{
  "best_metric": 1.0106004476547241,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.44052863436123346,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00881057268722467,
      "grad_norm": 68.2496566772461,
      "learning_rate": 2e-05,
      "loss": 6.4572,
      "step": 1
    },
    {
      "epoch": 0.00881057268722467,
      "eval_loss": 2.527791738510132,
      "eval_runtime": 6.71,
      "eval_samples_per_second": 28.614,
      "eval_steps_per_second": 3.577,
      "step": 1
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 50.708988189697266,
      "learning_rate": 4e-05,
      "loss": 6.4946,
      "step": 2
    },
    {
      "epoch": 0.02643171806167401,
      "grad_norm": 44.1339225769043,
      "learning_rate": 6e-05,
      "loss": 6.527,
      "step": 3
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 19.318286895751953,
      "learning_rate": 8e-05,
      "loss": 4.3438,
      "step": 4
    },
    {
      "epoch": 0.04405286343612335,
      "grad_norm": 18.93522071838379,
      "learning_rate": 0.0001,
      "loss": 4.9276,
      "step": 5
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 14.795171737670898,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.8183,
      "step": 6
    },
    {
      "epoch": 0.06167400881057269,
      "grad_norm": 13.332947731018066,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.4671,
      "step": 7
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 12.206098556518555,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.3656,
      "step": 8
    },
    {
      "epoch": 0.07929515418502203,
      "grad_norm": 12.272443771362305,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.893,
      "step": 9
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 12.4472074508667,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.4506,
      "step": 10
    },
    {
      "epoch": 0.09691629955947137,
      "grad_norm": 12.094071388244629,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.7599,
      "step": 11
    },
    {
      "epoch": 0.10572687224669604,
      "grad_norm": 12.491962432861328,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.513,
      "step": 12
    },
    {
      "epoch": 0.1145374449339207,
      "grad_norm": 12.175878524780273,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.2163,
      "step": 13
    },
    {
      "epoch": 0.12334801762114538,
      "grad_norm": 11.396886825561523,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.1033,
      "step": 14
    },
    {
      "epoch": 0.13215859030837004,
      "grad_norm": 12.93130874633789,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.5041,
      "step": 15
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": 12.235413551330566,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.4852,
      "step": 16
    },
    {
      "epoch": 0.14977973568281938,
      "grad_norm": 11.997471809387207,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.1465,
      "step": 17
    },
    {
      "epoch": 0.15859030837004406,
      "grad_norm": 10.910942077636719,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.9378,
      "step": 18
    },
    {
      "epoch": 0.16740088105726872,
      "grad_norm": 11.567279815673828,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.9317,
      "step": 19
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 13.30049991607666,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.3284,
      "step": 20
    },
    {
      "epoch": 0.18502202643171806,
      "grad_norm": 11.890619277954102,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.4783,
      "step": 21
    },
    {
      "epoch": 0.19383259911894274,
      "grad_norm": 12.334750175476074,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.1746,
      "step": 22
    },
    {
      "epoch": 0.2026431718061674,
      "grad_norm": 12.509641647338867,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.2126,
      "step": 23
    },
    {
      "epoch": 0.21145374449339208,
      "grad_norm": 11.47304630279541,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.6245,
      "step": 24
    },
    {
      "epoch": 0.22026431718061673,
      "grad_norm": 12.029542922973633,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.1595,
      "step": 25
    },
    {
      "epoch": 0.22026431718061673,
      "eval_loss": 1.1055799722671509,
      "eval_runtime": 6.9256,
      "eval_samples_per_second": 27.723,
      "eval_steps_per_second": 3.465,
      "step": 25
    },
    {
      "epoch": 0.2290748898678414,
      "grad_norm": 13.63646411895752,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.2333,
      "step": 26
    },
    {
      "epoch": 0.23788546255506607,
      "grad_norm": 12.906288146972656,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.7754,
      "step": 27
    },
    {
      "epoch": 0.24669603524229075,
      "grad_norm": 32.98773956298828,
      "learning_rate": 4.825502516487497e-05,
      "loss": 5.5734,
      "step": 28
    },
    {
      "epoch": 0.2555066079295154,
      "grad_norm": 36.30422592163086,
      "learning_rate": 4.477357683661734e-05,
      "loss": 5.2083,
      "step": 29
    },
    {
      "epoch": 0.2643171806167401,
      "grad_norm": 29.99471092224121,
      "learning_rate": 4.131759111665349e-05,
      "loss": 5.2787,
      "step": 30
    },
    {
      "epoch": 0.27312775330396477,
      "grad_norm": 17.82193374633789,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.5795,
      "step": 31
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": 13.2213716506958,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.3673,
      "step": 32
    },
    {
      "epoch": 0.2907488986784141,
      "grad_norm": 11.667417526245117,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.9109,
      "step": 33
    },
    {
      "epoch": 0.29955947136563876,
      "grad_norm": 10.663423538208008,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.0043,
      "step": 34
    },
    {
      "epoch": 0.30837004405286345,
      "grad_norm": 10.346181869506836,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.8749,
      "step": 35
    },
    {
      "epoch": 0.31718061674008813,
      "grad_norm": 10.776055335998535,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.8847,
      "step": 36
    },
    {
      "epoch": 0.32599118942731276,
      "grad_norm": 10.248950004577637,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.7897,
      "step": 37
    },
    {
      "epoch": 0.33480176211453744,
      "grad_norm": 10.948817253112793,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.9268,
      "step": 38
    },
    {
      "epoch": 0.3436123348017621,
      "grad_norm": 10.441291809082031,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.5599,
      "step": 39
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": 12.858811378479004,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.607,
      "step": 40
    },
    {
      "epoch": 0.36123348017621143,
      "grad_norm": 11.29244327545166,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.1881,
      "step": 41
    },
    {
      "epoch": 0.3700440528634361,
      "grad_norm": 10.727145195007324,
      "learning_rate": 7.597595192178702e-06,
      "loss": 4.1046,
      "step": 42
    },
    {
      "epoch": 0.3788546255506608,
      "grad_norm": 11.454111099243164,
      "learning_rate": 5.852620357053651e-06,
      "loss": 4.0834,
      "step": 43
    },
    {
      "epoch": 0.3876651982378855,
      "grad_norm": 10.730988502502441,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.7658,
      "step": 44
    },
    {
      "epoch": 0.3964757709251101,
      "grad_norm": 12.551647186279297,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.5078,
      "step": 45
    },
    {
      "epoch": 0.4052863436123348,
      "grad_norm": 12.465065956115723,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.9693,
      "step": 46
    },
    {
      "epoch": 0.41409691629955947,
      "grad_norm": 11.369115829467773,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.7502,
      "step": 47
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": 11.680598258972168,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.6231,
      "step": 48
    },
    {
      "epoch": 0.43171806167400884,
      "grad_norm": 14.236860275268555,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 4.1521,
      "step": 49
    },
    {
      "epoch": 0.44052863436123346,
      "grad_norm": 12.475255966186523,
      "learning_rate": 0.0,
      "loss": 4.2304,
      "step": 50
    },
    {
      "epoch": 0.44052863436123346,
      "eval_loss": 1.0106004476547241,
      "eval_runtime": 6.9593,
      "eval_samples_per_second": 27.589,
      "eval_steps_per_second": 3.449,
      "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": 5,
        "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": 3.57749502246912e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}