{
  "best_metric": 0.22786331176757812,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.012324377618930245,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004929751047572097,
      "grad_norm": 15.836606979370117,
      "learning_rate": 5e-05,
      "loss": 29.4505,
      "step": 1
    },
    {
      "epoch": 0.0004929751047572097,
      "eval_loss": 0.9615499973297119,
      "eval_runtime": 4.366,
      "eval_samples_per_second": 11.452,
      "eval_steps_per_second": 2.978,
      "step": 1
    },
    {
      "epoch": 0.0009859502095144195,
      "grad_norm": 20.275806427001953,
      "learning_rate": 0.0001,
      "loss": 26.9938,
      "step": 2
    },
    {
      "epoch": 0.0014789253142716292,
      "grad_norm": 26.798494338989258,
      "learning_rate": 9.990365154573717e-05,
      "loss": 28.5796,
      "step": 3
    },
    {
      "epoch": 0.001971900419028839,
      "grad_norm": 30.672178268432617,
      "learning_rate": 9.961501876182148e-05,
      "loss": 27.7565,
      "step": 4
    },
    {
      "epoch": 0.002464875523786049,
      "grad_norm": 33.4011344909668,
      "learning_rate": 9.913533761814537e-05,
      "loss": 20.0287,
      "step": 5
    },
    {
      "epoch": 0.0029578506285432584,
      "grad_norm": 29.589982986450195,
      "learning_rate": 9.846666218300807e-05,
      "loss": 14.5695,
      "step": 6
    },
    {
      "epoch": 0.0034508257333004683,
      "grad_norm": 19.356657028198242,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3163,
      "step": 7
    },
    {
      "epoch": 0.003943800838057678,
      "grad_norm": 12.323790550231934,
      "learning_rate": 9.657457896300791e-05,
      "loss": 8.5799,
      "step": 8
    },
    {
      "epoch": 0.004436775942814888,
      "grad_norm": 11.540504455566406,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.7095,
      "step": 9
    },
    {
      "epoch": 0.004929751047572098,
      "grad_norm": 16.579092025756836,
      "learning_rate": 9.397114317029975e-05,
      "loss": 8.8016,
      "step": 10
    },
    {
      "epoch": 0.005422726152329307,
      "grad_norm": 16.947864532470703,
      "learning_rate": 9.241613255361455e-05,
      "loss": 8.6639,
      "step": 11
    },
    {
      "epoch": 0.005915701257086517,
      "grad_norm": 14.9745454788208,
      "learning_rate": 9.070090031310558e-05,
      "loss": 8.5057,
      "step": 12
    },
    {
      "epoch": 0.006408676361843727,
      "grad_norm": 24.430723190307617,
      "learning_rate": 8.883279133655399e-05,
      "loss": 21.0764,
      "step": 13
    },
    {
      "epoch": 0.006901651466600937,
      "grad_norm": 23.794771194458008,
      "learning_rate": 8.681980515339464e-05,
      "loss": 17.5838,
      "step": 14
    },
    {
      "epoch": 0.007394626571358146,
      "grad_norm": 18.92736053466797,
      "learning_rate": 8.467056167950311e-05,
      "loss": 14.8331,
      "step": 15
    },
    {
      "epoch": 0.007887601676115356,
      "grad_norm": 15.444158554077148,
      "learning_rate": 8.239426430539243e-05,
      "loss": 9.2209,
      "step": 16
    },
    {
      "epoch": 0.008380576780872565,
      "grad_norm": 13.837785720825195,
      "learning_rate": 8.000066048588211e-05,
      "loss": 9.4275,
      "step": 17
    },
    {
      "epoch": 0.008873551885629776,
      "grad_norm": 18.459226608276367,
      "learning_rate": 7.75e-05,
      "loss": 9.8233,
      "step": 18
    },
    {
      "epoch": 0.009366526990386986,
      "grad_norm": 17.682174682617188,
      "learning_rate": 7.490299105985507e-05,
      "loss": 8.4284,
      "step": 19
    },
    {
      "epoch": 0.009859502095144195,
      "grad_norm": 13.08686351776123,
      "learning_rate": 7.222075445642904e-05,
      "loss": 6.4925,
      "step": 20
    },
    {
      "epoch": 0.010352477199901405,
      "grad_norm": 8.8076753616333,
      "learning_rate": 6.946477593864228e-05,
      "loss": 5.1792,
      "step": 21
    },
    {
      "epoch": 0.010845452304658615,
      "grad_norm": 6.819372653961182,
      "learning_rate": 6.664685702961344e-05,
      "loss": 5.9031,
      "step": 22
    },
    {
      "epoch": 0.011338427409415824,
      "grad_norm": 8.491634368896484,
      "learning_rate": 6.377906449072578e-05,
      "loss": 6.2824,
      "step": 23
    },
    {
      "epoch": 0.011831402514173034,
      "grad_norm": 13.081597328186035,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.0264,
      "step": 24
    },
    {
      "epoch": 0.012324377618930245,
      "grad_norm": 14.241148948669434,
      "learning_rate": 5.794314081535644e-05,
      "loss": 6.0079,
      "step": 25
    },
    {
      "epoch": 0.012324377618930245,
      "eval_loss": 0.22786331176757812,
      "eval_runtime": 4.3594,
      "eval_samples_per_second": 11.47,
      "eval_steps_per_second": 2.982,
      "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": 1.4868141154762752e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}