{
  "best_metric": 11.930267333984375,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06284861340246681,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002513944536098672,
      "grad_norm": 0.012646043673157692,
      "learning_rate": 5e-05,
      "loss": 11.9327,
      "step": 1
    },
    {
      "epoch": 0.002513944536098672,
      "eval_loss": 11.931513786315918,
      "eval_runtime": 0.2515,
      "eval_samples_per_second": 198.82,
      "eval_steps_per_second": 51.693,
      "step": 1
    },
    {
      "epoch": 0.005027889072197344,
      "grad_norm": 0.012877545319497585,
      "learning_rate": 0.0001,
      "loss": 11.9322,
      "step": 2
    },
    {
      "epoch": 0.007541833608296017,
      "grad_norm": 0.013343454338610172,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.010055778144394689,
      "grad_norm": 0.012295612134039402,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9316,
      "step": 4
    },
    {
      "epoch": 0.012569722680493361,
      "grad_norm": 0.013433913700282574,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9319,
      "step": 5
    },
    {
      "epoch": 0.015083667216592034,
      "grad_norm": 0.017989417538046837,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9317,
      "step": 6
    },
    {
      "epoch": 0.017597611752690707,
      "grad_norm": 0.019290514290332794,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.931,
      "step": 7
    },
    {
      "epoch": 0.020111556288789377,
      "grad_norm": 0.018904713913798332,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9307,
      "step": 8
    },
    {
      "epoch": 0.02262550082488805,
      "grad_norm": 0.02798588201403618,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9314,
      "step": 9
    },
    {
      "epoch": 0.025139445360986723,
      "grad_norm": 0.030021728947758675,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9326,
      "step": 10
    },
    {
      "epoch": 0.027653389897085396,
      "grad_norm": 0.03367425501346588,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9304,
      "step": 11
    },
    {
      "epoch": 0.03016733443318407,
      "grad_norm": 0.03730316087603569,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.928,
      "step": 12
    },
    {
      "epoch": 0.03268127896928274,
      "grad_norm": 0.017860587686300278,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9323,
      "step": 13
    },
    {
      "epoch": 0.035195223505381415,
      "grad_norm": 0.01678677462041378,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9322,
      "step": 14
    },
    {
      "epoch": 0.037709168041480084,
      "grad_norm": 0.017414981499314308,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9321,
      "step": 15
    },
    {
      "epoch": 0.040223112577578754,
      "grad_norm": 0.018565161153674126,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9315,
      "step": 16
    },
    {
      "epoch": 0.04273705711367743,
      "grad_norm": 0.023156052455306053,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9313,
      "step": 17
    },
    {
      "epoch": 0.0452510016497761,
      "grad_norm": 0.024580350145697594,
      "learning_rate": 7.75e-05,
      "loss": 11.9309,
      "step": 18
    },
    {
      "epoch": 0.047764946185874776,
      "grad_norm": 0.025019587948918343,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9314,
      "step": 19
    },
    {
      "epoch": 0.050278890721973446,
      "grad_norm": 0.03346352279186249,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9309,
      "step": 20
    },
    {
      "epoch": 0.052792835258072116,
      "grad_norm": 0.030500687658786774,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9301,
      "step": 21
    },
    {
      "epoch": 0.05530677979417079,
      "grad_norm": 0.04018493369221687,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9317,
      "step": 22
    },
    {
      "epoch": 0.05782072433026946,
      "grad_norm": 0.03532632812857628,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9303,
      "step": 23
    },
    {
      "epoch": 0.06033466886636814,
      "grad_norm": 0.0557476244866848,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9325,
      "step": 24
    },
    {
      "epoch": 0.06284861340246681,
      "grad_norm": 0.0716874822974205,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9321,
      "step": 25
    },
    {
      "epoch": 0.06284861340246681,
      "eval_loss": 11.930267333984375,
      "eval_runtime": 0.2538,
      "eval_samples_per_second": 197.011,
      "eval_steps_per_second": 51.223,
      "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": 521247129600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}