{
  "best_metric": 0.04146807640790939,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6420545746388443,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012841091492776886,
      "grad_norm": 2.98820424079895,
      "learning_rate": 5e-05,
      "loss": 1.7501,
      "step": 1
    },
    {
      "epoch": 0.012841091492776886,
      "eval_loss": 4.6158623695373535,
      "eval_runtime": 2.1584,
      "eval_samples_per_second": 23.165,
      "eval_steps_per_second": 6.023,
      "step": 1
    },
    {
      "epoch": 0.025682182985553772,
      "grad_norm": 3.726931095123291,
      "learning_rate": 0.0001,
      "loss": 2.2293,
      "step": 2
    },
    {
      "epoch": 0.038523274478330656,
      "grad_norm": 3.8018789291381836,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.317,
      "step": 3
    },
    {
      "epoch": 0.051364365971107544,
      "grad_norm": 4.310789585113525,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.9756,
      "step": 4
    },
    {
      "epoch": 0.06420545746388442,
      "grad_norm": 5.516280174255371,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.5689,
      "step": 5
    },
    {
      "epoch": 0.07704654895666131,
      "grad_norm": 4.980829238891602,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.0627,
      "step": 6
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 5.193998336791992,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.7698,
      "step": 7
    },
    {
      "epoch": 0.10272873194221509,
      "grad_norm": 3.3907129764556885,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.4906,
      "step": 8
    },
    {
      "epoch": 0.11556982343499198,
      "grad_norm": 2.7564470767974854,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.1924,
      "step": 9
    },
    {
      "epoch": 0.12841091492776885,
      "grad_norm": 1.1876503229141235,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.1494,
      "step": 10
    },
    {
      "epoch": 0.14125200642054575,
      "grad_norm": 2.6727466583251953,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.2081,
      "step": 11
    },
    {
      "epoch": 0.15409309791332262,
      "grad_norm": 0.9418500065803528,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.117,
      "step": 12
    },
    {
      "epoch": 0.16693418940609953,
      "grad_norm": 0.27055737376213074,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0342,
      "step": 13
    },
    {
      "epoch": 0.1797752808988764,
      "grad_norm": 0.29577669501304626,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0389,
      "step": 14
    },
    {
      "epoch": 0.1926163723916533,
      "grad_norm": 0.1944814771413803,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0505,
      "step": 15
    },
    {
      "epoch": 0.20545746388443017,
      "grad_norm": 0.30078575015068054,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.043,
      "step": 16
    },
    {
      "epoch": 0.21829855537720708,
      "grad_norm": 0.28765007853507996,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0478,
      "step": 17
    },
    {
      "epoch": 0.23113964686998395,
      "grad_norm": 0.4925723671913147,
      "learning_rate": 7.75e-05,
      "loss": 0.0432,
      "step": 18
    },
    {
      "epoch": 0.24398073836276082,
      "grad_norm": 0.3609505593776703,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0644,
      "step": 19
    },
    {
      "epoch": 0.2568218298555377,
      "grad_norm": 0.45685964822769165,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.056,
      "step": 20
    },
    {
      "epoch": 0.2696629213483146,
      "grad_norm": 0.4444729685783386,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0824,
      "step": 21
    },
    {
      "epoch": 0.2825040128410915,
      "grad_norm": 0.47437188029289246,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0743,
      "step": 22
    },
    {
      "epoch": 0.2953451043338684,
      "grad_norm": 0.44289061427116394,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0703,
      "step": 23
    },
    {
      "epoch": 0.30818619582664525,
      "grad_norm": 0.7908194065093994,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0685,
      "step": 24
    },
    {
      "epoch": 0.32102728731942215,
      "grad_norm": 0.45595434308052063,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0865,
      "step": 25
    },
    {
      "epoch": 0.32102728731942215,
      "eval_loss": 0.0494825541973114,
      "eval_runtime": 1.423,
      "eval_samples_per_second": 35.138,
      "eval_steps_per_second": 9.136,
      "step": 25
    },
    {
      "epoch": 0.33386837881219905,
      "grad_norm": 0.20905837416648865,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0245,
      "step": 26
    },
    {
      "epoch": 0.3467094703049759,
      "grad_norm": 0.30377206206321716,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0387,
      "step": 27
    },
    {
      "epoch": 0.3595505617977528,
      "grad_norm": 0.27176252007484436,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0467,
      "step": 28
    },
    {
      "epoch": 0.3723916532905297,
      "grad_norm": 0.2371463179588318,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0226,
      "step": 29
    },
    {
      "epoch": 0.3852327447833066,
      "grad_norm": 0.31079021096229553,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0387,
      "step": 30
    },
    {
      "epoch": 0.39807383627608345,
      "grad_norm": 0.3452705442905426,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0517,
      "step": 31
    },
    {
      "epoch": 0.41091492776886035,
      "grad_norm": 0.3658089339733124,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0658,
      "step": 32
    },
    {
      "epoch": 0.42375601926163725,
      "grad_norm": 0.4322083294391632,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0681,
      "step": 33
    },
    {
      "epoch": 0.43659711075441415,
      "grad_norm": 0.4732019305229187,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0646,
      "step": 34
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.4330652058124542,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0844,
      "step": 35
    },
    {
      "epoch": 0.4622792937399679,
      "grad_norm": 0.7389253377914429,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0973,
      "step": 36
    },
    {
      "epoch": 0.4751203852327448,
      "grad_norm": 0.49224039912223816,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.096,
      "step": 37
    },
    {
      "epoch": 0.48796147672552165,
      "grad_norm": 0.13378825783729553,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0347,
      "step": 38
    },
    {
      "epoch": 0.5008025682182986,
      "grad_norm": 0.2096407264471054,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0399,
      "step": 39
    },
    {
      "epoch": 0.5136436597110754,
      "grad_norm": 0.16437120735645294,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0273,
      "step": 40
    },
    {
      "epoch": 0.5264847512038523,
      "grad_norm": 0.18588468432426453,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0318,
      "step": 41
    },
    {
      "epoch": 0.5393258426966292,
      "grad_norm": 0.27155569195747375,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0459,
      "step": 42
    },
    {
      "epoch": 0.5521669341894061,
      "grad_norm": 0.29355552792549133,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.049,
      "step": 43
    },
    {
      "epoch": 0.565008025682183,
      "grad_norm": 0.1788083165884018,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0402,
      "step": 44
    },
    {
      "epoch": 0.5778491171749599,
      "grad_norm": 0.4135901927947998,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0646,
      "step": 45
    },
    {
      "epoch": 0.5906902086677368,
      "grad_norm": 0.5709441900253296,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0726,
      "step": 46
    },
    {
      "epoch": 0.6035313001605136,
      "grad_norm": 0.5146852135658264,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0611,
      "step": 47
    },
    {
      "epoch": 0.6163723916532905,
      "grad_norm": 0.45884639024734497,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0695,
      "step": 48
    },
    {
      "epoch": 0.6292134831460674,
      "grad_norm": 0.3609980046749115,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0776,
      "step": 49
    },
    {
      "epoch": 0.6420545746388443,
      "grad_norm": 0.46642816066741943,
      "learning_rate": 1e-05,
      "loss": 0.079,
      "step": 50
    },
    {
      "epoch": 0.6420545746388443,
      "eval_loss": 0.04146807640790939,
      "eval_runtime": 1.4221,
      "eval_samples_per_second": 35.16,
      "eval_steps_per_second": 9.142,
      "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": 5.624057810649088e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}