{
  "best_metric": 1.1481486558914185,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.016909029421711193,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006763611768684477,
      "grad_norm": 2.210228681564331,
      "learning_rate": 2e-05,
      "loss": 5.2324,
      "step": 1
    },
    {
      "epoch": 0.0006763611768684477,
      "eval_loss": 1.3878569602966309,
      "eval_runtime": 62.4568,
      "eval_samples_per_second": 39.868,
      "eval_steps_per_second": 4.995,
      "step": 1
    },
    {
      "epoch": 0.0013527223537368955,
      "grad_norm": 2.4433717727661133,
      "learning_rate": 4e-05,
      "loss": 5.1105,
      "step": 2
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": 2.504581928253174,
      "learning_rate": 6e-05,
      "loss": 5.0322,
      "step": 3
    },
    {
      "epoch": 0.002705444707473791,
      "grad_norm": 2.3368101119995117,
      "learning_rate": 8e-05,
      "loss": 5.1913,
      "step": 4
    },
    {
      "epoch": 0.0033818058843422386,
      "grad_norm": 2.202308416366577,
      "learning_rate": 0.0001,
      "loss": 4.6383,
      "step": 5
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": 1.9372011423110962,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.8722,
      "step": 6
    },
    {
      "epoch": 0.0047345282380791345,
      "grad_norm": 2.3214731216430664,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.7582,
      "step": 7
    },
    {
      "epoch": 0.005410889414947582,
      "grad_norm": 2.0861144065856934,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.6053,
      "step": 8
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": 1.699201226234436,
      "learning_rate": 9.806308479691595e-05,
      "loss": 4.3391,
      "step": 9
    },
    {
      "epoch": 0.006763611768684477,
      "grad_norm": 1.7300448417663574,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.7776,
      "step": 10
    },
    {
      "epoch": 0.0074399729455529254,
      "grad_norm": 1.5897445678710938,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.5046,
      "step": 11
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": 1.7118216753005981,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.5287,
      "step": 12
    },
    {
      "epoch": 0.00879269529928982,
      "grad_norm": 1.6620103120803833,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.6679,
      "step": 13
    },
    {
      "epoch": 0.009469056476158269,
      "grad_norm": 1.6078102588653564,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.6585,
      "step": 14
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": 1.708989143371582,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.6418,
      "step": 15
    },
    {
      "epoch": 0.010821778829895164,
      "grad_norm": 1.634358286857605,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.7981,
      "step": 16
    },
    {
      "epoch": 0.011498140006763611,
      "grad_norm": 1.641950249671936,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.6754,
      "step": 17
    },
    {
      "epoch": 0.01217450118363206,
      "grad_norm": 1.6090244054794312,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.7456,
      "step": 18
    },
    {
      "epoch": 0.012850862360500507,
      "grad_norm": 1.5953105688095093,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.6286,
      "step": 19
    },
    {
      "epoch": 0.013527223537368955,
      "grad_norm": 1.5897241830825806,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.5854,
      "step": 20
    },
    {
      "epoch": 0.014203584714237404,
      "grad_norm": 1.5782119035720825,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.9393,
      "step": 21
    },
    {
      "epoch": 0.014879945891105851,
      "grad_norm": 1.5145971775054932,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.5412,
      "step": 22
    },
    {
      "epoch": 0.015556307067974298,
      "grad_norm": 1.4755655527114868,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.5503,
      "step": 23
    },
    {
      "epoch": 0.016232668244842745,
      "grad_norm": 1.4611729383468628,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.5544,
      "step": 24
    },
    {
      "epoch": 0.016909029421711193,
      "grad_norm": 1.5055865049362183,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.6855,
      "step": 25
    },
    {
      "epoch": 0.016909029421711193,
      "eval_loss": 1.1481486558914185,
      "eval_runtime": 63.488,
      "eval_samples_per_second": 39.22,
      "eval_steps_per_second": 4.914,
      "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": 5,
        "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": 9914505064611840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}