{
  "best_metric": 0.8921794295310974,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10178117048346055,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005089058524173028,
      "eval_loss": 1.7877963781356812,
      "eval_runtime": 34.8303,
      "eval_samples_per_second": 23.772,
      "eval_steps_per_second": 5.943,
      "step": 1
    },
    {
      "epoch": 0.005089058524173028,
      "grad_norm": 19.215145111083984,
      "learning_rate": 5.05e-06,
      "loss": 1.8396,
      "step": 10
    },
    {
      "epoch": 0.010178117048346057,
      "grad_norm": 18.71825408935547,
      "learning_rate": 1.01e-05,
      "loss": 1.8566,
      "step": 20
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 11.373724937438965,
      "learning_rate": 9.538888888888889e-06,
      "loss": 1.0249,
      "step": 30
    },
    {
      "epoch": 0.020356234096692113,
      "grad_norm": 9.73820972442627,
      "learning_rate": 8.977777777777778e-06,
      "loss": 0.8865,
      "step": 40
    },
    {
      "epoch": 0.02544529262086514,
      "grad_norm": 16.09589195251465,
      "learning_rate": 8.416666666666667e-06,
      "loss": 0.8376,
      "step": 50
    },
    {
      "epoch": 0.02544529262086514,
      "eval_loss": 1.0367200374603271,
      "eval_runtime": 34.9046,
      "eval_samples_per_second": 23.722,
      "eval_steps_per_second": 5.93,
      "step": 50
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 10.095135688781738,
      "learning_rate": 7.855555555555556e-06,
      "loss": 1.0159,
      "step": 60
    },
    {
      "epoch": 0.035623409669211195,
      "grad_norm": 14.570350646972656,
      "learning_rate": 7.294444444444444e-06,
      "loss": 1.5958,
      "step": 70
    },
    {
      "epoch": 0.04071246819338423,
      "grad_norm": 6.843364715576172,
      "learning_rate": 6.733333333333333e-06,
      "loss": 0.9956,
      "step": 80
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": 7.70328426361084,
      "learning_rate": 6.172222222222223e-06,
      "loss": 0.7241,
      "step": 90
    },
    {
      "epoch": 0.05089058524173028,
      "grad_norm": 14.757134437561035,
      "learning_rate": 5.611111111111111e-06,
      "loss": 0.6845,
      "step": 100
    },
    {
      "epoch": 0.05089058524173028,
      "eval_loss": 0.9478112459182739,
      "eval_runtime": 35.0001,
      "eval_samples_per_second": 23.657,
      "eval_steps_per_second": 5.914,
      "step": 100
    },
    {
      "epoch": 0.05597964376590331,
      "grad_norm": 9.257173538208008,
      "learning_rate": 5.05e-06,
      "loss": 1.2995,
      "step": 110
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": 12.88524341583252,
      "learning_rate": 4.488888888888889e-06,
      "loss": 1.1067,
      "step": 120
    },
    {
      "epoch": 0.06615776081424936,
      "grad_norm": 5.52728796005249,
      "learning_rate": 3.927777777777778e-06,
      "loss": 0.8998,
      "step": 130
    },
    {
      "epoch": 0.07124681933842239,
      "grad_norm": 11.348931312561035,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 0.7852,
      "step": 140
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": 9.074958801269531,
      "learning_rate": 2.8055555555555555e-06,
      "loss": 0.7446,
      "step": 150
    },
    {
      "epoch": 0.07633587786259542,
      "eval_loss": 0.9015980362892151,
      "eval_runtime": 35.055,
      "eval_samples_per_second": 23.62,
      "eval_steps_per_second": 5.905,
      "step": 150
    },
    {
      "epoch": 0.08142493638676845,
      "grad_norm": 9.362646102905273,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 1.1438,
      "step": 160
    },
    {
      "epoch": 0.08651399491094147,
      "grad_norm": 14.217305183410645,
      "learning_rate": 1.6833333333333332e-06,
      "loss": 1.2251,
      "step": 170
    },
    {
      "epoch": 0.0916030534351145,
      "grad_norm": 8.306926727294922,
      "learning_rate": 1.1222222222222222e-06,
      "loss": 0.7782,
      "step": 180
    },
    {
      "epoch": 0.09669211195928754,
      "grad_norm": 8.390512466430664,
      "learning_rate": 5.611111111111111e-07,
      "loss": 0.8091,
      "step": 190
    },
    {
      "epoch": 0.10178117048346055,
      "grad_norm": 9.584101676940918,
      "learning_rate": 0.0,
      "loss": 0.6583,
      "step": 200
    },
    {
      "epoch": 0.10178117048346055,
      "eval_loss": 0.8921794295310974,
      "eval_runtime": 35.0768,
      "eval_samples_per_second": 23.605,
      "eval_steps_per_second": 5.901,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 5.33047358301143e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}