{
  "best_metric": 10.361746788024902,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2796225096120238,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005592450192240475,
      "grad_norm": 0.14615148305892944,
      "learning_rate": 5e-05,
      "loss": 10.383,
      "step": 1
    },
    {
      "epoch": 0.005592450192240475,
      "eval_loss": 10.380449295043945,
      "eval_runtime": 0.1129,
      "eval_samples_per_second": 442.836,
      "eval_steps_per_second": 115.137,
      "step": 1
    },
    {
      "epoch": 0.01118490038448095,
      "grad_norm": 0.13564914464950562,
      "learning_rate": 0.0001,
      "loss": 10.3826,
      "step": 2
    },
    {
      "epoch": 0.016777350576721427,
      "grad_norm": 0.1270395666360855,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3829,
      "step": 3
    },
    {
      "epoch": 0.0223698007689619,
      "grad_norm": 0.1220603659749031,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3805,
      "step": 4
    },
    {
      "epoch": 0.027962250961202376,
      "grad_norm": 0.11310075968503952,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.38,
      "step": 5
    },
    {
      "epoch": 0.033554701153442855,
      "grad_norm": 0.10876661539077759,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3802,
      "step": 6
    },
    {
      "epoch": 0.03914715134568333,
      "grad_norm": 0.10691489279270172,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3797,
      "step": 7
    },
    {
      "epoch": 0.0447396015379238,
      "grad_norm": 0.10898499190807343,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3797,
      "step": 8
    },
    {
      "epoch": 0.05033205173016428,
      "grad_norm": 0.10882221907377243,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3793,
      "step": 9
    },
    {
      "epoch": 0.05592450192240475,
      "grad_norm": 0.10796788334846497,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3777,
      "step": 10
    },
    {
      "epoch": 0.06151695211464523,
      "grad_norm": 0.10834939777851105,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3736,
      "step": 11
    },
    {
      "epoch": 0.06710940230688571,
      "grad_norm": 0.11363967508077621,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3719,
      "step": 12
    },
    {
      "epoch": 0.07270185249912618,
      "grad_norm": 0.156457781791687,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3763,
      "step": 13
    },
    {
      "epoch": 0.07829430269136665,
      "grad_norm": 0.15085114538669586,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3761,
      "step": 14
    },
    {
      "epoch": 0.08388675288360713,
      "grad_norm": 0.1429266333580017,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3753,
      "step": 15
    },
    {
      "epoch": 0.0894792030758476,
      "grad_norm": 0.13529515266418457,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.375,
      "step": 16
    },
    {
      "epoch": 0.09507165326808809,
      "grad_norm": 0.13351839780807495,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3738,
      "step": 17
    },
    {
      "epoch": 0.10066410346032856,
      "grad_norm": 0.1335008144378662,
      "learning_rate": 7.75e-05,
      "loss": 10.3745,
      "step": 18
    },
    {
      "epoch": 0.10625655365256903,
      "grad_norm": 0.1339954137802124,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3735,
      "step": 19
    },
    {
      "epoch": 0.1118490038448095,
      "grad_norm": 0.1330738365650177,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3751,
      "step": 20
    },
    {
      "epoch": 0.11744145403704999,
      "grad_norm": 0.13523127138614655,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.374,
      "step": 21
    },
    {
      "epoch": 0.12303390422929046,
      "grad_norm": 0.13809822499752045,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.372,
      "step": 22
    },
    {
      "epoch": 0.12862635442153092,
      "grad_norm": 0.13312876224517822,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3706,
      "step": 23
    },
    {
      "epoch": 0.13421880461377142,
      "grad_norm": 0.1388683021068573,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3663,
      "step": 24
    },
    {
      "epoch": 0.1398112548060119,
      "grad_norm": 0.15188777446746826,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3646,
      "step": 25
    },
    {
      "epoch": 0.1398112548060119,
      "eval_loss": 10.368451118469238,
      "eval_runtime": 0.1119,
      "eval_samples_per_second": 447.013,
      "eval_steps_per_second": 116.223,
      "step": 25
    },
    {
      "epoch": 0.14540370499825236,
      "grad_norm": 0.19245736300945282,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3696,
      "step": 26
    },
    {
      "epoch": 0.15099615519049284,
      "grad_norm": 0.18666407465934753,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.3691,
      "step": 27
    },
    {
      "epoch": 0.1565886053827333,
      "grad_norm": 0.18163171410560608,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3689,
      "step": 28
    },
    {
      "epoch": 0.16218105557497378,
      "grad_norm": 0.17533497512340546,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3671,
      "step": 29
    },
    {
      "epoch": 0.16777350576721425,
      "grad_norm": 0.1728811413049698,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3676,
      "step": 30
    },
    {
      "epoch": 0.17336595595945473,
      "grad_norm": 0.16648425161838531,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3689,
      "step": 31
    },
    {
      "epoch": 0.1789584061516952,
      "grad_norm": 0.16129642724990845,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3691,
      "step": 32
    },
    {
      "epoch": 0.1845508563439357,
      "grad_norm": 0.16618475317955017,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.3692,
      "step": 33
    },
    {
      "epoch": 0.19014330653617617,
      "grad_norm": 0.1671101450920105,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3682,
      "step": 34
    },
    {
      "epoch": 0.19573575672841664,
      "grad_norm": 0.1676071584224701,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3671,
      "step": 35
    },
    {
      "epoch": 0.20132820692065712,
      "grad_norm": 0.16497556865215302,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3637,
      "step": 36
    },
    {
      "epoch": 0.2069206571128976,
      "grad_norm": 0.16900619864463806,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3615,
      "step": 37
    },
    {
      "epoch": 0.21251310730513806,
      "grad_norm": 0.22142191231250763,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3646,
      "step": 38
    },
    {
      "epoch": 0.21810555749737853,
      "grad_norm": 0.21971495449543,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3646,
      "step": 39
    },
    {
      "epoch": 0.223698007689619,
      "grad_norm": 0.21041202545166016,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3645,
      "step": 40
    },
    {
      "epoch": 0.22929045788185948,
      "grad_norm": 0.2077437788248062,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3635,
      "step": 41
    },
    {
      "epoch": 0.23488290807409998,
      "grad_norm": 0.19469435513019562,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3635,
      "step": 42
    },
    {
      "epoch": 0.24047535826634045,
      "grad_norm": 0.19135217368602753,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.3646,
      "step": 43
    },
    {
      "epoch": 0.24606780845858092,
      "grad_norm": 0.1929345279932022,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3648,
      "step": 44
    },
    {
      "epoch": 0.25166025865082137,
      "grad_norm": 0.18326839804649353,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.3651,
      "step": 45
    },
    {
      "epoch": 0.25725270884306184,
      "grad_norm": 0.18715374171733856,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3651,
      "step": 46
    },
    {
      "epoch": 0.26284515903530237,
      "grad_norm": 0.1834271103143692,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.3643,
      "step": 47
    },
    {
      "epoch": 0.26843760922754284,
      "grad_norm": 0.17882713675498962,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3625,
      "step": 48
    },
    {
      "epoch": 0.2740300594197833,
      "grad_norm": 0.1836736798286438,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3601,
      "step": 49
    },
    {
      "epoch": 0.2796225096120238,
      "grad_norm": 0.19659334421157837,
      "learning_rate": 1e-05,
      "loss": 10.3583,
      "step": 50
    },
    {
      "epoch": 0.2796225096120238,
      "eval_loss": 10.361746788024902,
      "eval_runtime": 0.1143,
      "eval_samples_per_second": 437.425,
      "eval_steps_per_second": 113.731,
      "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": 43075455025152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}