{
  "best_metric": 3.6986312866210938,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0035167153878277687,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014066861551311076,
      "grad_norm": 0.9218872785568237,
      "learning_rate": 5e-05,
      "loss": 2.2525,
      "step": 1
    },
    {
      "epoch": 0.00014066861551311076,
      "eval_loss": 5.381374359130859,
      "eval_runtime": 4.3276,
      "eval_samples_per_second": 11.554,
      "eval_steps_per_second": 3.004,
      "step": 1
    },
    {
      "epoch": 0.00028133723102622153,
      "grad_norm": 1.4398459196090698,
      "learning_rate": 0.0001,
      "loss": 3.0518,
      "step": 2
    },
    {
      "epoch": 0.00042200584653933227,
      "grad_norm": 1.8477466106414795,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.6471,
      "step": 3
    },
    {
      "epoch": 0.0005626744620524431,
      "grad_norm": 2.2851502895355225,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.4055,
      "step": 4
    },
    {
      "epoch": 0.0007033430775655537,
      "grad_norm": 3.3054018020629883,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.6705,
      "step": 5
    },
    {
      "epoch": 0.0008440116930786645,
      "grad_norm": 3.301938056945801,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.4529,
      "step": 6
    },
    {
      "epoch": 0.0009846803085917753,
      "grad_norm": 2.362037420272827,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.2649,
      "step": 7
    },
    {
      "epoch": 0.0011253489241048861,
      "grad_norm": 2.303856372833252,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.3427,
      "step": 8
    },
    {
      "epoch": 0.0012660175396179967,
      "grad_norm": 2.2928717136383057,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.2532,
      "step": 9
    },
    {
      "epoch": 0.0014066861551311075,
      "grad_norm": 2.7700459957122803,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.1642,
      "step": 10
    },
    {
      "epoch": 0.0015473547706442183,
      "grad_norm": 3.446438789367676,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.4021,
      "step": 11
    },
    {
      "epoch": 0.001688023386157329,
      "grad_norm": 4.7801079750061035,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.6508,
      "step": 12
    },
    {
      "epoch": 0.0018286920016704399,
      "grad_norm": 3.1333518028259277,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.4654,
      "step": 13
    },
    {
      "epoch": 0.0019693606171835507,
      "grad_norm": 3.198070526123047,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.8728,
      "step": 14
    },
    {
      "epoch": 0.0021100292326966612,
      "grad_norm": 2.388134002685547,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.9741,
      "step": 15
    },
    {
      "epoch": 0.0022506978482097722,
      "grad_norm": 2.387596368789673,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.3491,
      "step": 16
    },
    {
      "epoch": 0.002391366463722883,
      "grad_norm": 3.9135308265686035,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.8081,
      "step": 17
    },
    {
      "epoch": 0.0025320350792359934,
      "grad_norm": 2.6444458961486816,
      "learning_rate": 7.75e-05,
      "loss": 3.7437,
      "step": 18
    },
    {
      "epoch": 0.0026727036947491044,
      "grad_norm": 1.9664329290390015,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.9872,
      "step": 19
    },
    {
      "epoch": 0.002813372310262215,
      "grad_norm": 1.8564341068267822,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.9519,
      "step": 20
    },
    {
      "epoch": 0.002954040925775326,
      "grad_norm": 2.011428117752075,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.7962,
      "step": 21
    },
    {
      "epoch": 0.0030947095412884366,
      "grad_norm": 2.2582523822784424,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.0475,
      "step": 22
    },
    {
      "epoch": 0.0032353781568015476,
      "grad_norm": 2.4788050651550293,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.9397,
      "step": 23
    },
    {
      "epoch": 0.003376046772314658,
      "grad_norm": 2.514291763305664,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.2982,
      "step": 24
    },
    {
      "epoch": 0.0035167153878277687,
      "grad_norm": 3.6239752769470215,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.8512,
      "step": 25
    },
    {
      "epoch": 0.0035167153878277687,
      "eval_loss": 3.6986312866210938,
      "eval_runtime": 4.3224,
      "eval_samples_per_second": 11.568,
      "eval_steps_per_second": 3.008,
      "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": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}