{
  "best_metric": 0.24638938903808594,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.27155465037338766,
  "eval_steps": 50,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036207286716451684,
      "grad_norm": 0.4402937889099121,
      "learning_rate": 5e-06,
      "loss": 0.4127,
      "step": 1
    },
    {
      "epoch": 0.0036207286716451684,
      "eval_loss": 0.39411357045173645,
      "eval_runtime": 233.1042,
      "eval_samples_per_second": 3.994,
      "eval_steps_per_second": 1.0,
      "step": 1
    },
    {
      "epoch": 0.007241457343290337,
      "grad_norm": 0.43906018137931824,
      "learning_rate": 1e-05,
      "loss": 0.3877,
      "step": 2
    },
    {
      "epoch": 0.010862186014935505,
      "grad_norm": 0.43620216846466064,
      "learning_rate": 1.5e-05,
      "loss": 0.3505,
      "step": 3
    },
    {
      "epoch": 0.014482914686580674,
      "grad_norm": 0.4520662724971771,
      "learning_rate": 2e-05,
      "loss": 0.4246,
      "step": 4
    },
    {
      "epoch": 0.018103643358225844,
      "grad_norm": 0.3887633979320526,
      "learning_rate": 2.5e-05,
      "loss": 0.3654,
      "step": 5
    },
    {
      "epoch": 0.02172437202987101,
      "grad_norm": 0.32681211829185486,
      "learning_rate": 3e-05,
      "loss": 0.3817,
      "step": 6
    },
    {
      "epoch": 0.02534510070151618,
      "grad_norm": 0.30532073974609375,
      "learning_rate": 3.5e-05,
      "loss": 0.3417,
      "step": 7
    },
    {
      "epoch": 0.028965829373161348,
      "grad_norm": 0.2958042621612549,
      "learning_rate": 4e-05,
      "loss": 0.3413,
      "step": 8
    },
    {
      "epoch": 0.032586558044806514,
      "grad_norm": 0.25813692808151245,
      "learning_rate": 4.5e-05,
      "loss": 0.3232,
      "step": 9
    },
    {
      "epoch": 0.03620728671645169,
      "grad_norm": 0.27644163370132446,
      "learning_rate": 5e-05,
      "loss": 0.3526,
      "step": 10
    },
    {
      "epoch": 0.039828015388096855,
      "grad_norm": 0.25497642159461975,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.2976,
      "step": 11
    },
    {
      "epoch": 0.04344874405974202,
      "grad_norm": 0.26926350593566895,
      "learning_rate": 6e-05,
      "loss": 0.2951,
      "step": 12
    },
    {
      "epoch": 0.047069472731387195,
      "grad_norm": 0.2823635935783386,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.3029,
      "step": 13
    },
    {
      "epoch": 0.05069020140303236,
      "grad_norm": 0.19785167276859283,
      "learning_rate": 7e-05,
      "loss": 0.2589,
      "step": 14
    },
    {
      "epoch": 0.05431093007467753,
      "grad_norm": 0.19602355360984802,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2614,
      "step": 15
    },
    {
      "epoch": 0.057931658746322695,
      "grad_norm": 0.18251068890094757,
      "learning_rate": 8e-05,
      "loss": 0.275,
      "step": 16
    },
    {
      "epoch": 0.06155238741796787,
      "grad_norm": 0.21483223140239716,
      "learning_rate": 8.5e-05,
      "loss": 0.3278,
      "step": 17
    },
    {
      "epoch": 0.06517311608961303,
      "grad_norm": 0.19363826513290405,
      "learning_rate": 9e-05,
      "loss": 0.2633,
      "step": 18
    },
    {
      "epoch": 0.0687938447612582,
      "grad_norm": 0.17659173905849457,
      "learning_rate": 9.5e-05,
      "loss": 0.2504,
      "step": 19
    },
    {
      "epoch": 0.07241457343290338,
      "grad_norm": 0.20334695279598236,
      "learning_rate": 0.0001,
      "loss": 0.3023,
      "step": 20
    },
    {
      "epoch": 0.07603530210454854,
      "grad_norm": 0.18668325245380402,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.2935,
      "step": 21
    },
    {
      "epoch": 0.07965603077619371,
      "grad_norm": 0.1616354137659073,
      "learning_rate": 9.967408676742751e-05,
      "loss": 0.256,
      "step": 22
    },
    {
      "epoch": 0.08327675944783888,
      "grad_norm": 0.16258352994918823,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.2442,
      "step": 23
    },
    {
      "epoch": 0.08689748811948404,
      "grad_norm": 0.17701072990894318,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.2841,
      "step": 24
    },
    {
      "epoch": 0.09051821679112922,
