{
  "best_metric": 0.6428024172782898,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.9002375296912115,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03800475059382423,
      "grad_norm": 0.2963005006313324,
      "learning_rate": 5e-05,
      "loss": 0.8144,
      "step": 1
    },
    {
      "epoch": 0.03800475059382423,
      "eval_loss": 1.0114444494247437,
      "eval_runtime": 3.596,
      "eval_samples_per_second": 13.904,
      "eval_steps_per_second": 3.615,
      "step": 1
    },
    {
      "epoch": 0.07600950118764846,
      "grad_norm": 0.44090691208839417,
      "learning_rate": 0.0001,
      "loss": 0.7299,
      "step": 2
    },
    {
      "epoch": 0.11401425178147269,
      "grad_norm": 0.532346248626709,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.7866,
      "step": 3
    },
    {
      "epoch": 0.15201900237529692,
      "grad_norm": 0.4509457051753998,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.6892,
      "step": 4
    },
    {
      "epoch": 0.19002375296912113,
      "grad_norm": 0.5534288287162781,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.8278,
      "step": 5
    },
    {
      "epoch": 0.22802850356294538,
      "grad_norm": 0.6633877754211426,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.8841,
      "step": 6
    },
    {
      "epoch": 0.2660332541567696,
      "grad_norm": 0.20802059769630432,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.6923,
      "step": 7
    },
    {
      "epoch": 0.30403800475059384,
      "grad_norm": 0.24803350865840912,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.4351,
      "step": 8
    },
    {
      "epoch": 0.342042755344418,
      "grad_norm": 0.31892770528793335,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.4281,
      "step": 9
    },
    {
      "epoch": 0.38004750593824227,
      "grad_norm": 0.35792720317840576,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.5003,
      "step": 10
    },
    {
      "epoch": 0.4180522565320665,
      "grad_norm": 0.2984336316585541,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.5092,
      "step": 11
    },
    {
      "epoch": 0.45605700712589076,
      "grad_norm": 0.3135700821876526,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.5726,
      "step": 12
    },
    {
      "epoch": 0.49406175771971494,
      "grad_norm": 0.47002974152565,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.7806,
      "step": 13
    },
    {
      "epoch": 0.5320665083135392,
      "grad_norm": 0.21935120224952698,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.5925,
      "step": 14
    },
    {
      "epoch": 0.5700712589073634,
      "grad_norm": 0.2080266773700714,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.5508,
      "step": 15
    },
    {
      "epoch": 0.6080760095011877,
      "grad_norm": 0.20049305260181427,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.4623,
      "step": 16
    },
    {
      "epoch": 0.6460807600950119,
      "grad_norm": 0.19378888607025146,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.4742,
      "step": 17
    },
    {
      "epoch": 0.684085510688836,
      "grad_norm": 0.22749175131320953,
      "learning_rate": 7.75e-05,
      "loss": 0.5927,
      "step": 18
    },
    {
      "epoch": 0.7220902612826603,
      "grad_norm": 0.27720770239830017,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.5858,
      "step": 19
    },
    {
      "epoch": 0.7600950118764845,
      "grad_norm": 0.19494353234767914,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.7252,
      "step": 20
    },
    {
      "epoch": 0.7980997624703088,
      "grad_norm": 0.14721950888633728,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.4843,
      "step": 21
    },
    {
      "epoch": 0.836104513064133,
      "grad_norm": 0.19257256388664246,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.6009,
      "step": 22
    },
    {
      "epoch": 0.8741092636579573,
      "grad_norm": 0.18636387586593628,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.477,
      "step": 23
    },
    {
      "epoch": 0.9121140142517815,
      "grad_norm": 0.1978946477174759,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.4872,
      "step": 24
    },
    {
      "epoch": 0.9501187648456056,
      "grad_norm": 0.24017634987831116,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.6923,
      "step": 25
    },
    {
      "epoch": 0.9501187648456056,
      "eval_loss": 0.6572102308273315,
      "eval_runtime": 3.2351,
