{
  "best_metric": 2.088284492492676,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.050100200400801605,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001002004008016032,
      "grad_norm": 1.9892041683197021,
      "learning_rate": 1e-05,
      "loss": 3.228,
      "step": 1
    },
    {
      "epoch": 0.001002004008016032,
      "eval_loss": 3.713639497756958,
      "eval_runtime": 9.9764,
      "eval_samples_per_second": 168.497,
      "eval_steps_per_second": 21.15,
      "step": 1
    },
    {
      "epoch": 0.002004008016032064,
      "grad_norm": 2.06142520904541,
      "learning_rate": 2e-05,
      "loss": 3.3001,
      "step": 2
    },
    {
      "epoch": 0.003006012024048096,
      "grad_norm": 1.839006781578064,
      "learning_rate": 3e-05,
      "loss": 3.1721,
      "step": 3
    },
    {
      "epoch": 0.004008016032064128,
      "grad_norm": 2.000424861907959,
      "learning_rate": 4e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.00501002004008016,
      "grad_norm": 1.9487165212631226,
      "learning_rate": 5e-05,
      "loss": 3.2505,
      "step": 5
    },
    {
      "epoch": 0.006012024048096192,
      "grad_norm": 1.8743599653244019,
      "learning_rate": 6e-05,
      "loss": 3.3262,
      "step": 6
    },
    {
      "epoch": 0.0070140280561122245,
      "grad_norm": 1.6559370756149292,
      "learning_rate": 7e-05,
      "loss": 3.2131,
      "step": 7
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 1.6868617534637451,
      "learning_rate": 8e-05,
      "loss": 3.1389,
      "step": 8
    },
    {
      "epoch": 0.009018036072144289,
      "grad_norm": 1.593652606010437,
      "learning_rate": 9e-05,
      "loss": 3.1291,
      "step": 9
    },
    {
      "epoch": 0.01002004008016032,
      "grad_norm": 1.531032681465149,
      "learning_rate": 0.0001,
      "loss": 3.1035,
      "step": 10
    },
    {
      "epoch": 0.011022044088176353,
      "grad_norm": 1.59713876247406,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.0948,
      "step": 11
    },
    {
      "epoch": 0.012024048096192385,
      "grad_norm": 1.5284147262573242,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8201,
      "step": 12
    },
    {
      "epoch": 0.013026052104208416,
      "grad_norm": 1.542348027229309,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.8589,
      "step": 13
    },
    {
      "epoch": 0.014028056112224449,
      "grad_norm": 1.7238450050354004,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.8647,
      "step": 14
    },
    {
      "epoch": 0.01503006012024048,
      "grad_norm": 1.7485935688018799,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.7815,
      "step": 15
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 1.9041484594345093,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.751,
      "step": 16
    },
    {
      "epoch": 0.017034068136272545,
      "grad_norm": 1.754050850868225,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.6011,
      "step": 17
    },
    {
      "epoch": 0.018036072144288578,
      "grad_norm": 1.5712624788284302,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6006,
      "step": 18
    },
    {
      "epoch": 0.01903807615230461,
      "grad_norm": 1.6208561658859253,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.57,
      "step": 19
    },
    {
      "epoch": 0.02004008016032064,
      "grad_norm": 1.7021604776382446,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5362,
      "step": 20
    },
    {
      "epoch": 0.021042084168336674,
      "grad_norm": 1.6615126132965088,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4146,
      "step": 21
    },
    {
      "epoch": 0.022044088176352707,
      "grad_norm": 1.4819920063018799,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.4761,
      "step": 22
    },
    {
      "epoch": 0.023046092184368736,
      "grad_norm": 1.5472745895385742,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.3338,
      "step": 23
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 1.9091078042984009,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3523,
      "step": 24
    },
    {
      "epoch": 0.025050100200400802,
      "grad_norm": 1.7454297542572021,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3323,
      "step": 25
    },
    {
      "epoch": 0.026052104208416832,
      "grad_norm": 1.334761142730713,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.3424,
      "step": 26
    },
    {
      "epoch": 0.027054108216432865,
      "grad_norm": 1.5471727848052979,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3023,
      "step": 27
    },
    {
      "epoch": 0.028056112224448898,
      "grad_norm": 2.1018128395080566,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3096,
      "step": 28
    },
    {
      "epoch": 0.02905811623246493,
      "grad_norm": 2.2362749576568604,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.4362,
      "step": 29
    },
    {
      "epoch": 0.03006012024048096,
      "grad_norm": 1.7347625494003296,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.4654,
      "step": 30
    },
    {
      "epoch": 0.031062124248496994,
      "grad_norm": 1.1744818687438965,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.2959,
      "step": 31
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 1.3074371814727783,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2445,
      "step": 32
    },
    {
      "epoch": 0.033066132264529056,
      "grad_norm": 1.2176134586334229,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.212,
      "step": 33
    },
    {
      "epoch": 0.03406813627254509,
      "grad_norm": 1.319883942604065,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2957,
      "step": 34
    },
    {
      "epoch": 0.03507014028056112,
      "grad_norm": 1.2122143507003784,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3501,
      "step": 35
    },
    {
      "epoch": 0.036072144288577156,
      "grad_norm": 1.1644178628921509,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.226,
      "step": 36
    },
    {
      "epoch": 0.03707414829659319,
      "grad_norm": 1.1486573219299316,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2286,
      "step": 37
    },
    {
      "epoch": 0.03807615230460922,
      "grad_norm": 1.1184206008911133,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.1459,
      "step": 38
    },
    {
      "epoch": 0.03907815631262525,
      "grad_norm": 1.2232961654663086,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.2814,
      "step": 39
    },
    {
      "epoch": 0.04008016032064128,
      "grad_norm": 1.3489000797271729,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3264,
      "step": 40
    },
    {
      "epoch": 0.041082164328657314,
      "grad_norm": 1.279327154159546,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3779,
      "step": 41
    },
    {
      "epoch": 0.04208416833667335,
      "grad_norm": 1.269199013710022,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.26,
      "step": 42
    },
    {
      "epoch": 0.04308617234468938,
      "grad_norm": 1.5359389781951904,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.355,
      "step": 43
    },
    {
      "epoch": 0.04408817635270541,
      "grad_norm": 1.267220377922058,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.1603,
      "step": 44
    },
    {
      "epoch": 0.045090180360721446,
      "grad_norm": 1.2115416526794434,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0991,
      "step": 45
    },
    {
      "epoch": 0.04609218436873747,
      "grad_norm": 1.1847515106201172,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1158,
      "step": 46
    },
    {
      "epoch": 0.047094188376753505,
      "grad_norm": 1.1961596012115479,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1763,
      "step": 47
    },
    {
      "epoch": 0.04809619238476954,
      "grad_norm": 2.5090718269348145,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2434,
      "step": 48
    },
    {
      "epoch": 0.04909819639278557,
      "grad_norm": 1.6135358810424805,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.3868,
      "step": 49
    },
    {
      "epoch": 0.050100200400801605,
      "grad_norm": 1.4976840019226074,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.3013,
      "step": 50
    },
    {
      "epoch": 0.050100200400801605,
      "eval_loss": 2.088284492492676,
      "eval_runtime": 9.5901,
      "eval_samples_per_second": 175.286,
      "eval_steps_per_second": 22.002,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1488394911744000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}