{
  "best_metric": 0.3447200655937195,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03772161448509996,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007544322897019992,
      "grad_norm": 0.8274133801460266,
      "learning_rate": 2e-05,
      "loss": 0.2964,
      "step": 1
    },
    {
      "epoch": 0.0007544322897019992,
      "eval_loss": 0.7299715876579285,
      "eval_runtime": 20.3801,
      "eval_samples_per_second": 109.568,
      "eval_steps_per_second": 13.739,
      "step": 1
    },
    {
      "epoch": 0.0015088645794039985,
      "grad_norm": 1.09823477268219,
      "learning_rate": 4e-05,
      "loss": 0.4161,
      "step": 2
    },
    {
      "epoch": 0.002263296869105998,
      "grad_norm": 1.4425480365753174,
      "learning_rate": 6e-05,
      "loss": 0.6274,
      "step": 3
    },
    {
      "epoch": 0.003017729158807997,
      "grad_norm": 1.3848803043365479,
      "learning_rate": 8e-05,
      "loss": 0.7209,
      "step": 4
    },
    {
      "epoch": 0.003772161448509996,
      "grad_norm": 1.6569702625274658,
      "learning_rate": 0.0001,
      "loss": 0.6621,
      "step": 5
    },
    {
      "epoch": 0.004526593738211996,
      "grad_norm": 1.4166218042373657,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7256,
      "step": 6
    },
    {
      "epoch": 0.005281026027913994,
      "grad_norm": 1.8955013751983643,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8542,
      "step": 7
    },
    {
      "epoch": 0.006035458317615994,
      "grad_norm": 1.964434027671814,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.849,
      "step": 8
    },
    {
      "epoch": 0.0067898906073179935,
      "grad_norm": 1.2425155639648438,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.58,
      "step": 9
    },
    {
      "epoch": 0.007544322897019992,
      "grad_norm": 1.0349457263946533,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4601,
      "step": 10
    },
    {
      "epoch": 0.008298755186721992,
      "grad_norm": 1.093508005142212,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.4566,
      "step": 11
    },
    {
      "epoch": 0.009053187476423991,
      "grad_norm": 1.153257966041565,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5095,
      "step": 12
    },
    {
      "epoch": 0.00980761976612599,
      "grad_norm": 0.9498189091682434,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4566,
      "step": 13
    },
    {
      "epoch": 0.010562052055827989,
      "grad_norm": 0.9866612553596497,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3953,
      "step": 14
    },
    {
      "epoch": 0.011316484345529988,
      "grad_norm": 0.8231657147407532,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2715,
      "step": 15
    },
    {
      "epoch": 0.012070916635231988,
      "grad_norm": 1.0097391605377197,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.4958,
      "step": 16
    },
    {
      "epoch": 0.012825348924933987,
      "grad_norm": 1.0180126428604126,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4226,
      "step": 17
    },
    {
      "epoch": 0.013579781214635987,
      "grad_norm": 0.902682363986969,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3739,
      "step": 18
    },
    {
      "epoch": 0.014334213504337986,
      "grad_norm": 0.825958788394928,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3627,
      "step": 19
    },
    {
      "epoch": 0.015088645794039984,
      "grad_norm": 0.8558096289634705,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.32,
      "step": 20
    },
    {
      "epoch": 0.015843078083741986,
      "grad_norm": 0.9081395864486694,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2988,
      "step": 21
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": 0.839869499206543,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3523,
      "step": 22
    },
    {
      "epoch": 0.01735194266314598,
      "grad_norm": 0.9551442861557007,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4289,
      "step": 23
    },
    {
      "epoch": 0.018106374952847983,
      "grad_norm": 0.7349039316177368,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2781,
      "step": 24
    },
    {
      "epoch": 0.01886080724254998,
      "grad_norm": 0.7527700662612915,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2911,
      "step": 25
    },
    {
      "epoch": 0.01886080724254998,
      "eval_loss": 0.37324193120002747,
      "eval_runtime": 20.3384,
      "eval_samples_per_second": 109.792,
      "eval_steps_per_second": 13.767,
      "step": 25
    },
    {
      "epoch": 0.01961523953225198,
      "grad_norm": 0.7944580316543579,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.3518,
      "step": 26
    },
    {
      "epoch": 0.02036967182195398,
      "grad_norm": 0.8035205006599426,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2861,
      "step": 27
    },
    {
      "epoch": 0.021124104111655977,
      "grad_norm": 0.8863422870635986,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3642,
      "step": 28
    },
    {
      "epoch": 0.02187853640135798,
      "grad_norm": 0.9828726649284363,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3992,
      "step": 29
    },
    {
      "epoch": 0.022632968691059976,
      "grad_norm": 0.8663574457168579,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2985,
      "step": 30
    },
    {
      "epoch": 0.023387400980761978,
      "grad_norm": 0.7883567214012146,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.3014,
      "step": 31
    },
    {
      "epoch": 0.024141833270463976,
      "grad_norm": 0.6813034415245056,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2094,
      "step": 32
    },
    {
      "epoch": 0.024896265560165973,
      "grad_norm": 0.9920178055763245,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3045,
      "step": 33
    },
    {
      "epoch": 0.025650697849867975,
      "grad_norm": 0.7917585968971252,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.3264,
      "step": 34
    },
    {
      "epoch": 0.026405130139569973,
      "grad_norm": 0.7119764089584351,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2033,
      "step": 35
    },
    {
      "epoch": 0.027159562429271974,
      "grad_norm": 0.8375765681266785,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3211,
      "step": 36
    },
    {
      "epoch": 0.02791399471897397,
      "grad_norm": 0.8587736487388611,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2886,
      "step": 37
    },
    {
      "epoch": 0.028668427008675973,
      "grad_norm": 1.0836652517318726,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4182,
      "step": 38
    },
    {
      "epoch": 0.02942285929837797,
      "grad_norm": 0.9219658374786377,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2996,
      "step": 39
    },
    {
      "epoch": 0.03017729158807997,
      "grad_norm": 0.8775100708007812,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3153,
      "step": 40
    },
    {
      "epoch": 0.03093172387778197,
      "grad_norm": 0.8956629633903503,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.298,
      "step": 41
    },
    {
      "epoch": 0.03168615616748397,
      "grad_norm": 1.0980639457702637,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3067,
      "step": 42
    },
    {
      "epoch": 0.03244058845718597,
      "grad_norm": 0.944616973400116,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.3261,
      "step": 43
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 1.178214192390442,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.3682,
      "step": 44
    },
    {
      "epoch": 0.033949453036589965,
      "grad_norm": 0.9967607855796814,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2924,
      "step": 45
    },
    {
      "epoch": 0.03470388532629196,
      "grad_norm": 1.1236211061477661,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.3553,
      "step": 46
    },
    {
      "epoch": 0.03545831761599397,
      "grad_norm": 1.3691303730010986,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.4054,
      "step": 47
    },
    {
      "epoch": 0.036212749905695965,
      "grad_norm": 1.5612680912017822,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4232,
      "step": 48
    },
    {
      "epoch": 0.03696718219539796,
      "grad_norm": 1.8830749988555908,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3219,
      "step": 49
    },
    {
      "epoch": 0.03772161448509996,
      "grad_norm": 3.1717007160186768,
      "learning_rate": 0.0,
      "loss": 0.5892,
      "step": 50
    },
    {
      "epoch": 0.03772161448509996,
      "eval_loss": 0.3447200655937195,
      "eval_runtime": 20.3319,
      "eval_samples_per_second": 109.828,
      "eval_steps_per_second": 13.771,
      "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": 1999744829227008.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}