{
  "best_metric": 2.271299362182617,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01365280906546522,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002730561813093044,
      "grad_norm": 43.446266174316406,
      "learning_rate": 1e-05,
      "loss": 10.0397,
      "step": 1
    },
    {
      "epoch": 0.0002730561813093044,
      "eval_loss": 4.238278865814209,
      "eval_runtime": 693.1619,
      "eval_samples_per_second": 8.898,
      "eval_steps_per_second": 2.225,
      "step": 1
    },
    {
      "epoch": 0.0005461123626186088,
      "grad_norm": 44.35715866088867,
      "learning_rate": 2e-05,
      "loss": 11.7295,
      "step": 2
    },
    {
      "epoch": 0.0008191685439279131,
      "grad_norm": 49.75259017944336,
      "learning_rate": 3e-05,
      "loss": 11.851,
      "step": 3
    },
    {
      "epoch": 0.0010922247252372176,
      "grad_norm": 46.56555938720703,
      "learning_rate": 4e-05,
      "loss": 11.3896,
      "step": 4
    },
    {
      "epoch": 0.0013652809065465218,
      "grad_norm": 40.56822967529297,
      "learning_rate": 5e-05,
      "loss": 10.777,
      "step": 5
    },
    {
      "epoch": 0.0016383370878558263,
      "grad_norm": 29.243772506713867,
      "learning_rate": 6e-05,
      "loss": 8.8778,
      "step": 6
    },
    {
      "epoch": 0.0019113932691651307,
      "grad_norm": 27.35118293762207,
      "learning_rate": 7e-05,
      "loss": 8.5317,
      "step": 7
    },
    {
      "epoch": 0.0021844494504744353,
      "grad_norm": 28.01230239868164,
      "learning_rate": 8e-05,
      "loss": 8.6976,
      "step": 8
    },
    {
      "epoch": 0.0024575056317837395,
      "grad_norm": 24.44605255126953,
      "learning_rate": 9e-05,
      "loss": 9.1925,
      "step": 9
    },
    {
      "epoch": 0.0027305618130930437,
      "grad_norm": 25.969579696655273,
      "learning_rate": 0.0001,
      "loss": 8.022,
      "step": 10
    },
    {
      "epoch": 0.0030036179944023483,
      "grad_norm": 27.08025550842285,
      "learning_rate": 9.999316524962345e-05,
      "loss": 9.1533,
      "step": 11
    },
    {
      "epoch": 0.0032766741757116525,
      "grad_norm": 18.790332794189453,
      "learning_rate": 9.997266286704631e-05,
      "loss": 7.5891,
      "step": 12
    },
    {
      "epoch": 0.003549730357020957,
      "grad_norm": 23.858049392700195,
      "learning_rate": 9.993849845741524e-05,
      "loss": 9.0651,
      "step": 13
    },
    {
      "epoch": 0.0038227865383302613,
      "grad_norm": 20.80962562561035,
      "learning_rate": 9.989068136093873e-05,
      "loss": 7.7469,
      "step": 14
    },
    {
      "epoch": 0.0040958427196395655,
      "grad_norm": 21.938926696777344,
      "learning_rate": 9.98292246503335e-05,
      "loss": 8.5726,
      "step": 15
    },
    {
      "epoch": 0.004368898900948871,
      "grad_norm": 19.670955657958984,
      "learning_rate": 9.975414512725057e-05,
      "loss": 7.9194,
      "step": 16
    },
    {
      "epoch": 0.004641955082258175,
      "grad_norm": 21.373003005981445,
      "learning_rate": 9.966546331768191e-05,
      "loss": 8.5548,
      "step": 17
    },
    {
      "epoch": 0.004915011263567479,
      "grad_norm": 21.677001953125,
      "learning_rate": 9.956320346634876e-05,
      "loss": 7.7842,
      "step": 18
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 21.132835388183594,
      "learning_rate": 9.944739353007344e-05,
      "loss": 9.1783,
      "step": 19
    },
    {
      "epoch": 0.005461123626186087,
      "grad_norm": 19.698659896850586,
      "learning_rate": 9.931806517013612e-05,
      "loss": 7.6789,
      "step": 20
    },
    {
      "epoch": 0.0057341798074953924,
      "grad_norm": 26.263071060180664,
      "learning_rate": 9.917525374361912e-05,
      "loss": 8.8006,
      "step": 21
    },
    {
      "epoch": 0.006007235988804697,
      "grad_norm": 19.799365997314453,
      "learning_rate": 9.901899829374047e-05,
      "loss": 8.5378,
      "step": 22
    },
    {
      "epoch": 0.006280292170114001,
      "grad_norm": 25.806068420410156,
      "learning_rate": 9.884934153917997e-05,
      "loss": 8.5017,
      "step": 23
    },
    {
      "epoch": 0.006553348351423305,
      "grad_norm": 24.34381866455078,
      "learning_rate": 9.86663298624003e-05,
      "loss": 8.9881,
      "step": 24
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 18.999231338500977,
      "learning_rate": 9.847001329696653e-05,
      "loss": 7.9945,
      "step": 25
    },
    {
      "epoch": 0.007099460714041914,
