{
  "best_metric": 4.455350399017334,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.8368200836820083,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 14.671270370483398,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 10.2306,
      "step": 1
    },
    {
      "epoch": 0.016736401673640166,
      "eval_loss": 10.369909286499023,
      "eval_runtime": 3.2742,
      "eval_samples_per_second": 30.847,
      "eval_steps_per_second": 3.97,
      "step": 1
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 14.328125,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 10.2034,
      "step": 2
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 14.797067642211914,
      "learning_rate": 5.000000000000001e-07,
      "loss": 10.2635,
      "step": 3
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 14.43250560760498,
      "learning_rate": 6.666666666666667e-07,
      "loss": 10.26,
      "step": 4
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 14.240781784057617,
      "learning_rate": 8.333333333333333e-07,
      "loss": 10.3516,
      "step": 5
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 14.158472061157227,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 10.3179,
      "step": 6
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 13.55285930633545,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 10.2092,
      "step": 7
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 13.010944366455078,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 10.3638,
      "step": 8
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 13.396709442138672,
      "learning_rate": 1.5e-06,
      "loss": 10.5753,
      "step": 9
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 13.725341796875,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 10.3501,
      "step": 10
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 12.478100776672363,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 10.3688,
      "step": 11
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 11.60485553741455,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 10.3377,
      "step": 12
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 11.682891845703125,
      "learning_rate": 2.166666666666667e-06,
      "loss": 10.3302,
      "step": 13
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 12.023148536682129,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 10.5306,
      "step": 14
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 14.947415351867676,
      "learning_rate": 2.5e-06,
      "loss": 10.3194,
      "step": 15
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 14.228991508483887,
      "learning_rate": 2.666666666666667e-06,
      "loss": 10.3125,
      "step": 16
    },
    {
      "epoch": 0.28451882845188287,
      "grad_norm": 13.104813575744629,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 9.8595,
      "step": 17
    },
    {
      "epoch": 0.301255230125523,
      "grad_norm": 13.878166198730469,
      "learning_rate": 3e-06,
      "loss": 9.8988,
      "step": 18
    },
    {
      "epoch": 0.3179916317991632,
      "grad_norm": 14.564827919006348,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 10.0827,
      "step": 19
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 14.366488456726074,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 9.8542,
      "step": 20
    },
    {
      "epoch": 0.3514644351464435,
      "grad_norm": 13.876509666442871,
      "learning_rate": 3.5e-06,
      "loss": 9.9533,
      "step": 21
    },
    {
      "epoch": 0.3682008368200837,
      "grad_norm": 13.74383544921875,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 9.7412,
      "step": 22
    },
    {
      "epoch": 0.38493723849372385,
      "grad_norm": 13.74951171875,
      "learning_rate": 3.833333333333334e-06,
      "loss": 9.6477,
      "step": 23
    },
    {
      "epoch": 0.401673640167364,
      "grad_norm": 13.71518325805664,
      "learning_rate": 4.000000000000001e-06,
      "loss": 9.6774,
      "step": 24
    },
    {
      "epoch": 0.41841004184100417,
      "grad_norm": 13.004035949707031,
      "learning_rate": 4.166666666666667e-06,
      "loss": 9.4434,
      "step": 25
    },
    {
      "epoch": 0.4351464435146444,
      "grad_norm": 13.47214126586914,
      "learning_rate": 4.333333333333334e-06,
