{
  "best_metric": 1.1880485544679686e-05,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.060505218575102104,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002420208743004084,
      "grad_norm": 131.33819580078125,
      "learning_rate": 5e-05,
      "loss": 111.0611,
      "step": 1
    },
    {
      "epoch": 0.002420208743004084,
      "eval_loss": 7.585880279541016,
      "eval_runtime": 2.9108,
      "eval_samples_per_second": 17.178,
      "eval_steps_per_second": 4.466,
      "step": 1
    },
    {
      "epoch": 0.004840417486008168,
      "grad_norm": 132.7710723876953,
      "learning_rate": 0.0001,
      "loss": 112.1903,
      "step": 2
    },
    {
      "epoch": 0.007260626229012252,
      "grad_norm": 125.43817901611328,
      "learning_rate": 9.990365154573717e-05,
      "loss": 106.0719,
      "step": 3
    },
    {
      "epoch": 0.009680834972016336,
      "grad_norm": 119.73974609375,
      "learning_rate": 9.961501876182148e-05,
      "loss": 83.2367,
      "step": 4
    },
    {
      "epoch": 0.01210104371502042,
      "grad_norm": 112.78900909423828,
      "learning_rate": 9.913533761814537e-05,
      "loss": 61.5406,
      "step": 5
    },
    {
      "epoch": 0.014521252458024504,
      "grad_norm": 125.04703521728516,
      "learning_rate": 9.846666218300807e-05,
      "loss": 38.4313,
      "step": 6
    },
    {
      "epoch": 0.016941461201028588,
      "grad_norm": 96.21353149414062,
      "learning_rate": 9.761185582727977e-05,
      "loss": 25.4436,
      "step": 7
    },
    {
      "epoch": 0.019361669944032673,
      "grad_norm": 72.18242645263672,
      "learning_rate": 9.657457896300791e-05,
      "loss": 14.8805,
      "step": 8
    },
    {
      "epoch": 0.02178187868703676,
      "grad_norm": 42.342674255371094,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.2297,
      "step": 9
    },
    {
      "epoch": 0.02420208743004084,
      "grad_norm": 18.25030517578125,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.5625,
      "step": 10
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 10.75106143951416,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.1359,
      "step": 11
    },
    {
      "epoch": 0.029042504916049008,
      "grad_norm": 8.85315990447998,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.4542,
      "step": 12
    },
    {
      "epoch": 0.03146271365905309,
      "grad_norm": 6.057021141052246,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.2374,
      "step": 13
    },
    {
      "epoch": 0.033882922402057175,
      "grad_norm": 3.520845413208008,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0789,
      "step": 14
    },
    {
      "epoch": 0.036303131145061264,
      "grad_norm": 0.16829857230186462,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0067,
      "step": 15
    },
    {
      "epoch": 0.038723339888065346,
      "grad_norm": 0.02904125675559044,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0015,
      "step": 16
    },
    {
      "epoch": 0.04114354863106943,
      "grad_norm": 0.049647390842437744,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0017,
      "step": 17
    },
    {
      "epoch": 0.04356375737407352,
      "grad_norm": 0.04762301966547966,
      "learning_rate": 7.75e-05,
      "loss": 0.0015,
      "step": 18
    },
    {
      "epoch": 0.0459839661170776,
      "grad_norm": 0.02013726718723774,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0007,
      "step": 19
    },
    {
      "epoch": 0.04840417486008168,
      "grad_norm": 0.012627098709344864,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0005,
      "step": 20
    },
    {
      "epoch": 0.05082438360308577,
      "grad_norm": 0.007175073027610779,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0003,
      "step": 21
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 0.010423569008708,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0004,
      "step": 22
    },
    {
      "epoch": 0.055664801089093933,
      "grad_norm": 0.010328639298677444,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0004,
      "step": 23
    },
    {
      "epoch": 0.058085009832098015,
      "grad_norm": 0.0085712019354105,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0003,
      "step": 24
    },
    {
      "epoch": 0.060505218575102104,
      "grad_norm": 0.014741580933332443,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0006,
      "step": 25
    },
    {
      "epoch": 0.060505218575102104,
      "eval_loss": 1.1880485544679686e-05,
      "eval_runtime": 2.97,
      "eval_samples_per_second": 16.835,
      "eval_steps_per_second": 4.377,
      "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": 2.631221648430203e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}