{
  "best_metric": 1.6087056398391724,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.03475238922675934,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017376194613379669,
      "grad_norm": 0.9239712953567505,
      "learning_rate": 2e-05,
      "loss": 2.4111,
      "step": 1
    },
    {
      "epoch": 0.0017376194613379669,
      "eval_loss": 2.3549845218658447,
      "eval_runtime": 70.6055,
      "eval_samples_per_second": 3.442,
      "eval_steps_per_second": 1.728,
      "step": 1
    },
    {
      "epoch": 0.0034752389226759338,
      "grad_norm": 0.7760213017463684,
      "learning_rate": 4e-05,
      "loss": 2.3583,
      "step": 2
    },
    {
      "epoch": 0.005212858384013901,
      "grad_norm": 0.6963823437690735,
      "learning_rate": 6e-05,
      "loss": 2.264,
      "step": 3
    },
    {
      "epoch": 0.0069504778453518675,
      "grad_norm": 0.6750634908676147,
      "learning_rate": 8e-05,
      "loss": 1.907,
      "step": 4
    },
    {
      "epoch": 0.008688097306689836,
      "grad_norm": 0.8768922686576843,
      "learning_rate": 0.0001,
      "loss": 2.3476,
      "step": 5
    },
    {
      "epoch": 0.008688097306689836,
      "eval_loss": 2.2883551120758057,
      "eval_runtime": 75.0878,
      "eval_samples_per_second": 3.236,
      "eval_steps_per_second": 1.625,
      "step": 5
    },
    {
      "epoch": 0.010425716768027803,
      "grad_norm": 1.0139464139938354,
      "learning_rate": 0.00012,
      "loss": 2.2134,
      "step": 6
    },
    {
      "epoch": 0.01216333622936577,
      "grad_norm": 1.1760687828063965,
      "learning_rate": 0.00014,
      "loss": 2.1547,
      "step": 7
    },
    {
      "epoch": 0.013900955690703735,
      "grad_norm": 1.0615777969360352,
      "learning_rate": 0.00016,
      "loss": 2.1396,
      "step": 8
    },
    {
      "epoch": 0.015638575152041704,
      "grad_norm": 0.7809844017028809,
      "learning_rate": 0.00018,
      "loss": 1.9578,
      "step": 9
    },
    {
      "epoch": 0.01737619461337967,
      "grad_norm": 0.510953426361084,
      "learning_rate": 0.0002,
      "loss": 1.9362,
      "step": 10
    },
    {
      "epoch": 0.01737619461337967,
      "eval_loss": 1.8564950227737427,
      "eval_runtime": 69.2931,
      "eval_samples_per_second": 3.507,
      "eval_steps_per_second": 1.761,
      "step": 10
    },
    {
      "epoch": 0.019113814074717638,
      "grad_norm": 0.5945761799812317,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.8057,
      "step": 11
    },
    {
      "epoch": 0.020851433536055605,
      "grad_norm": 1.0553749799728394,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.9281,
      "step": 12
    },
    {
      "epoch": 0.022589052997393572,
      "grad_norm": 0.8017647862434387,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.7854,
      "step": 13
    },
    {
      "epoch": 0.02432667245873154,
      "grad_norm": 0.8131036758422852,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.8849,
      "step": 14
    },
    {
      "epoch": 0.026064291920069503,
      "grad_norm": 0.7698544263839722,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5259,
      "step": 15
    },
    {
      "epoch": 0.026064291920069503,
      "eval_loss": 1.663969874382019,
      "eval_runtime": 69.1246,
      "eval_samples_per_second": 3.515,
      "eval_steps_per_second": 1.765,
      "step": 15
    },
    {
      "epoch": 0.02780191138140747,
      "grad_norm": 0.6345564723014832,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5678,
      "step": 16
    },
    {
      "epoch": 0.029539530842745437,
      "grad_norm": 0.6471442580223083,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.7016,
      "step": 17
    },
    {
      "epoch": 0.03127715030408341,
      "grad_norm": 0.6346880793571472,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.6915,
      "step": 18
    },
    {
      "epoch": 0.03301476976542137,
      "grad_norm": 1.3961195945739746,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.5982,
      "step": 19
    },
    {
      "epoch": 0.03475238922675934,
      "grad_norm": 0.6392167806625366,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.3933,
      "step": 20
    },
    {
      "epoch": 0.03475238922675934,
      "eval_loss": 1.6087056398391724,
      "eval_runtime": 69.6659,
      "eval_samples_per_second": 3.488,
      "eval_steps_per_second": 1.751,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 3913579442995200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}