{
  "best_metric": 11.909934043884277,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.4916512059369202,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029684601113172542,
      "grad_norm": 0.08440621197223663,
      "learning_rate": 5e-05,
      "loss": 11.9231,
      "step": 1
    },
    {
      "epoch": 0.029684601113172542,
      "eval_loss": 11.920661926269531,
      "eval_runtime": 0.1771,
      "eval_samples_per_second": 282.363,
      "eval_steps_per_second": 73.414,
      "step": 1
    },
    {
      "epoch": 0.059369202226345084,
      "grad_norm": 0.07143169641494751,
      "learning_rate": 0.0001,
      "loss": 11.9261,
      "step": 2
    },
    {
      "epoch": 0.08905380333951762,
      "grad_norm": 0.07815750688314438,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9269,
      "step": 3
    },
    {
      "epoch": 0.11873840445269017,
      "grad_norm": 0.09560947865247726,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9222,
      "step": 4
    },
    {
      "epoch": 0.14842300556586271,
      "grad_norm": 0.0957864299416542,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9285,
      "step": 5
    },
    {
      "epoch": 0.17810760667903525,
      "grad_norm": 0.09346175938844681,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.934,
      "step": 6
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.11279693245887756,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9301,
      "step": 7
    },
    {
      "epoch": 0.23747680890538034,
      "grad_norm": 0.11731767654418945,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9298,
      "step": 8
    },
    {
      "epoch": 0.26716141001855287,
      "grad_norm": 0.07877083867788315,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9248,
      "step": 9
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 0.045284539461135864,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9318,
      "step": 10
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.07036509364843369,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9297,
      "step": 11
    },
    {
      "epoch": 0.3562152133580705,
      "grad_norm": 0.07343818247318268,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9276,
      "step": 12
    },
    {
      "epoch": 0.38589981447124305,
      "grad_norm": 0.08361507207155228,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9237,
      "step": 13
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.10278163850307465,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9262,
      "step": 14
    },
    {
      "epoch": 0.4452690166975881,
      "grad_norm": 0.10730006545782089,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9315,
      "step": 15
    },
    {
      "epoch": 0.4749536178107607,
      "grad_norm": 0.11636124551296234,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9271,
      "step": 16
    },
    {
      "epoch": 0.5046382189239332,
      "grad_norm": 0.0831388458609581,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9265,
      "step": 17
    },
    {
      "epoch": 0.5343228200371057,
      "grad_norm": 0.06362044811248779,
      "learning_rate": 7.75e-05,
      "loss": 11.9248,
      "step": 18
    },
    {
      "epoch": 0.5640074211502782,
      "grad_norm": 0.0942530408501625,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9219,
      "step": 19
    },
    {
      "epoch": 0.5936920222634509,
      "grad_norm": 0.0732453465461731,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9212,
      "step": 20
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.11220160126686096,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9295,
      "step": 21
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.10498771071434021,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9278,
      "step": 22
    },
    {
      "epoch": 0.6827458256029685,
      "grad_norm": 0.124515600502491,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9253,
      "step": 23
    },
    {
      "epoch": 0.712430426716141,
      "grad_norm": 0.1343991756439209,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9325,
      "step": 24
    },
    {
      "epoch": 0.7421150278293135,
      "grad_norm": 0.12157789617776871,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9332,
      "step": 25
    },
    {
      "epoch": 0.7421150278293135,
      "eval_loss": 11.913727760314941,
      "eval_runtime": 0.1789,
      "eval_samples_per_second": 279.536,
      "eval_steps_per_second": 72.679,
      "step": 25
    },
    {
      "epoch": 0.7717996289424861,
      "grad_norm": 0.0719190388917923,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.924,
      "step": 26
    },
    {
      "epoch": 0.8014842300556586,
      "grad_norm": 0.08129285275936127,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9228,
      "step": 27
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.09859055280685425,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9232,
      "step": 28
    },
    {
      "epoch": 0.8608534322820037,
      "grad_norm": 0.11506542563438416,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.926,
      "step": 29
    },
    {
      "epoch": 0.8905380333951762,
      "grad_norm": 0.15384303033351898,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9283,
      "step": 30
    },
    {
      "epoch": 0.9202226345083488,
      "grad_norm": 0.1378241777420044,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9293,
      "step": 31
    },
    {
      "epoch": 0.9499072356215214,
      "grad_norm": 0.16257359087467194,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9229,
      "step": 32
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.17936405539512634,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9234,
      "step": 33
    },
    {
      "epoch": 1.0166975881261595,
      "grad_norm": 0.15958204865455627,
      "learning_rate": 3.250000000000001e-05,
      "loss": 17.6078,
      "step": 34
    },
    {
      "epoch": 1.0463821892393321,
      "grad_norm": 0.09481591731309891,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 13.2428,
      "step": 35
    },
    {
      "epoch": 1.0760667903525047,
      "grad_norm": 0.10548726469278336,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.713,
      "step": 36
    },
    {
      "epoch": 1.1057513914656771,
      "grad_norm": 0.11312992870807648,
      "learning_rate": 2.53294383204969e-05,
      "loss": 12.1172,
      "step": 37
    },
    {
      "epoch": 1.1354359925788498,
      "grad_norm": 0.15006272494792938,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.5776,
      "step": 38
    },
    {
      "epoch": 1.1651205936920221,
      "grad_norm": 0.1586989313364029,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.8544,
      "step": 39
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 0.1619988977909088,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.812,
      "step": 40
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 0.1769491583108902,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9887,
      "step": 41
    },
    {
      "epoch": 1.25417439703154,
      "grad_norm": 0.13794884085655212,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.9086,
      "step": 42
    },
    {
      "epoch": 1.2838589981447124,
      "grad_norm": 0.10126476734876633,
      "learning_rate": 1.464072663102903e-05,
      "loss": 13.3781,
      "step": 43
    },
    {
      "epoch": 1.313543599257885,
      "grad_norm": 0.10457659512758255,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.5312,
      "step": 44
    },
    {
      "epoch": 1.3432282003710574,
      "grad_norm": 0.12314631044864655,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.4098,
      "step": 45
    },
    {
      "epoch": 1.37291280148423,
      "grad_norm": 0.12051708251237869,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 13.2575,
      "step": 46
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 0.15540221333503723,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.282,
      "step": 47
    },
    {
      "epoch": 1.4322820037105752,
      "grad_norm": 0.14833006262779236,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 12.1183,
      "step": 48
    },
    {
      "epoch": 1.4619666048237476,
      "grad_norm": 0.19068753719329834,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 12.0193,
      "step": 49
    },
    {
      "epoch": 1.4916512059369202,
      "grad_norm": 0.1597161591053009,
      "learning_rate": 1e-05,
      "loss": 10.5403,
      "step": 50
    },
    {
      "epoch": 1.4916512059369202,
      "eval_loss": 11.909934043884277,
      "eval_runtime": 0.1791,
      "eval_samples_per_second": 279.203,
      "eval_steps_per_second": 72.593,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}