{
  "best_metric": 0.9570152163505554,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.14947683109118087,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005979073243647235,
      "grad_norm": 1.0753231048583984,
      "learning_rate": 5e-05,
      "loss": 2.6085,
      "step": 1
    },
    {
      "epoch": 0.005979073243647235,
      "eval_loss": 2.679072380065918,
      "eval_runtime": 9.2659,
      "eval_samples_per_second": 121.629,
      "eval_steps_per_second": 15.217,
      "step": 1
    },
    {
      "epoch": 0.01195814648729447,
      "grad_norm": 1.1164913177490234,
      "learning_rate": 0.0001,
      "loss": 2.606,
      "step": 2
    },
    {
      "epoch": 0.017937219730941704,
      "grad_norm": 1.1199455261230469,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.5675,
      "step": 3
    },
    {
      "epoch": 0.02391629297458894,
      "grad_norm": 1.0659465789794922,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.4704,
      "step": 4
    },
    {
      "epoch": 0.029895366218236172,
      "grad_norm": 1.0874993801116943,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.3747,
      "step": 5
    },
    {
      "epoch": 0.03587443946188341,
      "grad_norm": 1.0592572689056396,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1872,
      "step": 6
    },
    {
      "epoch": 0.04185351270553064,
      "grad_norm": 1.0288424491882324,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0218,
      "step": 7
    },
    {
      "epoch": 0.04783258594917788,
      "grad_norm": 0.964034914970398,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8934,
      "step": 8
    },
    {
      "epoch": 0.053811659192825115,
      "grad_norm": 0.9067386388778687,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7613,
      "step": 9
    },
    {
      "epoch": 0.059790732436472344,
      "grad_norm": 0.875987708568573,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7118,
      "step": 10
    },
    {
      "epoch": 0.06576980568011959,
      "grad_norm": 0.8584564328193665,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.7108,
      "step": 11
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": 0.8755573630332947,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.6767,
      "step": 12
    },
    {
      "epoch": 0.07772795216741404,
      "grad_norm": 0.7942352890968323,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.5869,
      "step": 13
    },
    {
      "epoch": 0.08370702541106129,
      "grad_norm": 0.7313013672828674,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3916,
      "step": 14
    },
    {
      "epoch": 0.08968609865470852,
      "grad_norm": 0.7297770380973816,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2703,
      "step": 15
    },
    {
      "epoch": 0.09566517189835576,
      "grad_norm": 0.7625865340232849,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.2765,
      "step": 16
    },
    {
      "epoch": 0.10164424514200299,
      "grad_norm": 0.7098815441131592,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1746,
      "step": 17
    },
    {
      "epoch": 0.10762331838565023,
      "grad_norm": 0.6497551202774048,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1205,
      "step": 18
    },
    {
      "epoch": 0.11360239162929746,
      "grad_norm": 0.5867015719413757,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.0144,
      "step": 19
    },
    {
      "epoch": 0.11958146487294469,
      "grad_norm": 0.6049321889877319,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0283,
      "step": 20
    },
    {
      "epoch": 0.12556053811659193,
      "grad_norm": 0.6885931491851807,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.0738,
      "step": 21
    },
    {
      "epoch": 0.13153961136023917,
      "grad_norm": 0.6182365417480469,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.0135,
      "step": 22
    },
    {
      "epoch": 0.1375186846038864,
      "grad_norm": 0.6049491763114929,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.9173,
      "step": 23
    },
    {
      "epoch": 0.14349775784753363,
      "grad_norm": 0.6933227777481079,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0891,
      "step": 24
    },
    {
      "epoch": 0.14947683109118087,
      "grad_norm": 0.7998446226119995,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1267,
      "step": 25
    },
    {
      "epoch": 0.14947683109118087,
      "eval_loss": 0.9570152163505554,
      "eval_runtime": 9.2344,
      "eval_samples_per_second": 122.044,
      "eval_steps_per_second": 15.269,
      "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": 4.200939509723955e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}