{
  "best_metric": 0.6246473789215088,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.033716862645930795,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000674337252918616,
      "grad_norm": 0.06702949106693268,
      "learning_rate": 5e-05,
      "loss": 0.6889,
      "step": 1
    },
    {
      "epoch": 0.000674337252918616,
      "eval_loss": 0.710753858089447,
      "eval_runtime": 323.6074,
      "eval_samples_per_second": 30.871,
      "eval_steps_per_second": 3.86,
      "step": 1
    },
    {
      "epoch": 0.001348674505837232,
      "grad_norm": 0.06914016604423523,
      "learning_rate": 0.0001,
      "loss": 0.6787,
      "step": 2
    },
    {
      "epoch": 0.0020230117587558476,
      "grad_norm": 0.05790046602487564,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.666,
      "step": 3
    },
    {
      "epoch": 0.002697349011674464,
      "grad_norm": 0.05246204137802124,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7055,
      "step": 4
    },
    {
      "epoch": 0.0033716862645930797,
      "grad_norm": 0.050530899316072464,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.6943,
      "step": 5
    },
    {
      "epoch": 0.004046023517511695,
      "grad_norm": 0.05254204943776131,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7192,
      "step": 6
    },
    {
      "epoch": 0.004720360770430311,
      "grad_norm": 0.05547985062003136,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7032,
      "step": 7
    },
    {
      "epoch": 0.005394698023348928,
      "grad_norm": 0.05607816204428673,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6877,
      "step": 8
    },
    {
      "epoch": 0.006069035276267543,
      "grad_norm": 0.05468464270234108,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6748,
      "step": 9
    },
    {
      "epoch": 0.006743372529186159,
      "grad_norm": 0.06065172702074051,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6917,
      "step": 10
    },
    {
      "epoch": 0.007417709782104775,
      "grad_norm": 0.07578393816947937,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.6906,
      "step": 11
    },
    {
      "epoch": 0.00809204703502339,
      "grad_norm": 0.10089249163866043,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6422,
      "step": 12
    },
    {
      "epoch": 0.008766384287942007,
      "grad_norm": 0.06586451828479767,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6682,
      "step": 13
    },
    {
      "epoch": 0.009440721540860623,
      "grad_norm": 0.06408973038196564,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.648,
      "step": 14
    },
    {
      "epoch": 0.010115058793779238,
      "grad_norm": 0.056105837225914,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6166,
      "step": 15
    },
    {
      "epoch": 0.010789396046697855,
      "grad_norm": 0.049004558473825455,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.641,
      "step": 16
    },
    {
      "epoch": 0.01146373329961647,
      "grad_norm": 0.04530835151672363,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.656,
      "step": 17
    },
    {
      "epoch": 0.012138070552535086,
      "grad_norm": 0.054369065910577774,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6779,
      "step": 18
    },
    {
      "epoch": 0.012812407805453703,
      "grad_norm": 0.045746251940727234,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6653,
      "step": 19
    },
    {
      "epoch": 0.013486745058372319,
      "grad_norm": 0.04066094011068344,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6455,
      "step": 20
    },
    {
      "epoch": 0.014161082311290934,
      "grad_norm": 0.046686429530382156,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6341,
      "step": 21
    },
    {
      "epoch": 0.01483541956420955,
      "grad_norm": 0.04868229106068611,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.648,
      "step": 22
    },
    {
      "epoch": 0.015509756817128167,
      "grad_norm": 0.054860349744558334,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.624,
      "step": 23
    },
    {
      "epoch": 0.01618409407004678,
      "grad_norm": 0.06884879618883133,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6175,
      "step": 24
    },
    {
      "epoch": 0.016858431322965398,
      "grad_norm": 0.10856156796216965,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6074,
      "step": 25
    },
    {
      "epoch": 0.016858431322965398,
      "eval_loss": 0.635942816734314,
