step": 1
    },
    {
      "epoch": 0.0008890864636585908,
      "grad_norm": 0.9996522665023804,
      "learning_rate": 0.0001,
      "loss": 1.0075,
      "step": 2
    },
    {
      "epoch": 0.0013336296954878863,
      "grad_norm": 0.9340676665306091,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.9786,
      "step": 3
    },
    {
      "epoch": 0.0017781729273171815,
      "grad_norm": 0.5101247429847717,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.8793,
      "step": 4
    },
    {
      "epoch": 0.002222716159146477,
      "grad_norm": 0.3960937261581421,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.8039,
      "step": 5
    },
    {
      "epoch": 0.0026672593909757725,
      "grad_norm": 0.42056599259376526,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.7691,
      "step": 6
    },
    {
      "epoch": 0.003111802622805068,
      "grad_norm": 0.39349016547203064,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.6964,
      "step": 7
    },
    {
      "epoch": 0.003556345854634363,
      "grad_norm": 0.43044349551200867,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.6832,
      "step": 8
    },
    {
      "epoch": 0.004000889086463659,
      "grad_norm": 0.4253298342227936,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.617,
      "step": 9
    },
    {
      "epoch": 0.004445432318292954,
      "grad_norm": 0.36185693740844727,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.6128,
      "step": 10
    },
    {
      "epoch": 0.004889975550122249,
      "grad_norm": 0.3083949685096741,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.5585,
      "step": 11
    },
    {
      "epoch": 0.005334518781951545,
      "grad_norm": 0.3098645806312561,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.5533,
      "step": 12
    },
    {
      "epoch": 0.00577906201378084,
      "grad_norm": 0.3249451220035553,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.7114,
      "step": 13
    },
    {
      "epoch": 0.006223605245610136,
      "grad_norm": 0.28438881039619446,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.7354,
      "step": 14
    },
    {
      "epoch": 0.006668148477439431,
      "grad_norm": 0.2185528427362442,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.6924,
      "step": 15
    },
    {
      "epoch": 0.007112691709268726,
      "grad_norm": 0.17781998217105865,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.6734,
      "step": 16
    },
    {
      "epoch": 0.007557234941098022,
      "grad_norm": 0.19341647624969482,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.6885,
      "step": 17
    },
    {
      "epoch": 0.008001778172927318,
      "grad_norm": 0.19029445946216583,
      "learning_rate": 7.75e-05,
      "loss": 0.66,
      "step": 18
    },
    {
      "epoch": 0.008446321404756613,
      "grad_norm": 0.18659715354442596,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.6319,
      "step": 19
    },
    {
      "epoch": 0.008890864636585907,
      "grad_norm": 0.19390127062797546,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.6099,
      "step": 20
    },
    {
      "epoch": 0.009335407868415203,
      "grad_norm": 0.19577656686306,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.6025,
      "step": 21
    },
    {
      "epoch": 0.009779951100244499,
      "grad_norm": 0.19913122057914734,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.5439,
      "step": 22
    },
    {
      "epoch": 0.010224494332073794,
      "grad_norm": 0.22242505848407745,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.5738,
      "step": 23
    },
    {
      "epoch": 0.01066903756390309,
      "grad_norm": 0.21811483800411224,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.5367,
      "step": 24
    },
    {
      "epoch": 0.011113580795732384,
      "grad_norm": 0.3701319694519043,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.5765,
      "step": 25
    },
    {
      "epoch": 0.011113580795732384,
      "eval_loss": 0.6047177314758301,
      "eval_runtime": 3.4784,
      "eval_samples_per_second": 14.374,
      "eval_steps_per_second": 3.737,
      "step": 25
    },
    {
      "epoch": 0.01155812402756168,
      "grad_norm": 0.14327451586723328,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.6614,
      "step": 26
    },
    {
      "epoch": 0.012002667259390976,
      "grad_norm": 0.1515110284090042,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.6824,
      "step": 27
    },
    {
      "epoch": 0.012447210491220271,
      "grad_norm": 0.15741868317127228,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.6585,
      "step": 28
    },
    {
      "epoch": 0.012891753723049567,
      "grad_norm": 0.17712979018688202,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.6518,
      "step": 29
    },
    {
      "epoch": 0.013336296954878863,
      "grad_norm": 0.1943611204624176,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.6639,
      "step": 30
    },
    {
      "epoch": 0.013780840186708157,
      "grad_norm": 0.19372722506523132,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.6339,
      "step": 31
    },
    {
      "epoch": 0.014225383418537452,
      "grad_norm": 0.17396874725818634,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.5713,
      "step": 32
    },
    {
      "epoch": 0.014669926650366748,
      "grad_norm": 0.16710332036018372,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.615,
      "step": 33
    },
    {
      "epoch": 0.015114469882196044,
      "grad_norm": 0.16157880425453186,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.5574,
      "step": 34
    },
    {
      "epoch": 0.01555901311402534,
      "grad_norm": 0.16557228565216064,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.5262,
      "step": 35
    },
    {
      "epoch": 0.016003556345854635,
      "grad_norm": 0.18180273473262787,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.5055,
      "step": 36
    },
    {
      "epoch": 0.01644809957768393,
      "grad_norm": 0.25119903683662415,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.4996,
      "step": 37
    },
    {
      "epoch": 0.016892642809513227,
      "grad_norm": 0.16843101382255554,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.7076,
      "step": 38
    },
    {
      "epoch": 0.01733718604134252,
      "grad_norm": 0.139786958694458,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.676,
      "step": 39
    },
    {
      "epoch": 0.017781729273171815,
      "grad_norm": 0.13475798070430756,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.6726,
      "step": 40
    },
    {
      "epoch": 0.018226272505001112,
      "grad_norm": 0.13363976776599884,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.6386,
      "step": 41
    },
    {
      "epoch": 0.018670815736830406,
      "grad_norm": 0.12477023899555206,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.6495,
      "step": 42
    },
    {
      "epoch": 0.019115358968659703,
      "grad_norm": 0.12433835864067078,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.6185,
      "step": 43
    },
    {
      "epoch": 0.019559902200488997,
      "grad_norm": 0.135418102145195,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.6286,
      "step": 44
    },
    {
      "epoch": 0.02000444543231829,
      "grad_norm": 0.1305476576089859,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.5891,
      "step": 45
    },
    {
      "epoch": 0.02044898866414759,
      "grad_norm": 0.1284274160861969,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.5447,
      "step": 46
    },
    {
      "epoch": 0.020893531895976883,
      "grad_norm": 0.1395895779132843,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.5439,
      "step": 47
    },
    {
      "epoch": 0.02133807512780618,
      "grad_norm": 0.1462106853723526,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.4906,
      "step": 48
    },
    {
      "epoch": 0.021782618359635474,
      "grad_norm": 0.16900724172592163,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.518,
      "step": 49
    },
    {
      "epoch": 0.02222716159146477,
      "grad_norm": 0.34547173976898193,
      "learning_rate": 1e-05,
      "loss": 0.5824,
      "step": 50
    },
    {
      "epoch": 0.02222716159146477,
      "eval_loss": 0.5870347023010254,
      "eval_runtime": 3.4885,
      "eval_samples_per_second": 14.333,
      "eval_steps_per_second": 3.727,
      "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": 5.975543717811978e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}