{
  "best_metric": 10.33413314819336,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01379690949227373,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002759381898454746,
      "grad_norm": 0.7791844606399536,
      "learning_rate": 2e-05,
      "loss": 41.5156,
      "step": 1
    },
    {
      "epoch": 0.0002759381898454746,
      "eval_loss": 10.377832412719727,
      "eval_runtime": 9.9897,
      "eval_samples_per_second": 611.029,
      "eval_steps_per_second": 76.379,
      "step": 1
    },
    {
      "epoch": 0.0005518763796909492,
      "grad_norm": 0.7612369060516357,
      "learning_rate": 4e-05,
      "loss": 41.5171,
      "step": 2
    },
    {
      "epoch": 0.0008278145695364238,
      "grad_norm": 0.6696538925170898,
      "learning_rate": 6e-05,
      "loss": 41.5131,
      "step": 3
    },
    {
      "epoch": 0.0011037527593818985,
      "grad_norm": 0.707078218460083,
      "learning_rate": 8e-05,
      "loss": 41.514,
      "step": 4
    },
    {
      "epoch": 0.0013796909492273732,
      "grad_norm": 0.6896539926528931,
      "learning_rate": 0.0001,
      "loss": 41.5098,
      "step": 5
    },
    {
      "epoch": 0.0016556291390728477,
      "grad_norm": 0.6793449521064758,
      "learning_rate": 9.987820251299122e-05,
      "loss": 41.505,
      "step": 6
    },
    {
      "epoch": 0.0019315673289183224,
      "grad_norm": 0.8174788355827332,
      "learning_rate": 9.951340343707852e-05,
      "loss": 41.4826,
      "step": 7
    },
    {
      "epoch": 0.002207505518763797,
      "grad_norm": 0.8543055653572083,
      "learning_rate": 9.890738003669029e-05,
      "loss": 41.4971,
      "step": 8
    },
    {
      "epoch": 0.0024834437086092716,
      "grad_norm": 0.9079226851463318,
      "learning_rate": 9.806308479691595e-05,
      "loss": 41.4819,
      "step": 9
    },
    {
      "epoch": 0.0027593818984547464,
      "grad_norm": 0.955985963344574,
      "learning_rate": 9.698463103929542e-05,
      "loss": 41.4738,
      "step": 10
    },
    {
      "epoch": 0.0030353200883002206,
      "grad_norm": 0.8214102983474731,
      "learning_rate": 9.567727288213005e-05,
      "loss": 41.491,
      "step": 11
    },
    {
      "epoch": 0.0033112582781456954,
      "grad_norm": 0.9615162014961243,
      "learning_rate": 9.414737964294636e-05,
      "loss": 41.4748,
      "step": 12
    },
    {
      "epoch": 0.00358719646799117,
      "grad_norm": 1.1011090278625488,
      "learning_rate": 9.24024048078213e-05,
      "loss": 41.4785,
      "step": 13
    },
    {
      "epoch": 0.003863134657836645,
      "grad_norm": 1.0929936170578003,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.4648,
      "step": 14
    },
    {
      "epoch": 0.0041390728476821195,
      "grad_norm": 1.2187824249267578,
      "learning_rate": 8.83022221559489e-05,
      "loss": 41.4642,
      "step": 15
    },
    {
      "epoch": 0.004415011037527594,
      "grad_norm": 1.2300453186035156,
      "learning_rate": 8.596699001693255e-05,
      "loss": 41.4482,
      "step": 16
    },
    {
      "epoch": 0.004690949227373068,
      "grad_norm": 1.3272128105163574,
      "learning_rate": 8.345653031794292e-05,
      "loss": 41.4428,
      "step": 17
    },
    {
      "epoch": 0.004966887417218543,
      "grad_norm": 1.5467745065689087,
      "learning_rate": 8.07830737662829e-05,
      "loss": 41.4327,
      "step": 18
    },
    {
      "epoch": 0.0052428256070640175,
      "grad_norm": 1.5245789289474487,
      "learning_rate": 7.795964517353735e-05,
      "loss": 41.4263,
      "step": 19
    },
    {
      "epoch": 0.005518763796909493,
      "grad_norm": 1.402025818824768,
      "learning_rate": 7.500000000000001e-05,
      "loss": 41.4265,
      "step": 20
    },
    {
      "epoch": 0.005794701986754967,
      "grad_norm": 1.3673166036605835,
      "learning_rate": 7.191855733945387e-05,
      "loss": 41.4348,
      "step": 21
    },
    {
      "epoch": 0.006070640176600441,
      "grad_norm": 1.5262682437896729,
      "learning_rate": 6.873032967079561e-05,
      "loss": 41.4242,
      "step": 22
    },
    {
      "epoch": 0.0063465783664459164,
      "grad_norm": 1.6054350137710571,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.4178,
      "step": 23
    },
    {
      "epoch": 0.006622516556291391,
      "grad_norm": 1.657697319984436,
      "learning_rate": 6.209609477998338e-05,
      "loss": 41.4017,
      "step": 24
    },
    {
      "epoch": 0.006898454746136865,
      "grad_norm": 1.6588268280029297,
      "learning_rate": 5.868240888334653e-05,
      "loss": 41.4046,
      "step": 25
    },
    {
      "epoch": 0.006898454746136865,
      "eval_loss": 10.3482084274292,
