{
  "best_metric": 0.22734582424163818,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.009680307833789115,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003872123133515646,
      "grad_norm": 18.427871704101562,
      "learning_rate": 5e-05,
      "loss": 3.8428,
      "step": 1
    },
    {
      "epoch": 0.0003872123133515646,
      "eval_loss": 3.816296339035034,
      "eval_runtime": 1.2522,
      "eval_samples_per_second": 39.928,
      "eval_steps_per_second": 10.381,
      "step": 1
    },
    {
      "epoch": 0.0007744246267031292,
      "grad_norm": 22.974451065063477,
      "learning_rate": 0.0001,
      "loss": 3.4935,
      "step": 2
    },
    {
      "epoch": 0.0011616369400546938,
      "grad_norm": 19.45110321044922,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.6111,
      "step": 3
    },
    {
      "epoch": 0.0015488492534062584,
      "grad_norm": 23.882034301757812,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.4094,
      "step": 4
    },
    {
      "epoch": 0.001936061566757823,
      "grad_norm": 20.992429733276367,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.6488,
      "step": 5
    },
    {
      "epoch": 0.0023232738801093875,
      "grad_norm": 10.908239364624023,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.2417,
      "step": 6
    },
    {
      "epoch": 0.002710486193460952,
      "grad_norm": 2.6740472316741943,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.059,
      "step": 7
    },
    {
      "epoch": 0.0030976985068125167,
      "grad_norm": 0.971660315990448,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0142,
      "step": 8
    },
    {
      "epoch": 0.003484910820164081,
      "grad_norm": 0.23529735207557678,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0017,
      "step": 9
    },
    {
      "epoch": 0.003872123133515646,
      "grad_norm": 0.04244418814778328,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0004,
      "step": 10
    },
    {
      "epoch": 0.00425933544686721,
      "grad_norm": 27.48731803894043,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.8628,
      "step": 11
    },
    {
      "epoch": 0.004646547760218775,
      "grad_norm": 68.8835220336914,
      "learning_rate": 9.070090031310558e-05,
      "loss": 5.1609,
      "step": 12
    },
    {
      "epoch": 0.00503376007357034,
      "grad_norm": 36.057044982910156,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.8459,
      "step": 13
    },
    {
      "epoch": 0.005420972386921904,
      "grad_norm": 0.17858703434467316,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0013,
      "step": 14
    },
    {
      "epoch": 0.005808184700273469,
      "grad_norm": 0.2483503371477127,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0017,
      "step": 15
    },
    {
      "epoch": 0.0061953970136250334,
      "grad_norm": 0.07233485579490662,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0006,
      "step": 16
    },
    {
      "epoch": 0.006582609326976598,
      "grad_norm": 0.031193960458040237,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0003,
      "step": 17
    },
    {
      "epoch": 0.006969821640328162,
      "grad_norm": 0.02067120373249054,
      "learning_rate": 7.75e-05,
      "loss": 0.0002,
      "step": 18
    },
    {
      "epoch": 0.007357033953679727,
      "grad_norm": 0.01805349811911583,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0002,
      "step": 19
    },
    {
      "epoch": 0.007744246267031292,
      "grad_norm": 0.020172208547592163,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0001,
      "step": 20
    },
    {
      "epoch": 0.008131458580382856,
      "grad_norm": 0.019413195550441742,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.00851867089373442,
      "grad_norm": 0.012640492059290409,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0001,
      "step": 22
    },
    {
      "epoch": 0.008905883207085985,
      "grad_norm": 3.7326242923736572,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.1703,
      "step": 23
    },
    {
      "epoch": 0.00929309552043755,
      "grad_norm": 22.277650833129883,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.8563,
      "step": 24
    },
    {
      "epoch": 0.009680307833789115,
      "grad_norm": 19.738676071166992,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.2722,
      "step": 25
    },
    {
      "epoch": 0.009680307833789115,
      "eval_loss": 0.22734582424163818,
      "eval_runtime": 0.749,
      "eval_samples_per_second": 66.752,
      "eval_steps_per_second": 17.356,
      "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": 1.47650456322048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}