{
  "best_metric": 1.1095232963562012,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03984162952264748,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007968325904529495,
      "grad_norm": 0.1616974025964737,
      "learning_rate": 5e-05,
      "loss": 0.8073,
      "step": 1
    },
    {
      "epoch": 0.0007968325904529495,
      "eval_loss": 1.8205456733703613,
      "eval_runtime": 5.2773,
      "eval_samples_per_second": 9.475,
      "eval_steps_per_second": 2.463,
      "step": 1
    },
    {
      "epoch": 0.001593665180905899,
      "grad_norm": 0.18667301535606384,
      "learning_rate": 0.0001,
      "loss": 0.849,
      "step": 2
    },
    {
      "epoch": 0.0023904977713588484,
      "grad_norm": 0.2040894478559494,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.8641,
      "step": 3
    },
    {
      "epoch": 0.003187330361811798,
      "grad_norm": 0.21868745982646942,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.9632,
      "step": 4
    },
    {
      "epoch": 0.003984162952264747,
      "grad_norm": 0.38121870160102844,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.3934,
      "step": 5
    },
    {
      "epoch": 0.004780995542717697,
      "grad_norm": 0.5214269757270813,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.4583,
      "step": 6
    },
    {
      "epoch": 0.005577828133170646,
      "grad_norm": 0.5762293934822083,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.5444,
      "step": 7
    },
    {
      "epoch": 0.006374660723623596,
      "grad_norm": 0.44824668765068054,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.4733,
      "step": 8
    },
    {
      "epoch": 0.007171493314076546,
      "grad_norm": 0.45602330565452576,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.5021,
      "step": 9
    },
    {
      "epoch": 0.007968325904529495,
      "grad_norm": 0.4500844180583954,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.4386,
      "step": 10
    },
    {
      "epoch": 0.008765158494982444,
      "grad_norm": 0.5259007215499878,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.4516,
      "step": 11
    },
    {
      "epoch": 0.009561991085435394,
      "grad_norm": 1.0761322975158691,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.6081,
      "step": 12
    },
    {
      "epoch": 0.010358823675888343,
      "grad_norm": 0.6197909712791443,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.8338,
      "step": 13
    },
    {
      "epoch": 0.011155656266341293,
      "grad_norm": 0.5446053743362427,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.7945,
      "step": 14
    },
    {
      "epoch": 0.011952488856794242,
      "grad_norm": 0.44415393471717834,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.7959,
      "step": 15
    },
    {
      "epoch": 0.012749321447247192,
      "grad_norm": 0.31911835074424744,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.7742,
      "step": 16
    },
    {
      "epoch": 0.013546154037700141,
      "grad_norm": 0.3819568455219269,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.9244,
      "step": 17
    },
    {
      "epoch": 0.014342986628153092,
      "grad_norm": 0.6737424731254578,
      "learning_rate": 7.75e-05,
      "loss": 1.2598,
      "step": 18
    },
    {
      "epoch": 0.015139819218606042,
      "grad_norm": 0.4782792627811432,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.2633,
      "step": 19
    },
    {
      "epoch": 0.01593665180905899,
      "grad_norm": 0.3833808898925781,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.2904,
      "step": 20
    },
    {
      "epoch": 0.01673348439951194,
      "grad_norm": 0.36358052492141724,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.3096,
      "step": 21
    },
    {
      "epoch": 0.01753031698996489,
      "grad_norm": 0.3689650297164917,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.3243,
      "step": 22
    },
    {
      "epoch": 0.01832714958041784,
      "grad_norm": 0.3343556523323059,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.3089,
      "step": 23
    },
    {
      "epoch": 0.019123982170870787,
      "grad_norm": 0.5067732334136963,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.351,
      "step": 24
    },
    {
      "epoch": 0.01992081476132374,
      "grad_norm": 1.9559608697891235,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.5621,
      "step": 25
    },
    {
      "epoch": 0.01992081476132374,
      "eval_loss": 1.1515358686447144,
      "eval_runtime": 5.3168,
      "eval_samples_per_second": 9.404,
