{
  "best_metric": 1.0094060897827148,
  "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": 71.52523803710938,
      "learning_rate": 2e-05,
      "loss": 6.4572,
      "step": 1
    },
    {
      "epoch": 0.00881057268722467,
      "eval_loss": 2.527791738510132,
      "eval_runtime": 6.7645,
      "eval_samples_per_second": 28.383,
      "eval_steps_per_second": 3.548,
      "step": 1
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 52.80047607421875,
      "learning_rate": 4e-05,
      "loss": 6.4946,
      "step": 2
    },
    {
      "epoch": 0.02643171806167401,
      "grad_norm": 45.3133544921875,
      "learning_rate": 6e-05,
      "loss": 6.4838,
      "step": 3
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 19.76211929321289,
      "learning_rate": 8e-05,
      "loss": 4.3298,
      "step": 4
    },
    {
      "epoch": 0.04405286343612335,
      "grad_norm": 19.206777572631836,
      "learning_rate": 0.0001,
      "loss": 4.9177,
      "step": 5
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 14.95755386352539,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.8063,
      "step": 6
    },
    {
      "epoch": 0.06167400881057269,
      "grad_norm": 13.54239273071289,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.4596,
      "step": 7
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 12.369343757629395,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.3516,
      "step": 8
    },
    {
      "epoch": 0.07929515418502203,
      "grad_norm": 12.412100791931152,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.8791,
      "step": 9
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 12.685561180114746,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.4534,
      "step": 10
    },
    {
      "epoch": 0.09691629955947137,
      "grad_norm": 12.313078880310059,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.7578,
      "step": 11
    },
    {
      "epoch": 0.10572687224669604,
      "grad_norm": 12.696328163146973,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.5216,
      "step": 12
    },
    {
      "epoch": 0.1145374449339207,
      "grad_norm": 12.560774803161621,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.2162,
      "step": 13
    },
    {
      "epoch": 0.12334801762114538,
      "grad_norm": 11.407295227050781,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.1029,
      "step": 14
    },
    {
      "epoch": 0.13215859030837004,
      "grad_norm": 13.14664077758789,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.5139,
      "step": 15
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": 12.264524459838867,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.4759,
      "step": 16
    },
    {
      "epoch": 0.14977973568281938,
      "grad_norm": 12.008437156677246,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.1597,
      "step": 17
    },
    {
      "epoch": 0.15859030837004406,
      "grad_norm": 11.117318153381348,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.9539,
      "step": 18
    },
    {
      "epoch": 0.16740088105726872,
      "grad_norm": 11.550792694091797,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.9259,
      "step": 19
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 13.204764366149902,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.3515,
      "step": 20
    },
    {
      "epoch": 0.18502202643171806,
      "grad_norm": 11.79154109954834,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.4793,
      "step": 21
    },
    {
      "epoch": 0.19383259911894274,
      "grad_norm": 12.395256042480469,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.1954,
      "step": 22
    },
    {
      "epoch": 0.2026431718061674,
      "grad_norm": 12.652040481567383,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.2384,
      "step": 23
    },
    {
      "epoch": 0.21145374449339208,
      "grad_norm": 11.535292625427246,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.6493,
      "step": 24
    },
    {
      "epoch": 0.22026431718061673,
      "grad_norm": 12.167210578918457,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.1739,
      "step": 25
    },
    {
      "epoch": 0.22026431718061673,
      "eval_loss": 1.0978758335113525,
      "eval_runtime": 6.9278,
      "eval_samples_per_second": 27.715,
      "eval_steps_per_second": 3.464,
      "step": 25
    },
    {
      "epoch": 0.2290748898678414,
      "grad_norm": 13.215066909790039,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.2612,
      "step": 26
    },
    {
      "epoch": 0.23788546255506607,
      "grad_norm": 13.42513656616211,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.7723,
      "step": 27
    },
    {
      "epoch": 0.24669603524229075,
      "grad_norm": 29.157196044921875,
      "learning_rate": 4.825502516487497e-05,
      "loss": 5.5152,
      "step": 28
    },
    {
      "epoch": 0.2555066079295154,
      "grad_norm": 35.22280502319336,
      "learning_rate": 4.477357683661734e-05,
      "loss": 5.2248,
      "step": 29
    },
    {
      "epoch": 0.2643171806167401,
      "grad_norm": 28.826953887939453,
      "learning_rate": 4.131759111665349e-05,
      "loss": 5.2727,
      "step": 30
    },
    {
      "epoch": 0.27312775330396477,
      "grad_norm": 17.708860397338867,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.621,
      "step": 31
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": 12.685564041137695,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.4044,
      "step": 32
    },
    {
      "epoch": 0.2907488986784141,
      "grad_norm": 10.034717559814453,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.948,
      "step": 33
    },
    {
      "epoch": 0.29955947136563876,
      "grad_norm": 10.584023475646973,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.025,
      "step": 34
    },
    {
      "epoch": 0.30837004405286345,
      "grad_norm": 10.168135643005371,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.8759,
      "step": 35
    },
    {
      "epoch": 0.31718061674008813,
      "grad_norm": 10.681046485900879,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.8895,
      "step": 36
    },
    {
      "epoch": 0.32599118942731276,
      "grad_norm": 10.135737419128418,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.7677,
      "step": 37
    },
    {
      "epoch": 0.33480176211453744,
      "grad_norm": 10.632367134094238,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.898,
      "step": 38
    },
    {
      "epoch": 0.3436123348017621,
      "grad_norm": 10.495468139648438,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.5627,
      "step": 39
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": 12.4844970703125,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.6167,
      "step": 40
    },
    {
      "epoch": 0.36123348017621143,
      "grad_norm": 11.088768005371094,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.134,
      "step": 41
    },
    {
      "epoch": 0.3700440528634361,
      "grad_norm": 10.535295486450195,
      "learning_rate": 7.597595192178702e-06,
      "loss": 4.1006,
      "step": 42
    },
    {
      "epoch": 0.3788546255506608,
      "grad_norm": 11.320088386535645,
      "learning_rate": 5.852620357053651e-06,
      "loss": 4.0713,
      "step": 43
    },
    {
      "epoch": 0.3876651982378855,
      "grad_norm": 10.537118911743164,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.7378,
      "step": 44
    },
    {
      "epoch": 0.3964757709251101,
      "grad_norm": 12.482701301574707,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.5002,
      "step": 45
    },
    {
      "epoch": 0.4052863436123348,
      "grad_norm": 12.518914222717285,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.9898,
      "step": 46
    },
    {
      "epoch": 0.41409691629955947,
      "grad_norm": 11.440350532531738,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.7755,
      "step": 47
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": 11.552277565002441,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.6187,
      "step": 48
    },
    {
      "epoch": 0.43171806167400884,
      "grad_norm": 13.912178039550781,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 4.1552,
      "step": 49
    },
    {
      "epoch": 0.44052863436123346,
      "grad_norm": 12.204792022705078,
      "learning_rate": 0.0,
      "loss": 4.1909,
      "step": 50
    },
    {
      "epoch": 0.44052863436123346,
      "eval_loss": 1.0094060897827148,
      "eval_runtime": 6.9686,
      "eval_samples_per_second": 27.552,
      "eval_steps_per_second": 3.444,
      "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
}