{
  "best_metric": 1.4937388896942139,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.5563282336578581,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022253129346314324,
      "grad_norm": 0.3120327889919281,
      "learning_rate": 5e-05,
      "loss": 1.6035,
      "step": 1
    },
    {
      "epoch": 0.022253129346314324,
      "eval_loss": 1.542589545249939,
      "eval_runtime": 9.287,
      "eval_samples_per_second": 5.384,
      "eval_steps_per_second": 1.4,
      "step": 1
    },
    {
      "epoch": 0.04450625869262865,
      "grad_norm": 0.37038734555244446,
      "learning_rate": 0.0001,
      "loss": 1.6081,
      "step": 2
    },
    {
      "epoch": 0.06675938803894298,
      "grad_norm": 0.37281283736228943,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.5752,
      "step": 3
    },
    {
      "epoch": 0.0890125173852573,
      "grad_norm": 0.3437151312828064,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.6186,
      "step": 4
    },
    {
      "epoch": 0.11126564673157163,
      "grad_norm": 0.3911067545413971,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.6111,
      "step": 5
    },
    {
      "epoch": 0.13351877607788595,
      "grad_norm": 0.4079926908016205,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.6172,
      "step": 6
    },
    {
      "epoch": 0.15577190542420027,
      "grad_norm": 0.3889995813369751,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.5655,
      "step": 7
    },
    {
      "epoch": 0.1780250347705146,
      "grad_norm": 0.4306317865848541,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.5386,
      "step": 8
    },
    {
      "epoch": 0.20027816411682892,
      "grad_norm": 0.5149466395378113,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.5265,
      "step": 9
    },
    {
      "epoch": 0.22253129346314326,
      "grad_norm": 0.4121442437171936,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.4133,
      "step": 10
    },
    {
      "epoch": 0.24478442280945759,
      "grad_norm": 0.46690434217453003,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.4478,
      "step": 11
    },
    {
      "epoch": 0.2670375521557719,
      "grad_norm": 0.3639894425868988,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.5897,
      "step": 12
    },
    {
      "epoch": 0.28929068150208626,
      "grad_norm": 0.368277370929718,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.6057,
      "step": 13
    },
    {
      "epoch": 0.31154381084840055,
      "grad_norm": 0.3164932131767273,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.6024,
      "step": 14
    },
    {
      "epoch": 0.3337969401947149,
      "grad_norm": 0.35643574595451355,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.589,
      "step": 15
    },
    {
      "epoch": 0.3560500695410292,
      "grad_norm": 0.3688993453979492,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.5525,
      "step": 16
    },
    {
      "epoch": 0.37830319888734354,
      "grad_norm": 0.4437098801136017,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.5871,
      "step": 17
    },
    {
      "epoch": 0.40055632823365783,
      "grad_norm": 0.42263108491897583,
      "learning_rate": 7.75e-05,
      "loss": 1.5396,
      "step": 18
    },
    {
      "epoch": 0.4228094575799722,
      "grad_norm": 0.4129128158092499,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.5581,
      "step": 19
    },
    {
      "epoch": 0.44506258692628653,
      "grad_norm": 0.4998800754547119,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.5161,
      "step": 20
    },
    {
      "epoch": 0.4673157162726008,
      "grad_norm": 0.40443554520606995,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.4355,
      "step": 21
    },
    {
      "epoch": 0.48956884561891517,
      "grad_norm": 0.48541754484176636,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.467,
      "step": 22
    },
    {
      "epoch": 0.5118219749652295,
      "grad_norm": 0.4150247275829315,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.5855,
      "step": 23
    },
    {
      "epoch": 0.5340751043115438,
      "grad_norm": 0.383695513010025,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.649,
      "step": 24
    },
    {
      "epoch": 0.5563282336578581,
      "grad_norm": 0.34226423501968384,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.5947,
      "step": 25
    },
    {
      "epoch": 0.5563282336578581,
      "eval_loss": 1.4937388896942139,
      "eval_runtime": 9.3685,
      "eval_samples_per_second": 5.337,
      "eval_steps_per_second": 1.388,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.852248692941128e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}