      "grad_norm": 20.11553382873535,
      "learning_rate": 9.826044551386744e-05,
      "loss": 8.4672,
      "step": 26
    },
    {
      "epoch": 0.0073725168953512185,
      "grad_norm": 21.312238693237305,
      "learning_rate": 9.803768380684242e-05,
      "loss": 8.6953,
      "step": 27
    },
    {
      "epoch": 0.007645573076660523,
      "grad_norm": 31.490800857543945,
      "learning_rate": 9.780178907671789e-05,
      "loss": 9.7065,
      "step": 28
    },
    {
      "epoch": 0.007918629257969828,
      "grad_norm": 20.707792282104492,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.5876,
      "step": 29
    },
    {
      "epoch": 0.008191685439279131,
      "grad_norm": 19.695018768310547,
      "learning_rate": 9.729086208503174e-05,
      "loss": 8.0395,
      "step": 30
    },
    {
      "epoch": 0.008464741620588436,
      "grad_norm": 21.563302993774414,
      "learning_rate": 9.701596950580806e-05,
      "loss": 7.869,
      "step": 31
    },
    {
      "epoch": 0.008737797801897741,
      "grad_norm": 25.480226516723633,
      "learning_rate": 9.672822322997305e-05,
      "loss": 8.0559,
      "step": 32
    },
    {
      "epoch": 0.009010853983207045,
      "grad_norm": 23.27593231201172,
      "learning_rate": 9.642770192448536e-05,
      "loss": 8.9705,
      "step": 33
    },
    {
      "epoch": 0.00928391016451635,
      "grad_norm": 22.600749969482422,
      "learning_rate": 9.611448774886924e-05,
      "loss": 8.3754,
      "step": 34
    },
    {
      "epoch": 0.009556966345825653,
      "grad_norm": 24.033321380615234,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.4395,
      "step": 35
    },
    {
      "epoch": 0.009830022527134958,
      "grad_norm": 25.064741134643555,
      "learning_rate": 9.545032675245813e-05,
      "loss": 8.8034,
      "step": 36
    },
    {
      "epoch": 0.010103078708444263,
      "grad_norm": 28.80820083618164,
      "learning_rate": 9.509956150664796e-05,
      "loss": 8.2912,
      "step": 37
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 29.365997314453125,
      "learning_rate": 9.473646649103818e-05,
      "loss": 7.6412,
      "step": 38
    },
    {
      "epoch": 0.010649191071062871,
      "grad_norm": 22.005088806152344,
      "learning_rate": 9.43611409721806e-05,
      "loss": 8.3727,
      "step": 39
    },
    {
      "epoch": 0.010922247252372175,
      "grad_norm": 22.131328582763672,
      "learning_rate": 9.397368756032445e-05,
      "loss": 7.4845,
      "step": 40
    },
    {
      "epoch": 0.01119530343368148,
      "grad_norm": 26.777101516723633,
      "learning_rate": 9.357421218136386e-05,
      "loss": 8.6799,
      "step": 41
    },
    {
      "epoch": 0.011468359614990785,
      "grad_norm": 27.420764923095703,
      "learning_rate": 9.316282404787871e-05,
      "loss": 8.6992,
      "step": 42
    },
    {
      "epoch": 0.011741415796300088,
      "grad_norm": 27.803956985473633,
      "learning_rate": 9.273963562927695e-05,
      "loss": 9.0848,
      "step": 43
    },
    {
      "epoch": 0.012014471977609393,
      "grad_norm": 32.42679214477539,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.5448,
      "step": 44
    },
    {
      "epoch": 0.012287528158918698,
      "grad_norm": 28.605180740356445,
      "learning_rate": 9.185832391312644e-05,
      "loss": 8.5635,
      "step": 45
    },
    {
      "epoch": 0.012560584340228002,
      "grad_norm": 28.457530975341797,
      "learning_rate": 9.140044155740101e-05,
      "loss": 9.0221,
      "step": 46
    },
    {
      "epoch": 0.012833640521537307,
      "grad_norm": 24.8094425201416,
      "learning_rate": 9.093124073433463e-05,
      "loss": 7.0862,
      "step": 47
    },
    {
      "epoch": 0.01310669670284661,
      "grad_norm": 30.082542419433594,
      "learning_rate": 9.045084971874738e-05,
      "loss": 8.431,
      "step": 48
    },
    {
      "epoch": 0.013379752884155915,
      "grad_norm": 26.035165786743164,
      "learning_rate": 8.995939984474624e-05,
      "loss": 8.7725,
      "step": 49
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 48.76018142700195,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.7992,
      "step": 50
    },
    {
      "epoch": 0.01365280906546522,
      "eval_loss": 2.271299362182617,
      "eval_runtime": 698.4085,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 2.208,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 7.15499004493824e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}