      "eval_runtime": 323.4927,
      "eval_samples_per_second": 30.882,
      "eval_steps_per_second": 3.861,
      "step": 25
    },
    {
      "epoch": 0.017532768575884015,
      "grad_norm": 0.03802214562892914,
      "learning_rate": 5e-05,
      "loss": 0.6201,
      "step": 26
    },
    {
      "epoch": 0.01820710582880263,
      "grad_norm": 0.03864743560552597,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.6096,
      "step": 27
    },
    {
      "epoch": 0.018881443081721246,
      "grad_norm": 0.03929690644145012,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.6099,
      "step": 28
    },
    {
      "epoch": 0.019555780334639863,
      "grad_norm": 0.03998783603310585,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6685,
      "step": 29
    },
    {
      "epoch": 0.020230117587558476,
      "grad_norm": 0.040432240813970566,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.6457,
      "step": 30
    },
    {
      "epoch": 0.020904454840477094,
      "grad_norm": 0.03912314400076866,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.6474,
      "step": 31
    },
    {
      "epoch": 0.02157879209339571,
      "grad_norm": 0.04070175811648369,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6623,
      "step": 32
    },
    {
      "epoch": 0.022253129346314324,
      "grad_norm": 0.042440399527549744,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.6445,
      "step": 33
    },
    {
      "epoch": 0.02292746659923294,
      "grad_norm": 0.04432351142168045,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6456,
      "step": 34
    },
    {
      "epoch": 0.02360180385215156,
      "grad_norm": 0.04915205016732216,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.6181,
      "step": 35
    },
    {
      "epoch": 0.024276141105070172,
      "grad_norm": 0.060590483248233795,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.6437,
      "step": 36
    },
    {
      "epoch": 0.02495047835798879,
      "grad_norm": 0.08441194891929626,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.5971,
      "step": 37
    },
    {
      "epoch": 0.025624815610907407,
      "grad_norm": 0.04252498969435692,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6199,
      "step": 38
    },
    {
      "epoch": 0.02629915286382602,
      "grad_norm": 0.03582555055618286,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6185,
      "step": 39
    },
    {
      "epoch": 0.026973490116744638,
      "grad_norm": 0.03583125025033951,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6102,
      "step": 40
    },
    {
      "epoch": 0.02764782736966325,
      "grad_norm": 0.03665323182940483,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.635,
      "step": 41
    },
    {
      "epoch": 0.02832216462258187,
      "grad_norm": 0.03724931553006172,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6318,
      "step": 42
    },
    {
      "epoch": 0.028996501875500486,
      "grad_norm": 0.0381876602768898,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.6356,
      "step": 43
    },
    {
      "epoch": 0.0296708391284191,
      "grad_norm": 0.03994078189134598,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6529,
      "step": 44
    },
    {
      "epoch": 0.030345176381337716,
      "grad_norm": 0.04033001512289047,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.6297,
      "step": 45
    },
    {
      "epoch": 0.031019513634256334,
      "grad_norm": 0.04195138439536095,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.6297,
      "step": 46
    },
    {
      "epoch": 0.03169385088717495,
      "grad_norm": 0.04799654707312584,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.5991,
      "step": 47
    },
    {
      "epoch": 0.03236818814009356,
      "grad_norm": 0.0569855198264122,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.6151,
      "step": 48
    },
    {
      "epoch": 0.03304252539301218,
      "grad_norm": 0.0731813982129097,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.6352,
      "step": 49
    },
    {
      "epoch": 0.033716862645930795,
      "grad_norm": 0.10938958823680878,
      "learning_rate": 0.0,
      "loss": 0.5487,
      "step": 50
    },
    {
      "epoch": 0.033716862645930795,
      "eval_loss": 0.6246473789215088,
      "eval_runtime": 322.2392,
      "eval_samples_per_second": 31.002,
      "eval_steps_per_second": 3.876,
      "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": 6.483553641436283e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}