{
  "best_metric": 3.723201871252968e-06,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.1501783367749202,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003003566735498404,
      "eval_loss": 2.3162312507629395,
      "eval_runtime": 137.0881,
      "eval_samples_per_second": 40.908,
      "eval_steps_per_second": 10.227,
      "step": 1
    },
    {
      "epoch": 0.015017833677492022,
      "grad_norm": 0.015516551211476326,
      "learning_rate": 0.000104,
      "loss": 0.3661,
      "step": 50
    },
    {
      "epoch": 0.030035667354984044,
      "grad_norm": 0.010866948403418064,
      "learning_rate": 0.000208,
      "loss": 0.0053,
      "step": 100
    },
    {
      "epoch": 0.045053501032476066,
      "grad_norm": 0.0025364630855619907,
      "learning_rate": 0.0002000834713811738,
      "loss": 0.0248,
      "step": 150
    },
    {
      "epoch": 0.06007133470996809,
      "grad_norm": 0.003113877959549427,
      "learning_rate": 0.00017753910524340093,
      "loss": 0.0354,
      "step": 200
    },
    {
      "epoch": 0.0750891683874601,
      "grad_norm": 0.005517065059393644,
      "learning_rate": 0.00014379907696596933,
      "loss": 0.0736,
      "step": 250
    },
    {
      "epoch": 0.09010700206495213,
      "grad_norm": 0.00502326525747776,
      "learning_rate": 0.000104,
      "loss": 0.0419,
      "step": 300
    },
    {
      "epoch": 0.10512483574244415,
      "grad_norm": 0.00045681343181058764,
      "learning_rate": 6.420092303403067e-05,
      "loss": 0.0001,
      "step": 350
    },
    {
      "epoch": 0.12014266941993618,
      "grad_norm": 0.00028651420143432915,
      "learning_rate": 3.0460894756599063e-05,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.1351605030974282,
      "grad_norm": 0.000249331264058128,
      "learning_rate": 7.916528618826179e-06,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.1501783367749202,
      "grad_norm": 0.0002594061370473355,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.1501783367749202,
      "eval_loss": 3.723201871252968e-06,
      "eval_runtime": 136.8368,
      "eval_samples_per_second": 40.983,
      "eval_steps_per_second": 10.246,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8642412158976e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}