      "loss": 9.7347,
      "step": 26
    },
    {
      "epoch": 0.45188284518828453,
      "grad_norm": 11.91252326965332,
      "learning_rate": 4.5e-06,
      "loss": 9.3702,
      "step": 27
    },
    {
      "epoch": 0.4686192468619247,
      "grad_norm": 12.803349494934082,
      "learning_rate": 4.666666666666667e-06,
      "loss": 9.4046,
      "step": 28
    },
    {
      "epoch": 0.48535564853556484,
      "grad_norm": 15.152267456054688,
      "learning_rate": 4.833333333333333e-06,
      "loss": 8.7671,
      "step": 29
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 14.327988624572754,
      "learning_rate": 5e-06,
      "loss": 8.4576,
      "step": 30
    },
    {
      "epoch": 0.5188284518828452,
      "grad_norm": 14.064353942871094,
      "learning_rate": 4.997482666353287e-06,
      "loss": 8.3482,
      "step": 31
    },
    {
      "epoch": 0.5355648535564853,
      "grad_norm": 14.080218315124512,
      "learning_rate": 4.989935734988098e-06,
      "loss": 8.2583,
      "step": 32
    },
    {
      "epoch": 0.5523012552301255,
      "grad_norm": 14.388766288757324,
      "learning_rate": 4.977374404419838e-06,
      "loss": 7.9582,
      "step": 33
    },
    {
      "epoch": 0.5690376569037657,
      "grad_norm": 13.374934196472168,
      "learning_rate": 4.959823971496575e-06,
      "loss": 7.8623,
      "step": 34
    },
    {
      "epoch": 0.5857740585774058,
      "grad_norm": 13.262751579284668,
      "learning_rate": 4.937319780454559e-06,
      "loss": 7.6083,
      "step": 35
    },
    {
      "epoch": 0.602510460251046,
      "grad_norm": 13.282503128051758,
      "learning_rate": 4.909907151739634e-06,
      "loss": 7.4737,
      "step": 36
    },
    {
      "epoch": 0.6192468619246861,
      "grad_norm": 13.080615043640137,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 7.3853,
      "step": 37
    },
    {
      "epoch": 0.6359832635983264,
      "grad_norm": 12.566425323486328,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 7.478,
      "step": 38
    },
    {
      "epoch": 0.6527196652719666,
      "grad_norm": 12.705647468566895,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 7.0334,
      "step": 39
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 12.801064491271973,
      "learning_rate": 4.752422169756048e-06,
      "loss": 6.9515,
      "step": 40
    },
    {
      "epoch": 0.6861924686192469,
      "grad_norm": 12.665898323059082,
      "learning_rate": 4.701488829641845e-06,
      "loss": 6.9226,
      "step": 41
    },
    {
      "epoch": 0.702928870292887,
      "grad_norm": 12.849478721618652,
      "learning_rate": 4.646121984004666e-06,
      "loss": 7.0246,
      "step": 42
    },
    {
      "epoch": 0.7196652719665272,
      "grad_norm": 13.124124526977539,
      "learning_rate": 4.586433134303257e-06,
      "loss": 5.601,
      "step": 43
    },
    {
      "epoch": 0.7364016736401674,
      "grad_norm": 12.630464553833008,
      "learning_rate": 4.522542485937369e-06,
      "loss": 5.2646,
      "step": 44
    },
    {
      "epoch": 0.7531380753138075,
      "grad_norm": 12.385834693908691,
      "learning_rate": 4.454578706170075e-06,
      "loss": 5.2738,
      "step": 45
    },
    {
      "epoch": 0.7698744769874477,
      "grad_norm": 12.193803787231445,
      "learning_rate": 4.382678665009028e-06,
      "loss": 5.2841,
      "step": 46
    },
    {
      "epoch": 0.7866108786610879,
      "grad_norm": 12.115005493164062,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 5.0223,
      "step": 47
    },
    {
      "epoch": 0.803347280334728,
      "grad_norm": 11.783625602722168,
      "learning_rate": 4.227656622467162e-06,
      "loss": 4.9352,
      "step": 48
    },
    {
      "epoch": 0.8200836820083682,
      "grad_norm": 11.882129669189453,
      "learning_rate": 4.144846814849282e-06,
      "loss": 4.845,
      "step": 49
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 11.96120834350586,
      "learning_rate": 4.058724504646834e-06,
      "loss": 4.6088,
      "step": 50
    },
    {
      "epoch": 0.8368200836820083,
      "eval_loss": 4.455350399017334,
      "eval_runtime": 2.9147,
      "eval_samples_per_second": 34.651,
      "eval_steps_per_second": 4.46,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.34680040964096e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}