{
  "best_metric": 0.7839556336402893,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.4836759371221282,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019347037484885126,
      "grad_norm": 0.1692863553762436,
      "learning_rate": 5e-05,
      "loss": 0.8982,
      "step": 1
    },
    {
      "epoch": 0.019347037484885126,
      "eval_loss": 0.9295976161956787,
      "eval_runtime": 11.7741,
      "eval_samples_per_second": 29.641,
      "eval_steps_per_second": 3.737,
      "step": 1
    },
    {
      "epoch": 0.03869407496977025,
      "grad_norm": 0.19595883786678314,
      "learning_rate": 0.0001,
      "loss": 0.914,
      "step": 2
    },
    {
      "epoch": 0.05804111245465538,
      "grad_norm": 0.20177775621414185,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.936,
      "step": 3
    },
    {
      "epoch": 0.0773881499395405,
      "grad_norm": 0.16258937120437622,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9217,
      "step": 4
    },
    {
      "epoch": 0.09673518742442563,
      "grad_norm": 0.116323322057724,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9111,
      "step": 5
    },
    {
      "epoch": 0.11608222490931076,
      "grad_norm": 0.11548236012458801,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9177,
      "step": 6
    },
    {
      "epoch": 0.1354292623941959,
      "grad_norm": 0.11138743907213211,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.9061,
      "step": 7
    },
    {
      "epoch": 0.154776299879081,
      "grad_norm": 0.09544515609741211,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.94,
      "step": 8
    },
    {
      "epoch": 0.17412333736396615,
      "grad_norm": 0.1043759360909462,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.8681,
      "step": 9
    },
    {
      "epoch": 0.19347037484885127,
      "grad_norm": 0.11711571365594864,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8598,
      "step": 10
    },
    {
      "epoch": 0.21281741233373638,
      "grad_norm": 0.1745804101228714,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.734,
      "step": 11
    },
    {
      "epoch": 0.23216444981862153,
      "grad_norm": 0.22588050365447998,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.4676,
      "step": 12
    },
    {
      "epoch": 0.25151148730350664,
      "grad_norm": 0.09927026927471161,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.7639,
      "step": 13
    },
    {
      "epoch": 0.2708585247883918,
      "grad_norm": 0.07218935340642929,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8462,
      "step": 14
    },
    {
      "epoch": 0.29020556227327693,
      "grad_norm": 0.07588931918144226,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8475,
      "step": 15
    },
    {
      "epoch": 0.309552599758162,
      "grad_norm": 0.07844097167253494,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8485,
      "step": 16
    },
    {
      "epoch": 0.32889963724304716,
      "grad_norm": 0.07124689221382141,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8208,
      "step": 17
    },
    {
      "epoch": 0.3482466747279323,
      "grad_norm": 0.07548082619905472,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8703,
      "step": 18
    },
    {
      "epoch": 0.3675937122128174,
      "grad_norm": 0.0742763951420784,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8794,
      "step": 19
    },
    {
      "epoch": 0.38694074969770254,
      "grad_norm": 0.06965313851833344,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8541,
      "step": 20
    },
    {
      "epoch": 0.4062877871825877,
      "grad_norm": 0.06608602404594421,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8269,
      "step": 21
    },
    {
      "epoch": 0.42563482466747277,
      "grad_norm": 0.0757472813129425,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8262,
      "step": 22
    },
    {
      "epoch": 0.4449818621523579,
      "grad_norm": 0.11505801230669022,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7423,
      "step": 23
    },
    {
      "epoch": 0.46432889963724305,
      "grad_norm": 0.13244807720184326,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6334,
      "step": 24
    },
    {
      "epoch": 0.4836759371221282,
      "grad_norm": 0.23997724056243896,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.2459,
      "step": 25
    },
    {
      "epoch": 0.4836759371221282,
      "eval_loss": 0.7839556336402893,
      "eval_runtime": 11.5661,
      "eval_samples_per_second": 30.174,
      "eval_steps_per_second": 3.804,
      "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": 3.005355905987379e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}