      "eval_steps_per_second": 2.445,
      "step": 25
    },
    {
      "epoch": 0.020717647351776686,
      "grad_norm": 0.1238275095820427,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.7318,
      "step": 26
    },
    {
      "epoch": 0.021514479942229638,
      "grad_norm": 0.12721899151802063,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.7337,
      "step": 27
    },
    {
      "epoch": 0.022311312532682585,
      "grad_norm": 0.12318814545869827,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.7866,
      "step": 28
    },
    {
      "epoch": 0.023108145123135537,
      "grad_norm": 0.14742588996887207,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.7804,
      "step": 29
    },
    {
      "epoch": 0.023904977713588484,
      "grad_norm": 0.23791754245758057,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.0907,
      "step": 30
    },
    {
      "epoch": 0.024701810304041436,
      "grad_norm": 0.29251614212989807,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.1775,
      "step": 31
    },
    {
      "epoch": 0.025498642894494383,
      "grad_norm": 0.29965853691101074,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.2387,
      "step": 32
    },
    {
      "epoch": 0.026295475484947334,
      "grad_norm": 0.3010103404521942,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.2586,
      "step": 33
    },
    {
      "epoch": 0.027092308075400282,
      "grad_norm": 0.2877664268016815,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.2567,
      "step": 34
    },
    {
      "epoch": 0.027889140665853233,
      "grad_norm": 0.2702466547489166,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.2134,
      "step": 35
    },
    {
      "epoch": 0.028685973256306185,
      "grad_norm": 0.3501109778881073,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.2461,
      "step": 36
    },
    {
      "epoch": 0.029482805846759132,
      "grad_norm": 0.8502271175384521,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.38,
      "step": 37
    },
    {
      "epoch": 0.030279638437212084,
      "grad_norm": 0.10287067294120789,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.7774,
      "step": 38
    },
    {
      "epoch": 0.03107647102766503,
      "grad_norm": 0.09060327708721161,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.7215,
      "step": 39
    },
    {
      "epoch": 0.03187330361811798,
      "grad_norm": 0.09810002893209457,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.7485,
      "step": 40
    },
    {
      "epoch": 0.032670136208570934,
      "grad_norm": 0.11357197165489197,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.7505,
      "step": 41
    },
    {
      "epoch": 0.03346696879902388,
      "grad_norm": 0.12801313400268555,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.8528,
      "step": 42
    },
    {
      "epoch": 0.03426380138947683,
      "grad_norm": 0.17026148736476898,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.1343,
      "step": 43
    },
    {
      "epoch": 0.03506063397992978,
      "grad_norm": 0.2460681051015854,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.2216,
      "step": 44
    },
    {
      "epoch": 0.03585746657038273,
      "grad_norm": 0.19261527061462402,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.1919,
      "step": 45
    },
    {
      "epoch": 0.03665429916083568,
      "grad_norm": 0.213339164853096,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.2428,
      "step": 46
    },
    {
      "epoch": 0.03745113175128863,
      "grad_norm": 0.23940491676330566,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.1661,
      "step": 47
    },
    {
      "epoch": 0.038247964341741575,
      "grad_norm": 0.31757083535194397,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.2426,
      "step": 48
    },
    {
      "epoch": 0.03904479693219453,
      "grad_norm": 0.6811033487319946,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.3631,
      "step": 49
    },
    {
      "epoch": 0.03984162952264748,
      "grad_norm": 2.329777956008911,
      "learning_rate": 1e-05,
      "loss": 1.6394,
      "step": 50
    },
    {
      "epoch": 0.03984162952264748,
      "eval_loss": 1.1095232963562012,
      "eval_runtime": 5.3407,
      "eval_samples_per_second": 9.362,
      "eval_steps_per_second": 2.434,
      "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": 1,
        "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": 2.654149397184512e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}