{
  "best_metric": 9.109885215759277,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.017778172848285517,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007111269139314207,
      "grad_norm": 4.551875591278076,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.2843,
      "step": 1
    },
    {
      "epoch": 0.0007111269139314207,
      "eval_loss": 10.709673881530762,
      "eval_runtime": 0.4786,
      "eval_samples_per_second": 104.474,
      "eval_steps_per_second": 27.163,
      "step": 1
    },
    {
      "epoch": 0.0014222538278628415,
      "grad_norm": 4.867107391357422,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.4354,
      "step": 2
    },
    {
      "epoch": 0.002133380741794262,
      "grad_norm": 5.008926868438721,
      "learning_rate": 0.0001,
      "loss": 10.5558,
      "step": 3
    },
    {
      "epoch": 0.002844507655725683,
      "grad_norm": 4.5886006355285645,
      "learning_rate": 9.997376600647783e-05,
      "loss": 10.7391,
      "step": 4
    },
    {
      "epoch": 0.0035556345696571034,
      "grad_norm": 4.7824931144714355,
      "learning_rate": 9.989509461357426e-05,
      "loss": 10.5872,
      "step": 5
    },
    {
      "epoch": 0.004266761483588524,
      "grad_norm": 4.664742946624756,
      "learning_rate": 9.976407754861426e-05,
      "loss": 10.5323,
      "step": 6
    },
    {
      "epoch": 0.004977888397519945,
      "grad_norm": 4.836978912353516,
      "learning_rate": 9.958086757163489e-05,
      "loss": 10.5264,
      "step": 7
    },
    {
      "epoch": 0.005689015311451366,
      "grad_norm": 4.371374607086182,
      "learning_rate": 9.934567829727386e-05,
      "loss": 10.2373,
      "step": 8
    },
    {
      "epoch": 0.006400142225382786,
      "grad_norm": 4.762342929840088,
      "learning_rate": 9.905878394570453e-05,
      "loss": 10.4186,
      "step": 9
    },
    {
      "epoch": 0.007111269139314207,
      "grad_norm": 4.17842435836792,
      "learning_rate": 9.872051902290737e-05,
      "loss": 10.331,
      "step": 10
    },
    {
      "epoch": 0.007822396053245627,
      "grad_norm": 4.5304059982299805,
      "learning_rate": 9.833127793065098e-05,
      "loss": 10.4491,
      "step": 11
    },
    {
      "epoch": 0.008533522967177049,
      "grad_norm": 4.463905334472656,
      "learning_rate": 9.789151450663723e-05,
      "loss": 10.2205,
      "step": 12
    },
    {
      "epoch": 0.00924464988110847,
      "grad_norm": 3.405884027481079,
      "learning_rate": 9.740174149534693e-05,
      "loss": 9.3648,
      "step": 13
    },
    {
      "epoch": 0.00995577679503989,
      "grad_norm": 3.4769484996795654,
      "learning_rate": 9.686252995020249e-05,
      "loss": 9.4946,
      "step": 14
    },
    {
      "epoch": 0.01066690370897131,
      "grad_norm": 3.3445122241973877,
      "learning_rate": 9.627450856774539e-05,
      "loss": 9.4722,
      "step": 15
    },
    {
      "epoch": 0.011378030622902732,
      "grad_norm": 3.351897716522217,
      "learning_rate": 9.563836295460398e-05,
      "loss": 9.4804,
      "step": 16
    },
    {
      "epoch": 0.012089157536834151,
      "grad_norm": 3.094649314880371,
      "learning_rate": 9.495483482810688e-05,
      "loss": 9.5855,
      "step": 17
    },
    {
      "epoch": 0.012800284450765573,
      "grad_norm": 2.8600270748138428,
      "learning_rate": 9.422472115147382e-05,
      "loss": 9.812,
      "step": 18
    },
    {
      "epoch": 0.013511411364696994,
      "grad_norm": 2.8953499794006348,
      "learning_rate": 9.3448873204592e-05,
      "loss": 9.3379,
      "step": 19
    },
    {
      "epoch": 0.014222538278628414,
      "grad_norm": 2.8371353149414062,
      "learning_rate": 9.2628195591462e-05,
      "loss": 9.3945,
      "step": 20
    },
    {
      "epoch": 0.014933665192559835,
      "grad_norm": 2.5929179191589355,
      "learning_rate": 9.176364518546989e-05,
      "loss": 9.698,
      "step": 21
    },
    {
      "epoch": 0.015644792106491254,
      "grad_norm": 2.513587474822998,
      "learning_rate": 9.08562300137157e-05,
      "loss": 9.4719,
      "step": 22
    },
    {
      "epoch": 0.016355919020422677,
      "grad_norm": 2.3741440773010254,
      "learning_rate": 8.990700808169889e-05,
      "loss": 9.5754,
      "step": 23
    },
    {
      "epoch": 0.017067045934354097,
      "grad_norm": 2.4249138832092285,
      "learning_rate": 8.891708613973126e-05,
      "loss": 9.6962,
      "step": 24
    },
    {
      "epoch": 0.017778172848285517,
      "grad_norm": 2.4952895641326904,
      "learning_rate": 8.788761839251559e-05,
      "loss": 9.6702,
      "step": 25
    },
    {
      "epoch": 0.017778172848285517,
      "eval_loss": 9.109885215759277,
      "eval_runtime": 0.4854,
      "eval_samples_per_second": 103.018,
      "eval_steps_per_second": 26.785,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 116006898892800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}