{
  "best_metric": 1.3544864654541016,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01113368775572689,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00044534751022907564,
      "grad_norm": 47.00421142578125,
      "learning_rate": 5e-05,
      "loss": 5.2543,
      "step": 1
    },
    {
      "epoch": 0.00044534751022907564,
      "eval_loss": 6.243781089782715,
      "eval_runtime": 737.4692,
      "eval_samples_per_second": 20.513,
      "eval_steps_per_second": 2.564,
      "step": 1
    },
    {
      "epoch": 0.0008906950204581513,
      "grad_norm": 45.821319580078125,
      "learning_rate": 0.0001,
      "loss": 5.2971,
      "step": 2
    },
    {
      "epoch": 0.001336042530687227,
      "grad_norm": 47.45862579345703,
      "learning_rate": 9.989294616193017e-05,
      "loss": 5.4538,
      "step": 3
    },
    {
      "epoch": 0.0017813900409163026,
      "grad_norm": 70.39472961425781,
      "learning_rate": 9.957224306869053e-05,
      "loss": 5.7192,
      "step": 4
    },
    {
      "epoch": 0.002226737551145378,
      "grad_norm": 76.26249694824219,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.7385,
      "step": 5
    },
    {
      "epoch": 0.002672085061374454,
      "grad_norm": 83.42272186279297,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.399,
      "step": 6
    },
    {
      "epoch": 0.0031174325716035295,
      "grad_norm": 77.07828521728516,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.9627,
      "step": 7
    },
    {
      "epoch": 0.003562780081832605,
      "grad_norm": 70.13909149169922,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.5779,
      "step": 8
    },
    {
      "epoch": 0.00400812759206168,
      "grad_norm": 46.44620895385742,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.2747,
      "step": 9
    },
    {
      "epoch": 0.004453475102290756,
      "grad_norm": 49.42829513549805,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.744,
      "step": 10
    },
    {
      "epoch": 0.0048988226125198315,
      "grad_norm": 48.85025405883789,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.5355,
      "step": 11
    },
    {
      "epoch": 0.005344170122748908,
      "grad_norm": 45.37143325805664,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.6555,
      "step": 12
    },
    {
      "epoch": 0.0057895176329779835,
      "grad_norm": 44.338478088378906,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.4589,
      "step": 13
    },
    {
      "epoch": 0.006234865143207059,
      "grad_norm": 37.574886322021484,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1478,
      "step": 14
    },
    {
      "epoch": 0.006680212653436135,
      "grad_norm": 40.13383483886719,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.8073,
      "step": 15
    },
    {
      "epoch": 0.00712556016366521,
      "grad_norm": 44.1107292175293,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7844,
      "step": 16
    },
    {
      "epoch": 0.007570907673894286,
      "grad_norm": 41.8834114074707,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8501,
      "step": 17
    },
    {
      "epoch": 0.00801625518412336,
      "grad_norm": 41.976158142089844,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6489,
      "step": 18
    },
    {
      "epoch": 0.008461602694352437,
      "grad_norm": 43.49707794189453,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.5935,
      "step": 19
    },
    {
      "epoch": 0.008906950204581512,
      "grad_norm": 29.12820816040039,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2958,
      "step": 20
    },
    {
      "epoch": 0.009352297714810588,
      "grad_norm": 35.42374038696289,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.3354,
      "step": 21
    },
    {
      "epoch": 0.009797645225039663,
      "grad_norm": 37.46640396118164,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5067,
      "step": 22
    },
    {
      "epoch": 0.01024299273526874,
      "grad_norm": 36.21051025390625,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4837,
      "step": 23
    },
    {
      "epoch": 0.010688340245497816,
      "grad_norm": 36.641109466552734,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2959,
      "step": 24
    },
    {
      "epoch": 0.01113368775572689,
      "grad_norm": 34.847164154052734,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.4527,
      "step": 25
    },
    {
      "epoch": 0.01113368775572689,
      "eval_loss": 1.3544864654541016,
      "eval_runtime": 736.2259,
      "eval_samples_per_second": 20.548,
      "eval_steps_per_second": 2.569,
      "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": 5.476375360176128e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}