      "grad_norm": 0.16547025740146637,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.2709,
      "step": 25
    },
    {
      "epoch": 0.09413894546277439,
      "grad_norm": 0.17125892639160156,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.2884,
      "step": 26
    },
    {
      "epoch": 0.09775967413441955,
      "grad_norm": 0.16323907673358917,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.2505,
      "step": 27
    },
    {
      "epoch": 0.10138040280606472,
      "grad_norm": 0.16210584342479706,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.2708,
      "step": 28
    },
    {
      "epoch": 0.10500113147770988,
      "grad_norm": 0.1565285623073578,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.2688,
      "step": 29
    },
    {
      "epoch": 0.10862186014935506,
      "grad_norm": 0.16366994380950928,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.2684,
      "step": 30
    },
    {
      "epoch": 0.11224258882100023,
      "grad_norm": 0.16400501132011414,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2653,
      "step": 31
    },
    {
      "epoch": 0.11586331749264539,
      "grad_norm": 0.1745917946100235,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.292,
      "step": 32
    },
    {
      "epoch": 0.11948404616429056,
      "grad_norm": 0.16044358909130096,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.244,
      "step": 33
    },
    {
      "epoch": 0.12310477483593574,
      "grad_norm": 0.14699938893318176,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.2351,
      "step": 34
    },
    {
      "epoch": 0.1267255035075809,
      "grad_norm": 0.16715097427368164,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.2797,
      "step": 35
    },
    {
      "epoch": 0.13034623217922606,
      "grad_norm": 0.16253520548343658,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.2663,
      "step": 36
    },
    {
      "epoch": 0.13396696085087123,
      "grad_norm": 0.15796582400798798,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.2547,
      "step": 37
    },
    {
      "epoch": 0.1375876895225164,
      "grad_norm": 0.1650385856628418,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.2821,
      "step": 38
    },
    {
      "epoch": 0.14120841819416158,
      "grad_norm": 0.14839529991149902,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.2406,
      "step": 39
    },
    {
      "epoch": 0.14482914686580675,
      "grad_norm": 0.14774177968502045,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.2531,
      "step": 40
    },
    {
      "epoch": 0.14844987553745193,
      "grad_norm": 0.16159765422344208,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.2816,
      "step": 41
    },
    {
      "epoch": 0.15207060420909707,
      "grad_norm": 0.15454764664173126,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2643,
      "step": 42
    },
    {
      "epoch": 0.15569133288074224,
      "grad_norm": 0.15375515818595886,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.2524,
      "step": 43
    },
    {
      "epoch": 0.15931206155238742,
      "grad_norm": 0.15904226899147034,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.2604,
      "step": 44
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.14393344521522522,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.243,
      "step": 45
    },
    {
      "epoch": 0.16655351889567777,
      "grad_norm": 0.14154766499996185,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.2498,
      "step": 46
    },
    {
      "epoch": 0.1701742475673229,
      "grad_norm": 0.15560780465602875,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.2599,
      "step": 47
    },
    {
      "epoch": 0.17379497623896809,
      "grad_norm": 0.16247297823429108,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.2789,
      "step": 48
    },
    {
      "epoch": 0.17741570491061326,
      "grad_norm": 0.15790365636348724,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.2529,
      "step": 49
    },
    {
      "epoch": 0.18103643358225843,
      "grad_norm": 0.1570451706647873,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.2401,
      "step": 50
    },
    {
      "epoch": 0.18103643358225843,
      "eval_loss": 0.24638938903808594,
      "eval_runtime": 233.4655,
