{
  "best_metric": 0.1733342856168747,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.02914602156805596,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011658408627222385,
      "grad_norm": 17.24015235900879,
      "learning_rate": 5e-05,
      "loss": 12.1759,
      "step": 1
    },
    {
      "epoch": 0.0011658408627222385,
      "eval_loss": 12.8995943069458,
      "eval_runtime": 175.2287,
      "eval_samples_per_second": 32.98,
      "eval_steps_per_second": 4.126,
      "step": 1
    },
    {
      "epoch": 0.002331681725444477,
      "grad_norm": 17.535289764404297,
      "learning_rate": 0.0001,
      "loss": 12.3466,
      "step": 2
    },
    {
      "epoch": 0.0034975225881667153,
      "grad_norm": 18.36772918701172,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.5776,
      "step": 3
    },
    {
      "epoch": 0.004663363450888954,
      "grad_norm": 16.71552848815918,
      "learning_rate": 9.957224306869053e-05,
      "loss": 8.4475,
      "step": 4
    },
    {
      "epoch": 0.005829204313611192,
      "grad_norm": 17.996538162231445,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.6639,
      "step": 5
    },
    {
      "epoch": 0.006995045176333431,
      "grad_norm": 16.047048568725586,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.0267,
      "step": 6
    },
    {
      "epoch": 0.00816088603905567,
      "grad_norm": 9.27939510345459,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.3969,
      "step": 7
    },
    {
      "epoch": 0.009326726901777908,
      "grad_norm": 7.133617401123047,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.834,
      "step": 8
    },
    {
      "epoch": 0.010492567764500145,
      "grad_norm": 5.511355876922607,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.4855,
      "step": 9
    },
    {
      "epoch": 0.011658408627222384,
      "grad_norm": 10.509987831115723,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7562,
      "step": 10
    },
    {
      "epoch": 0.012824249489944622,
      "grad_norm": 7.408633708953857,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5402,
      "step": 11
    },
    {
      "epoch": 0.013990090352666861,
      "grad_norm": 4.484230041503906,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.3087,
      "step": 12
    },
    {
      "epoch": 0.0151559312153891,
      "grad_norm": 4.411365985870361,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3547,
      "step": 13
    },
    {
      "epoch": 0.01632177207811134,
      "grad_norm": 4.336910247802734,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.267,
      "step": 14
    },
    {
      "epoch": 0.017487612940833577,
      "grad_norm": 1.5031633377075195,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.206,
      "step": 15
    },
    {
      "epoch": 0.018653453803555816,
      "grad_norm": 1.7164764404296875,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2121,
      "step": 16
    },
    {
      "epoch": 0.019819294666278055,
      "grad_norm": 3.2747690677642822,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2256,
      "step": 17
    },
    {
      "epoch": 0.02098513552900029,
      "grad_norm": 1.200957179069519,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1851,
      "step": 18
    },
    {
      "epoch": 0.02215097639172253,
      "grad_norm": 2.802654266357422,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.1723,
      "step": 19
    },
    {
      "epoch": 0.023316817254444767,
      "grad_norm": 2.411452054977417,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1544,
      "step": 20
    },
    {
      "epoch": 0.024482658117167006,
      "grad_norm": 0.8326784372329712,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1383,
      "step": 21
    },
    {
      "epoch": 0.025648498979889245,
      "grad_norm": 0.6607847809791565,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1423,
      "step": 22
    },
    {
      "epoch": 0.026814339842611484,
      "grad_norm": 0.9250856041908264,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1132,
      "step": 23
    },
    {
      "epoch": 0.027980180705333722,
      "grad_norm": 3.356832504272461,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1259,
      "step": 24
    },
    {
      "epoch": 0.02914602156805596,
      "grad_norm": 1.1452975273132324,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.1304,
      "step": 25
    },
    {
      "epoch": 0.02914602156805596,
      "eval_loss": 0.1733342856168747,
      "eval_runtime": 175.3599,
      "eval_samples_per_second": 32.955,
      "eval_steps_per_second": 4.123,
      "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}