{
  "best_metric": 1.372193455696106,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.9347826086956523,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03864734299516908,
      "grad_norm": 44.83037567138672,
      "learning_rate": 5e-05,
      "loss": 8.6573,
      "step": 1
    },
    {
      "epoch": 0.03864734299516908,
      "eval_loss": 9.180410385131836,
      "eval_runtime": 1.2448,
      "eval_samples_per_second": 40.166,
      "eval_steps_per_second": 10.443,
      "step": 1
    },
    {
      "epoch": 0.07729468599033816,
      "grad_norm": 45.76945495605469,
      "learning_rate": 0.0001,
      "loss": 8.7617,
      "step": 2
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 23.18575668334961,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.3742,
      "step": 3
    },
    {
      "epoch": 0.15458937198067632,
      "grad_norm": 13.35321044921875,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.4927,
      "step": 4
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 9.369305610656738,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.3661,
      "step": 5
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 6.873307228088379,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.9901,
      "step": 6
    },
    {
      "epoch": 0.27053140096618356,
      "grad_norm": 11.262555122375488,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.961,
      "step": 7
    },
    {
      "epoch": 0.30917874396135264,
      "grad_norm": 4.840822219848633,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.4759,
      "step": 8
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 3.267213821411133,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.4742,
      "step": 9
    },
    {
      "epoch": 0.3864734299516908,
      "grad_norm": 3.991497755050659,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0675,
      "step": 10
    },
    {
      "epoch": 0.4251207729468599,
      "grad_norm": 3.9884159564971924,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.8785,
      "step": 11
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 9.527798652648926,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.9114,
      "step": 12
    },
    {
      "epoch": 0.5024154589371981,
      "grad_norm": 6.80998420715332,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.4089,
      "step": 13
    },
    {
      "epoch": 0.5410628019323671,
      "grad_norm": 3.134706974029541,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.0732,
      "step": 14
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 2.9002878665924072,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.2018,
      "step": 15
    },
    {
      "epoch": 0.6183574879227053,
      "grad_norm": 3.49242901802063,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.915,
      "step": 16
    },
    {
      "epoch": 0.6570048309178744,
      "grad_norm": 2.8339154720306396,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.8098,
      "step": 17
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 2.4505181312561035,
      "learning_rate": 7.75e-05,
      "loss": 1.7044,
      "step": 18
    },
    {
      "epoch": 0.7342995169082126,
      "grad_norm": 3.9613678455352783,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.9439,
      "step": 19
    },
    {
      "epoch": 0.7729468599033816,
      "grad_norm": 4.712571620941162,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.1957,
      "step": 20
    },
    {
      "epoch": 0.8115942028985508,
      "grad_norm": 3.8725621700286865,
      "learning_rate": 6.946477593864228e-05,
      "loss": 2.1478,
      "step": 21
    },
    {
      "epoch": 0.8502415458937198,
      "grad_norm": 3.0220134258270264,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.8578,
      "step": 22
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.3540871143341064,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.5192,
      "step": 23
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 2.1330745220184326,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.484,
      "step": 24
    },
    {
      "epoch": 0.966183574879227,
      "grad_norm": 2.330143690109253,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.6236,
      "step": 25
    },
    {
      "epoch": 0.966183574879227,
      "eval_loss": 1.6289045810699463,
      "eval_runtime": 1.2687,
      "eval_samples_per_second": 39.41,
      "eval_steps_per_second": 10.247,
      "step": 25
    },
    {
      "epoch": 1.0072463768115942,
      "grad_norm": 2.7831952571868896,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.0748,
      "step": 26
    },
    {
      "epoch": 1.0458937198067633,
      "grad_norm": 2.014694929122925,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.9726,
      "step": 27
    },
    {
      "epoch": 1.0845410628019323,
      "grad_norm": 1.541536569595337,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.9017,
      "step": 28
    },
    {
      "epoch": 1.1231884057971016,
      "grad_norm": 3.653707504272461,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.7134,
      "step": 29
    },
    {
      "epoch": 1.1618357487922706,
      "grad_norm": 4.211123943328857,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.4641,
      "step": 30
    },
    {
      "epoch": 1.2004830917874396,
      "grad_norm": 3.187204360961914,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.4011,
      "step": 31
    },
    {
      "epoch": 1.2391304347826086,
      "grad_norm": 2.7480978965759277,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.4607,
      "step": 32
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 2.39614200592041,
      "learning_rate": 3.509700894014496e-05,
      "loss": 2.0324,
      "step": 33
    },
    {
      "epoch": 1.316425120772947,
      "grad_norm": 3.0056447982788086,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.8739,
      "step": 34
    },
    {
      "epoch": 1.355072463768116,
      "grad_norm": 3.2308599948883057,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.811,
      "step": 35
    },
    {
      "epoch": 1.393719806763285,
      "grad_norm": 2.4190244674682617,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.4012,
      "step": 36
    },
    {
      "epoch": 1.432367149758454,
      "grad_norm": 2.9130115509033203,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.3067,
      "step": 37
    },
    {
      "epoch": 1.471014492753623,
      "grad_norm": 2.56050443649292,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.4833,
      "step": 38
    },
    {
      "epoch": 1.5096618357487923,
      "grad_norm": 2.319148540496826,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.7662,
      "step": 39
    },
    {
      "epoch": 1.5483091787439613,
      "grad_norm": 2.010082721710205,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.786,
      "step": 40
    },
    {
      "epoch": 1.5869565217391304,
      "grad_norm": 2.326204299926758,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.7224,
      "step": 41
    },
    {
      "epoch": 1.6256038647342996,
      "grad_norm": 2.6092209815979004,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.4101,
      "step": 42
    },
    {
      "epoch": 1.6642512077294684,
      "grad_norm": 3.253211498260498,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.175,
      "step": 43
    },
    {
      "epoch": 1.7028985507246377,
      "grad_norm": 2.6981844902038574,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.1852,
      "step": 44
    },
    {
      "epoch": 1.7415458937198067,
      "grad_norm": 2.8664114475250244,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.5638,
      "step": 45
    },
    {
      "epoch": 1.7801932367149758,
      "grad_norm": 2.2756621837615967,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.8545,
      "step": 46
    },
    {
      "epoch": 1.818840579710145,
      "grad_norm": 2.5986602306365967,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.6885,
      "step": 47
    },
    {
      "epoch": 1.857487922705314,
      "grad_norm": 2.4868955612182617,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.3364,
      "step": 48
    },
    {
      "epoch": 1.896135265700483,
      "grad_norm": 2.897385835647583,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.144,
      "step": 49
    },
    {
      "epoch": 1.9347826086956523,
      "grad_norm": 2.7919833660125732,
      "learning_rate": 1e-05,
      "loss": 1.1587,
      "step": 50
    },
    {
      "epoch": 1.9347826086956523,
      "eval_loss": 1.372193455696106,
      "eval_runtime": 1.263,
      "eval_samples_per_second": 39.59,
      "eval_steps_per_second": 10.293,
      "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}