      "eval_samples_per_second": 3.988,
      "eval_steps_per_second": 0.998,
      "step": 50
    },
    {
      "epoch": 0.1846571622539036,
      "grad_norm": 0.1534356325864792,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.2336,
      "step": 51
    },
    {
      "epoch": 0.18827789092554878,
      "grad_norm": 0.1455630511045456,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.2266,
      "step": 52
    },
    {
      "epoch": 0.19189861959719393,
      "grad_norm": 0.15997833013534546,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2716,
      "step": 53
    },
    {
      "epoch": 0.1955193482688391,
      "grad_norm": 0.16611649096012115,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.2594,
      "step": 54
    },
    {
      "epoch": 0.19914007694048427,
      "grad_norm": 0.14760734140872955,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.2265,
      "step": 55
    },
    {
      "epoch": 0.20276080561212945,
      "grad_norm": 0.14981094002723694,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.2602,
      "step": 56
    },
    {
      "epoch": 0.20638153428377462,
      "grad_norm": 0.15253275632858276,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.2395,
      "step": 57
    },
    {
      "epoch": 0.21000226295541977,
      "grad_norm": 0.14788293838500977,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.2445,
      "step": 58
    },
    {
      "epoch": 0.21362299162706494,
      "grad_norm": 0.14573223888874054,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.2352,
      "step": 59
    },
    {
      "epoch": 0.2172437202987101,
      "grad_norm": 0.1522066593170166,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.2466,
      "step": 60
    },
    {
      "epoch": 0.2208644489703553,
      "grad_norm": 0.15221665799617767,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.2667,
      "step": 61
    },
    {
      "epoch": 0.22448517764200046,
      "grad_norm": 0.15091469883918762,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.2431,
      "step": 62
    },
    {
      "epoch": 0.22810590631364563,
      "grad_norm": 0.14665627479553223,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.2503,
      "step": 63
    },
    {
      "epoch": 0.23172663498529078,
      "grad_norm": 0.1365693211555481,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.243,
      "step": 64
    },
    {
      "epoch": 0.23534736365693595,
      "grad_norm": 0.14656876027584076,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.2269,
      "step": 65
    },
    {
      "epoch": 0.23896809232858113,
      "grad_norm": 0.150408074259758,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.2334,
      "step": 66
    },
    {
      "epoch": 0.2425888210002263,
      "grad_norm": 0.1671358346939087,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.2789,
      "step": 67
    },
    {
      "epoch": 0.24620954967187147,
      "grad_norm": 0.15173529088497162,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.2539,
      "step": 68
    },
    {
      "epoch": 0.24983027834351662,
      "grad_norm": 0.13886642456054688,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.2293,
      "step": 69
    },
    {
      "epoch": 0.2534510070151618,
      "grad_norm": 0.14482015371322632,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.2467,
      "step": 70
    },
    {
      "epoch": 0.25707173568680697,
      "grad_norm": 0.14723734557628632,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.2377,
      "step": 71
    },
    {
      "epoch": 0.2606924643584521,
      "grad_norm": 0.16239996254444122,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.2581,
      "step": 72
    },
    {
      "epoch": 0.2643131930300973,
      "grad_norm": 0.14651106297969818,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.2307,
      "step": 73
    },
    {
      "epoch": 0.26793392170174246,
      "grad_norm": 0.15978926420211792,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.2613,
      "step": 74
    },
    {
      "epoch": 0.27155465037338766,
      "grad_norm": 0.1479509025812149,
      "learning_rate": 0.0,
      "loss": 0.2537,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.815322950521324e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}