{
  "best_metric": 1.3377610445022583,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.027018811847748996,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005403762369549799,
      "grad_norm": 0.7583011984825134,
      "learning_rate": 5e-05,
      "loss": 1.297,
      "step": 1
    },
    {
      "epoch": 0.0005403762369549799,
      "eval_loss": 2.174191474914551,
      "eval_runtime": 4.1899,
      "eval_samples_per_second": 11.933,
      "eval_steps_per_second": 3.103,
      "step": 1
    },
    {
      "epoch": 0.0010807524739099598,
      "grad_norm": 1.1101243495941162,
      "learning_rate": 0.0001,
      "loss": 1.583,
      "step": 2
    },
    {
      "epoch": 0.0016211287108649397,
      "grad_norm": 1.038528323173523,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.5361,
      "step": 3
    },
    {
      "epoch": 0.0021615049478199196,
      "grad_norm": 0.9262168407440186,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.5997,
      "step": 4
    },
    {
      "epoch": 0.0027018811847748995,
      "grad_norm": 0.7537561655044556,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.5466,
      "step": 5
    },
    {
      "epoch": 0.0032422574217298794,
      "grad_norm": 1.0774636268615723,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.4077,
      "step": 6
    },
    {
      "epoch": 0.0037826336586848593,
      "grad_norm": 0.8793153762817383,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.3987,
      "step": 7
    },
    {
      "epoch": 0.004323009895639839,
      "grad_norm": 0.5507789850234985,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.3115,
      "step": 8
    },
    {
      "epoch": 0.004863386132594819,
      "grad_norm": 0.3755969703197479,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.3452,
      "step": 9
    },
    {
      "epoch": 0.005403762369549799,
      "grad_norm": 0.43587180972099304,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.4233,
      "step": 10
    },
    {
      "epoch": 0.0059441386065047785,
      "grad_norm": 0.49514809250831604,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.3115,
      "step": 11
    },
    {
      "epoch": 0.006484514843459759,
      "grad_norm": 0.5087136626243591,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.3965,
      "step": 12
    },
    {
      "epoch": 0.007024891080414738,
      "grad_norm": 0.3325331509113312,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.1429,
      "step": 13
    },
    {
      "epoch": 0.007565267317369719,
      "grad_norm": 0.33711519837379456,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.2356,
      "step": 14
    },
    {
      "epoch": 0.008105643554324698,
      "grad_norm": 0.3120402991771698,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.2588,
      "step": 15
    },
    {
      "epoch": 0.008646019791279679,
      "grad_norm": 0.2945317327976227,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.206,
      "step": 16
    },
    {
      "epoch": 0.009186396028234659,
      "grad_norm": 0.3258124589920044,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.2862,
      "step": 17
    },
    {
      "epoch": 0.009726772265189637,
      "grad_norm": 0.35412508249282837,
      "learning_rate": 7.75e-05,
      "loss": 1.2796,
      "step": 18
    },
    {
      "epoch": 0.010267148502144618,
      "grad_norm": 0.3369511365890503,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.3092,
      "step": 19
    },
    {
      "epoch": 0.010807524739099598,
      "grad_norm": 0.35932448506355286,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.2865,
      "step": 20
    },
    {
      "epoch": 0.011347900976054578,
      "grad_norm": 0.3596166968345642,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.3316,
      "step": 21
    },
    {
      "epoch": 0.011888277213009557,
      "grad_norm": 0.360521525144577,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.332,
      "step": 22
    },
    {
      "epoch": 0.012428653449964537,
      "grad_norm": 0.3786364793777466,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.3656,
      "step": 23
    },
    {
      "epoch": 0.012969029686919518,
      "grad_norm": 0.37271133065223694,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.3373,
      "step": 24
    },
    {
      "epoch": 0.013509405923874498,
      "grad_norm": 0.3994540274143219,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.311,
      "step": 25
    },
    {
      "epoch": 0.013509405923874498,
      "eval_loss": 1.3446965217590332,
      "eval_runtime": 3.8313,
