{
  "best_metric": 0.4119807779788971,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.022559995488000903,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000902399819520036,
      "grad_norm": 8.212875366210938,
      "learning_rate": 5e-05,
      "loss": 2.6447,
      "step": 1
    },
    {
      "epoch": 0.000902399819520036,
      "eval_loss": 6.4507269859313965,
      "eval_runtime": 2.0199,
      "eval_samples_per_second": 24.753,
      "eval_steps_per_second": 6.436,
      "step": 1
    },
    {
      "epoch": 0.001804799639040072,
      "grad_norm": 8.473448753356934,
      "learning_rate": 0.0001,
      "loss": 2.6436,
      "step": 2
    },
    {
      "epoch": 0.0027071994585601083,
      "grad_norm": 7.5769195556640625,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.4067,
      "step": 3
    },
    {
      "epoch": 0.003609599278080144,
      "grad_norm": 5.150447368621826,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.497,
      "step": 4
    },
    {
      "epoch": 0.004511999097600181,
      "grad_norm": 3.948168992996216,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.1283,
      "step": 5
    },
    {
      "epoch": 0.0054143989171202165,
      "grad_norm": 5.283059120178223,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.9159,
      "step": 6
    },
    {
      "epoch": 0.0063167987366402525,
      "grad_norm": 3.407850503921509,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.7784,
      "step": 7
    },
    {
      "epoch": 0.007219198556160288,
      "grad_norm": 2.219080686569214,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.6191,
      "step": 8
    },
    {
      "epoch": 0.008121598375680324,
      "grad_norm": 1.9241960048675537,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.7074,
      "step": 9
    },
    {
      "epoch": 0.009023998195200361,
      "grad_norm": 1.7714288234710693,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.5067,
      "step": 10
    },
    {
      "epoch": 0.009926398014720396,
      "grad_norm": 1.5934926271438599,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.4878,
      "step": 11
    },
    {
      "epoch": 0.010828797834240433,
      "grad_norm": 1.5990341901779175,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.5536,
      "step": 12
    },
    {
      "epoch": 0.01173119765376047,
      "grad_norm": 1.3820379972457886,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.4728,
      "step": 13
    },
    {
      "epoch": 0.012633597473280505,
      "grad_norm": 1.4526031017303467,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.5001,
      "step": 14
    },
    {
      "epoch": 0.013535997292800542,
      "grad_norm": 1.1816612482070923,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.4505,
      "step": 15
    },
    {
      "epoch": 0.014438397112320577,
      "grad_norm": 1.2769337892532349,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.4592,
      "step": 16
    },
    {
      "epoch": 0.015340796931840614,
      "grad_norm": 1.3497493267059326,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.4632,
      "step": 17
    },
    {
      "epoch": 0.01624319675136065,
      "grad_norm": 1.1774433851242065,
      "learning_rate": 7.75e-05,
      "loss": 0.4911,
      "step": 18
    },
    {
      "epoch": 0.017145596570880686,
      "grad_norm": 1.2581998109817505,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.5264,
      "step": 19
    },
    {
      "epoch": 0.018047996390400722,
      "grad_norm": 1.0584566593170166,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.459,
      "step": 20
    },
    {
      "epoch": 0.01895039620992076,
      "grad_norm": 1.1238056421279907,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.4488,
      "step": 21
    },
    {
      "epoch": 0.019852796029440792,
      "grad_norm": 1.1382229328155518,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.4585,
      "step": 22
    },
    {
      "epoch": 0.02075519584896083,
      "grad_norm": 1.353520154953003,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.5537,
      "step": 23
    },
    {
      "epoch": 0.021657595668480866,
      "grad_norm": 1.172533631324768,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.4503,
      "step": 24
    },
    {
      "epoch": 0.022559995488000903,
      "grad_norm": 1.1839252710342407,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.5279,
      "step": 25
    },
    {
      "epoch": 0.022559995488000903,
      "eval_loss": 0.4119807779788971,
      "eval_runtime": 2.0297,
      "eval_samples_per_second": 24.635,
      "eval_steps_per_second": 6.405,
      "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": 7.94731890081792e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}