{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05636978579481398,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002254791431792559,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.002254791431792559,
      "eval_loss": NaN,
      "eval_runtime": 201.9202,
      "eval_samples_per_second": 14.798,
      "eval_steps_per_second": 1.852,
      "step": 1
    },
    {
      "epoch": 0.004509582863585118,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006764374295377677,
      "grad_norm": 0.0,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.009019165727170236,
      "grad_norm": 6.439255714416504,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.0658,
      "step": 4
    },
    {
      "epoch": 0.011273957158962795,
      "grad_norm": 0.0,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.013528748590755355,
      "grad_norm": 0.0,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.015783540022547914,
      "grad_norm": 13.426411628723145,
      "learning_rate": 9.73465064747553e-05,
      "loss": 6.6367,
      "step": 7
    },
    {
      "epoch": 0.018038331454340473,
      "grad_norm": 14.613255500793457,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.8099,
      "step": 8
    },
    {
      "epoch": 0.020293122886133032,
      "grad_norm": 15.032930374145508,
      "learning_rate": 9.484363707663442e-05,
      "loss": 9.2525,
      "step": 9
    },
    {
      "epoch": 0.02254791431792559,
      "grad_norm": 17.658451080322266,
      "learning_rate": 9.330127018922194e-05,
      "loss": 7.5193,
      "step": 10
    },
    {
      "epoch": 0.02480270574971815,
      "grad_norm": 16.159095764160156,
      "learning_rate": 9.157348061512727e-05,
      "loss": 6.0037,
      "step": 11
    },
    {
      "epoch": 0.02705749718151071,
      "grad_norm": 13.322366714477539,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.3432,
      "step": 12
    },
    {
      "epoch": 0.029312288613303268,
      "grad_norm": 11.127376556396484,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.6831,
      "step": 13
    },
    {
      "epoch": 0.03156708004509583,
      "grad_norm": 0.0,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.033821871476888386,
      "grad_norm": 0.0,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.036076662908680945,
      "grad_norm": 10.085834503173828,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.1855,
      "step": 16
    },
    {
      "epoch": 0.038331454340473504,
      "grad_norm": 0.0,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.040586245772266064,
      "grad_norm": 0.0,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04284103720405862,
      "grad_norm": 0.0,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.04509582863585118,
      "grad_norm": 25.233718872070312,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.9613,
      "step": 20
    },
    {
      "epoch": 0.04735062006764374,
      "grad_norm": 22.64263153076172,
      "learning_rate": 6.607197326515808e-05,
      "loss": 6.1834,
      "step": 21
    },
    {
      "epoch": 0.0496054114994363,
      "grad_norm": 14.661815643310547,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.6658,
      "step": 22
    },
    {
      "epoch": 0.05186020293122886,
      "grad_norm": 15.324529647827148,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.5992,
      "step": 23
    },
    {
      "epoch": 0.05411499436302142,
      "grad_norm": 13.3060884475708,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.7297,
      "step": 24
    },
    {
      "epoch": 0.05636978579481398,
      "grad_norm": 8.085643768310547,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.9261,
      "step": 25
    },
    {
      "epoch": 0.05636978579481398,
      "eval_loss": NaN,
      "eval_runtime": 201.7596,
      "eval_samples_per_second": 14.81,
      "eval_steps_per_second": 1.854,
      "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
}