      "eval_samples_per_second": 13.05,
      "eval_steps_per_second": 3.393,
      "step": 25
    },
    {
      "epoch": 0.014049782160829477,
      "grad_norm": 0.21121986210346222,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.2169,
      "step": 26
    },
    {
      "epoch": 0.014590158397784457,
      "grad_norm": 0.2865726351737976,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.2484,
      "step": 27
    },
    {
      "epoch": 0.015130534634739437,
      "grad_norm": 0.28713157773017883,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.3285,
      "step": 28
    },
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 0.28808316588401794,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.2291,
      "step": 29
    },
    {
      "epoch": 0.016211287108649396,
      "grad_norm": 0.30568546056747437,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.2678,
      "step": 30
    },
    {
      "epoch": 0.01675166334560438,
      "grad_norm": 0.31598296761512756,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.3251,
      "step": 31
    },
    {
      "epoch": 0.017292039582559357,
      "grad_norm": 0.30213311314582825,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.2651,
      "step": 32
    },
    {
      "epoch": 0.017832415819514336,
      "grad_norm": 0.3201400339603424,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.3113,
      "step": 33
    },
    {
      "epoch": 0.018372792056469318,
      "grad_norm": 0.2984909415245056,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.2781,
      "step": 34
    },
    {
      "epoch": 0.018913168293424296,
      "grad_norm": 0.3035302758216858,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.3588,
      "step": 35
    },
    {
      "epoch": 0.019453544530379275,
      "grad_norm": 0.35229870676994324,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.2524,
      "step": 36
    },
    {
      "epoch": 0.019993920767334257,
      "grad_norm": 0.35506507754325867,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.2212,
      "step": 37
    },
    {
      "epoch": 0.020534297004289236,
      "grad_norm": 0.2368265688419342,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.2029,
      "step": 38
    },
    {
      "epoch": 0.021074673241244218,
      "grad_norm": 0.20984533429145813,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.1931,
      "step": 39
    },
    {
      "epoch": 0.021615049478199196,
      "grad_norm": 0.24961891770362854,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.2394,
      "step": 40
    },
    {
      "epoch": 0.022155425715154175,
      "grad_norm": 0.24971644580364227,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.2365,
      "step": 41
    },
    {
      "epoch": 0.022695801952109157,
      "grad_norm": 0.27246740460395813,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.315,
      "step": 42
    },
    {
      "epoch": 0.023236178189064136,
      "grad_norm": 0.27005693316459656,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.2841,
      "step": 43
    },
    {
      "epoch": 0.023776554426019114,
      "grad_norm": 0.3045419752597809,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.2755,
      "step": 44
    },
    {
      "epoch": 0.024316930662974096,
      "grad_norm": 0.28059327602386475,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.2918,
      "step": 45
    },
    {
      "epoch": 0.024857306899929075,
      "grad_norm": 0.2891661822795868,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.2547,
      "step": 46
    },
    {
      "epoch": 0.025397683136884057,
      "grad_norm": 0.30394497513771057,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.2912,
      "step": 47
    },
    {
      "epoch": 0.025938059373839036,
      "grad_norm": 0.3209138810634613,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.3645,
      "step": 48
    },
    {
      "epoch": 0.026478435610794014,
      "grad_norm": 0.33830150961875916,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.3915,
      "step": 49
    },
    {
      "epoch": 0.027018811847748996,
      "grad_norm": 0.3909822702407837,
      "learning_rate": 1e-05,
      "loss": 1.3414,
      "step": 50
    },
    {
      "epoch": 0.027018811847748996,
      "eval_loss": 1.3377610445022583,
      "eval_runtime": 3.8377,
      "eval_samples_per_second": 13.029,
      "eval_steps_per_second": 3.387,
      "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": 6.061338191368028e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}