{
  "best_metric": 3.714874029159546,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.029708853238265002,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011883541295306002,
      "grad_norm": 0.8201372027397156,
      "learning_rate": 5e-05,
      "loss": 3.8926,
      "step": 1
    },
    {
      "epoch": 0.0011883541295306002,
      "eval_loss": 4.030940532684326,
      "eval_runtime": 6.3143,
      "eval_samples_per_second": 897.805,
      "eval_steps_per_second": 112.285,
      "step": 1
    },
    {
      "epoch": 0.0023767082590612004,
      "grad_norm": 0.8224248886108398,
      "learning_rate": 0.0001,
      "loss": 3.9675,
      "step": 2
    },
    {
      "epoch": 0.0035650623885918,
      "grad_norm": 0.7688699960708618,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.9722,
      "step": 3
    },
    {
      "epoch": 0.004753416518122401,
      "grad_norm": 0.674767255783081,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.9571,
      "step": 4
    },
    {
      "epoch": 0.0059417706476530005,
      "grad_norm": 0.7187216877937317,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.0018,
      "step": 5
    },
    {
      "epoch": 0.0071301247771836,
      "grad_norm": 0.7618054747581482,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.9173,
      "step": 6
    },
    {
      "epoch": 0.008318478906714201,
      "grad_norm": 0.7201687693595886,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.8358,
      "step": 7
    },
    {
      "epoch": 0.009506833036244802,
      "grad_norm": 0.8512358665466309,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.8229,
      "step": 8
    },
    {
      "epoch": 0.0106951871657754,
      "grad_norm": 0.8960956335067749,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.0595,
      "step": 9
    },
    {
      "epoch": 0.011883541295306001,
      "grad_norm": 1.1318275928497314,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.0056,
      "step": 10
    },
    {
      "epoch": 0.013071895424836602,
      "grad_norm": 2.0533359050750732,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.6666,
      "step": 11
    },
    {
      "epoch": 0.0142602495543672,
      "grad_norm": 2.345188617706299,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.794,
      "step": 12
    },
    {
      "epoch": 0.015448603683897801,
      "grad_norm": 1.2211459875106812,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.8926,
      "step": 13
    },
    {
      "epoch": 0.016636957813428402,
      "grad_norm": 1.8413808345794678,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.8035,
      "step": 14
    },
    {
      "epoch": 0.017825311942959002,
      "grad_norm": 1.8401907682418823,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.8536,
      "step": 15
    },
    {
      "epoch": 0.019013666072489603,
      "grad_norm": 1.4689157009124756,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.8415,
      "step": 16
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 1.282709002494812,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.7771,
      "step": 17
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.0199166536331177,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.7448,
      "step": 18
    },
    {
      "epoch": 0.0225787284610814,
      "grad_norm": 0.7743180394172668,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.7384,
      "step": 19
    },
    {
      "epoch": 0.023767082590612002,
      "grad_norm": 0.9698879718780518,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.7292,
      "step": 20
    },
    {
      "epoch": 0.024955436720142603,
      "grad_norm": 1.0978937149047852,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.7939,
      "step": 21
    },
    {
      "epoch": 0.026143790849673203,
      "grad_norm": 0.9687146544456482,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.9402,
      "step": 22
    },
    {
      "epoch": 0.027332144979203804,
      "grad_norm": 1.7143734693527222,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.8069,
      "step": 23
    },
    {
      "epoch": 0.0285204991087344,
      "grad_norm": 2.6094236373901367,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.7251,
      "step": 24
    },
    {
      "epoch": 0.029708853238265002,
      "grad_norm": 2.66898775100708,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.9362,
      "step": 25
    },
    {
      "epoch": 0.029708853238265002,
      "eval_loss": 3.714874029159546,
      "eval_runtime": 6.4212,
      "eval_samples_per_second": 882.856,
      "eval_steps_per_second": 110.415,
      "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": 1754237608394752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}