      "eval_runtime": 10.0013,
      "eval_samples_per_second": 610.32,
      "eval_steps_per_second": 76.29,
      "step": 25
    },
    {
      "epoch": 0.00717439293598234,
      "grad_norm": 1.8097715377807617,
      "learning_rate": 5.522642316338268e-05,
      "loss": 41.3958,
      "step": 26
    },
    {
      "epoch": 0.0074503311258278145,
      "grad_norm": 1.8108034133911133,
      "learning_rate": 5.174497483512506e-05,
      "loss": 41.3864,
      "step": 27
    },
    {
      "epoch": 0.00772626931567329,
      "grad_norm": 1.754759669303894,
      "learning_rate": 4.825502516487497e-05,
      "loss": 41.3837,
      "step": 28
    },
    {
      "epoch": 0.008002207505518763,
      "grad_norm": 1.8080745935440063,
      "learning_rate": 4.477357683661734e-05,
      "loss": 41.3763,
      "step": 29
    },
    {
      "epoch": 0.008278145695364239,
      "grad_norm": 1.805918574333191,
      "learning_rate": 4.131759111665349e-05,
      "loss": 41.3753,
      "step": 30
    },
    {
      "epoch": 0.008554083885209713,
      "grad_norm": 1.8674601316452026,
      "learning_rate": 3.790390522001662e-05,
      "loss": 41.3552,
      "step": 31
    },
    {
      "epoch": 0.008830022075055188,
      "grad_norm": 1.57460355758667,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.3589,
      "step": 32
    },
    {
      "epoch": 0.009105960264900662,
      "grad_norm": 1.5840908288955688,
      "learning_rate": 3.12696703292044e-05,
      "loss": 41.3505,
      "step": 33
    },
    {
      "epoch": 0.009381898454746136,
      "grad_norm": 1.6467429399490356,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 41.3469,
      "step": 34
    },
    {
      "epoch": 0.009657836644591612,
      "grad_norm": 1.7981724739074707,
      "learning_rate": 2.500000000000001e-05,
      "loss": 41.3437,
      "step": 35
    },
    {
      "epoch": 0.009933774834437087,
      "grad_norm": 1.6016830205917358,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 41.3345,
      "step": 36
    },
    {
      "epoch": 0.01020971302428256,
      "grad_norm": 1.5844223499298096,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 41.3542,
      "step": 37
    },
    {
      "epoch": 0.010485651214128035,
      "grad_norm": 1.611533761024475,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 41.3537,
      "step": 38
    },
    {
      "epoch": 0.01076158940397351,
      "grad_norm": 1.47672438621521,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 41.3644,
      "step": 39
    },
    {
      "epoch": 0.011037527593818985,
      "grad_norm": 1.5298023223876953,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 41.3503,
      "step": 40
    },
    {
      "epoch": 0.01131346578366446,
      "grad_norm": 1.5764249563217163,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.3264,
      "step": 41
    },
    {
      "epoch": 0.011589403973509934,
      "grad_norm": 1.6167798042297363,
      "learning_rate": 7.597595192178702e-06,
      "loss": 41.3208,
      "step": 42
    },
    {
      "epoch": 0.011865342163355408,
      "grad_norm": 1.622572898864746,
      "learning_rate": 5.852620357053651e-06,
      "loss": 41.3475,
      "step": 43
    },
    {
      "epoch": 0.012141280353200883,
      "grad_norm": 1.5153831243515015,
      "learning_rate": 4.322727117869951e-06,
      "loss": 41.3442,
      "step": 44
    },
    {
      "epoch": 0.012417218543046357,
      "grad_norm": 1.5510733127593994,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 41.346,
      "step": 45
    },
    {
      "epoch": 0.012693156732891833,
      "grad_norm": 1.6752930879592896,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 41.3647,
      "step": 46
    },
    {
      "epoch": 0.012969094922737307,
      "grad_norm": 1.623339295387268,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 41.3218,
      "step": 47
    },
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 2.007035732269287,
      "learning_rate": 4.865965629214819e-07,
      "loss": 41.3647,
      "step": 48
    },
    {
      "epoch": 0.013520971302428256,
      "grad_norm": 1.9220043420791626,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 41.3541,
      "step": 49
    },
    {
      "epoch": 0.01379690949227373,
      "grad_norm": 2.5197606086730957,
      "learning_rate": 0.0,
      "loss": 41.3483,
      "step": 50
    },
    {
      "epoch": 0.01379690949227373,
      "eval_loss": 10.33413314819336,
      "eval_runtime": 9.9898,
      "eval_samples_per_second": 611.024,
      "eval_steps_per_second": 76.378,
      "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": 8726623027200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}