{
  "best_metric": 0.6284409761428833,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0005227719459662916,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0910877838651665e-05,
      "grad_norm": 84.06869506835938,
      "learning_rate": 0.0001,
      "loss": 22.151,
      "step": 1
    },
    {
      "epoch": 2.0910877838651665e-05,
      "eval_loss": 2.1250600814819336,
      "eval_runtime": 13090.2285,
      "eval_samples_per_second": 1.538,
      "eval_steps_per_second": 0.769,
      "step": 1
    },
    {
      "epoch": 4.182175567730333e-05,
      "grad_norm": 107.03520202636719,
      "learning_rate": 0.0002,
      "loss": 20.9938,
      "step": 2
    },
    {
      "epoch": 6.2732633515955e-05,
      "grad_norm": 93.73246002197266,
      "learning_rate": 0.00019978589232386035,
      "loss": 17.9108,
      "step": 3
    },
    {
      "epoch": 8.364351135460666e-05,
      "grad_norm": 113.86500549316406,
      "learning_rate": 0.00019914448613738106,
      "loss": 9.6585,
      "step": 4
    },
    {
      "epoch": 0.00010455438919325834,
      "grad_norm": 41.913482666015625,
      "learning_rate": 0.00019807852804032305,
      "loss": 3.5512,
      "step": 5
    },
    {
      "epoch": 0.00012546526703191,
      "grad_norm": 16.28923225402832,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.7501,
      "step": 6
    },
    {
      "epoch": 0.00014637614487056166,
      "grad_norm": 41.71613693237305,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.7932,
      "step": 7
    },
    {
      "epoch": 0.00016728702270921332,
      "grad_norm": 23.011554718017578,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.9985,
      "step": 8
    },
    {
      "epoch": 0.000188197900547865,
      "grad_norm": 24.655874252319336,
      "learning_rate": 0.00018968727415326884,
      "loss": 2.7035,
      "step": 9
    },
    {
      "epoch": 0.00020910877838651668,
      "grad_norm": 25.26650619506836,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.4406,
      "step": 10
    },
    {
      "epoch": 0.00023001965622516834,
      "grad_norm": 16.074581146240234,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.7873,
      "step": 11
    },
    {
      "epoch": 0.00025093053406382,
      "grad_norm": 25.244714736938477,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.9661,
      "step": 12
    },
    {
      "epoch": 0.00027184141190247165,
      "grad_norm": 10.805883407592773,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.9819,
      "step": 13
    },
    {
      "epoch": 0.0002927522897411233,
      "grad_norm": 14.331748962402344,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.7413,
      "step": 14
    },
    {
      "epoch": 0.000313663167579775,
      "grad_norm": 10.190518379211426,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.8453,
      "step": 15
    },
    {
      "epoch": 0.00033457404541842664,
      "grad_norm": 11.442252159118652,
      "learning_rate": 0.00016087614290087208,
      "loss": 1.5277,
      "step": 16
    },
    {
      "epoch": 0.0003554849232570783,
      "grad_norm": 8.8699312210083,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.3802,
      "step": 17
    },
    {
      "epoch": 0.00037639580109573,
      "grad_norm": 14.440268516540527,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6073,
      "step": 18
    },
    {
      "epoch": 0.0003973066789343817,
      "grad_norm": 9.176239013671875,
      "learning_rate": 0.00014422886902190014,
      "loss": 1.4792,
      "step": 19
    },
    {
      "epoch": 0.00041821755677303336,
      "grad_norm": 6.998920917510986,
      "learning_rate": 0.000138268343236509,
      "loss": 1.379,
      "step": 20
    },
    {
      "epoch": 0.000439128434611685,
      "grad_norm": 8.3809814453125,
      "learning_rate": 0.00013214394653031616,
      "loss": 1.6289,
      "step": 21
    },
    {
      "epoch": 0.0004600393124503367,
      "grad_norm": 6.837754249572754,
      "learning_rate": 0.00012588190451025207,
      "loss": 1.5846,
      "step": 22
    },
    {
      "epoch": 0.00048095019028898835,
      "grad_norm": 3.7508742809295654,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.9953,
      "step": 23
    },
    {
      "epoch": 0.00050186106812764,
      "grad_norm": 3.6553502082824707,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.2621,
      "step": 24
    },
    {
      "epoch": 0.0005227719459662916,
      "grad_norm": 7.979381084442139,
      "learning_rate": 0.00010654031292301432,
      "loss": 1.2568,
      "step": 25
    },
    {
      "epoch": 0.0005227719459662916,
      "eval_loss": 0.6284409761428833,
      "eval_runtime": 13131.3766,
      "eval_samples_per_second": 1.533,
      "eval_steps_per_second": 0.767,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.51564749340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}