      "eval_samples_per_second": 15.455,
      "eval_steps_per_second": 4.018,
      "step": 25
    },
    {
      "epoch": 0.9881235154394299,
      "grad_norm": 0.3923742473125458,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.7254,
      "step": 26
    },
    {
      "epoch": 1.0261282660332542,
      "grad_norm": 0.287060409784317,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.9874,
      "step": 27
    },
    {
      "epoch": 1.0641330166270784,
      "grad_norm": 0.12502576410770416,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.4236,
      "step": 28
    },
    {
      "epoch": 1.1021377672209025,
      "grad_norm": 0.1519356071949005,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.5404,
      "step": 29
    },
    {
      "epoch": 1.1401425178147269,
      "grad_norm": 0.1616930067539215,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.4119,
      "step": 30
    },
    {
      "epoch": 1.178147268408551,
      "grad_norm": 0.21593336760997772,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.4632,
      "step": 31
    },
    {
      "epoch": 1.2161520190023754,
      "grad_norm": 0.22321325540542603,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.5468,
      "step": 32
    },
    {
      "epoch": 1.2541567695961995,
      "grad_norm": 0.17082692682743073,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.5635,
      "step": 33
    },
    {
      "epoch": 1.2921615201900236,
      "grad_norm": 0.14728975296020508,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.5655,
      "step": 34
    },
    {
      "epoch": 1.330166270783848,
      "grad_norm": 0.13425937294960022,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.4028,
      "step": 35
    },
    {
      "epoch": 1.3681710213776723,
      "grad_norm": 0.15661655366420746,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.4111,
      "step": 36
    },
    {
      "epoch": 1.4061757719714965,
      "grad_norm": 0.17608828842639923,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.3637,
      "step": 37
    },
    {
      "epoch": 1.4441805225653206,
      "grad_norm": 0.24201960861682892,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.6137,
      "step": 38
    },
    {
      "epoch": 1.482185273159145,
      "grad_norm": 0.2761252224445343,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.6965,
      "step": 39
    },
    {
      "epoch": 1.520190023752969,
      "grad_norm": 0.18873077630996704,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.4831,
      "step": 40
    },
    {
      "epoch": 1.5581947743467932,
      "grad_norm": 0.13722312450408936,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.3967,
      "step": 41
    },
    {
      "epoch": 1.5961995249406176,
      "grad_norm": 0.15244022011756897,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.4337,
      "step": 42
    },
    {
      "epoch": 1.634204275534442,
      "grad_norm": 0.16839975118637085,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.4065,
      "step": 43
    },
    {
      "epoch": 1.672209026128266,
      "grad_norm": 0.22024290263652802,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.5043,
      "step": 44
    },
    {
      "epoch": 1.7102137767220902,
      "grad_norm": 0.25446122884750366,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.5892,
      "step": 45
    },
    {
      "epoch": 1.7482185273159145,
      "grad_norm": 0.1789197474718094,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.4094,
      "step": 46
    },
    {
      "epoch": 1.7862232779097387,
      "grad_norm": 0.1745312511920929,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.6796,
      "step": 47
    },
    {
      "epoch": 1.8242280285035628,
      "grad_norm": 0.14252056181430817,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.4309,
      "step": 48
    },
    {
      "epoch": 1.8622327790973872,
      "grad_norm": 0.15681980550289154,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.4304,
      "step": 49
    },
    {
      "epoch": 1.9002375296912115,
      "grad_norm": 0.16831724345684052,
      "learning_rate": 1e-05,
      "loss": 0.3753,
      "step": 50
    },
    {
      "epoch": 1.9002375296912115,
      "eval_loss": 0.6428024172782898,
      "eval_runtime": 3.2585,
      "eval_samples_per_second": 15.344,
      "eval_steps_per_second": 3.99,
      "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": 5.624057810649088e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}