{
  "best_metric": 1.025231957435608,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.13311148086522462,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005324459234608985,
      "grad_norm": 18.178590774536133,
      "learning_rate": 5e-05,
      "loss": 8.5952,
      "step": 1
    },
    {
      "epoch": 0.005324459234608985,
      "eval_loss": 9.400318145751953,
      "eval_runtime": 18.5977,
      "eval_samples_per_second": 68.019,
      "eval_steps_per_second": 8.549,
      "step": 1
    },
    {
      "epoch": 0.01064891846921797,
      "grad_norm": 18.524410247802734,
      "learning_rate": 0.0001,
      "loss": 9.3788,
      "step": 2
    },
    {
      "epoch": 0.015973377703826955,
      "grad_norm": 19.018756866455078,
      "learning_rate": 9.989294616193017e-05,
      "loss": 8.7897,
      "step": 3
    },
    {
      "epoch": 0.02129783693843594,
      "grad_norm": 20.549850463867188,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.7922,
      "step": 4
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 16.51919174194336,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.5688,
      "step": 5
    },
    {
      "epoch": 0.03194675540765391,
      "grad_norm": 17.26973533630371,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.8683,
      "step": 6
    },
    {
      "epoch": 0.03727121464226289,
      "grad_norm": 17.099246978759766,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.3049,
      "step": 7
    },
    {
      "epoch": 0.04259567387687188,
      "grad_norm": 15.791613578796387,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7113,
      "step": 8
    },
    {
      "epoch": 0.04792013311148086,
      "grad_norm": 13.631885528564453,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.1921,
      "step": 9
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 10.722579956054688,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9171,
      "step": 10
    },
    {
      "epoch": 0.05856905158069883,
      "grad_norm": 8.825370788574219,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.6998,
      "step": 11
    },
    {
      "epoch": 0.06389351081530782,
      "grad_norm": 9.83297348022461,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.6349,
      "step": 12
    },
    {
      "epoch": 0.06921797004991681,
      "grad_norm": 8.454965591430664,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.4389,
      "step": 13
    },
    {
      "epoch": 0.07454242928452579,
      "grad_norm": 7.133016586303711,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.068,
      "step": 14
    },
    {
      "epoch": 0.07986688851913477,
      "grad_norm": 5.394034385681152,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.1103,
      "step": 15
    },
    {
      "epoch": 0.08519134775374376,
      "grad_norm": 4.61173677444458,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7236,
      "step": 16
    },
    {
      "epoch": 0.09051580698835275,
      "grad_norm": 5.1000494956970215,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6841,
      "step": 17
    },
    {
      "epoch": 0.09584026622296173,
      "grad_norm": 4.409814834594727,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5031,
      "step": 18
    },
    {
      "epoch": 0.10116472545757071,
      "grad_norm": 4.465449810028076,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6356,
      "step": 19
    },
    {
      "epoch": 0.1064891846921797,
      "grad_norm": 3.6205997467041016,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2527,
      "step": 20
    },
    {
      "epoch": 0.11181364392678869,
      "grad_norm": 3.848710775375366,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.0677,
      "step": 21
    },
    {
      "epoch": 0.11713810316139767,
      "grad_norm": 4.458807468414307,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.1782,
      "step": 22
    },
    {
      "epoch": 0.12246256239600666,
      "grad_norm": 5.331320762634277,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.1036,
      "step": 23
    },
    {
      "epoch": 0.12778702163061564,
      "grad_norm": 6.583466529846191,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1917,
      "step": 24
    },
    {
      "epoch": 0.13311148086522462,
      "grad_norm": 8.270636558532715,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5809,
      "step": 25
    },
    {
      "epoch": 0.13311148086522462,
      "eval_loss": 1.025231957435608,
      "eval_runtime": 18.5274,
      "eval_samples_per_second": 68.277,
      "eval_steps_per_second": 8.582,
      "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
}