{
  "best_metric": 2.962515354156494,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.016687526074259492,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008343763037129745,
      "grad_norm": 34.29297637939453,
      "learning_rate": 2e-05,
      "loss": 24.0775,
      "step": 1
    },
    {
      "epoch": 0.0008343763037129745,
      "eval_loss": 5.678721904754639,
      "eval_runtime": 59.4816,
      "eval_samples_per_second": 8.49,
      "eval_steps_per_second": 4.253,
      "step": 1
    },
    {
      "epoch": 0.001668752607425949,
      "grad_norm": 24.284271240234375,
      "learning_rate": 4e-05,
      "loss": 23.022,
      "step": 2
    },
    {
      "epoch": 0.0025031289111389237,
      "grad_norm": 27.474864959716797,
      "learning_rate": 6e-05,
      "loss": 25.1288,
      "step": 3
    },
    {
      "epoch": 0.003337505214851898,
      "grad_norm": 28.17964744567871,
      "learning_rate": 8e-05,
      "loss": 26.486,
      "step": 4
    },
    {
      "epoch": 0.004171881518564873,
      "grad_norm": 27.849876403808594,
      "learning_rate": 0.0001,
      "loss": 21.9326,
      "step": 5
    },
    {
      "epoch": 0.004171881518564873,
      "eval_loss": 5.414963245391846,
      "eval_runtime": 57.7372,
      "eval_samples_per_second": 8.747,
      "eval_steps_per_second": 4.382,
      "step": 5
    },
    {
      "epoch": 0.0050062578222778474,
      "grad_norm": 29.93986701965332,
      "learning_rate": 0.00012,
      "loss": 25.6554,
      "step": 6
    },
    {
      "epoch": 0.005840634125990822,
      "grad_norm": 24.581716537475586,
      "learning_rate": 0.00014,
      "loss": 22.6291,
      "step": 7
    },
    {
      "epoch": 0.006675010429703796,
      "grad_norm": 26.354127883911133,
      "learning_rate": 0.00016,
      "loss": 20.9398,
      "step": 8
    },
    {
      "epoch": 0.007509386733416771,
      "grad_norm": 26.201875686645508,
      "learning_rate": 0.00018,
      "loss": 20.722,
      "step": 9
    },
    {
      "epoch": 0.008343763037129746,
      "grad_norm": 26.015750885009766,
      "learning_rate": 0.0002,
      "loss": 19.3643,
      "step": 10
    },
    {
      "epoch": 0.008343763037129746,
      "eval_loss": 4.316664218902588,
      "eval_runtime": 57.8275,
      "eval_samples_per_second": 8.733,
      "eval_steps_per_second": 4.375,
      "step": 10
    },
    {
      "epoch": 0.00917813934084272,
      "grad_norm": 24.7475528717041,
      "learning_rate": 0.00019781476007338058,
      "loss": 18.5352,
      "step": 11
    },
    {
      "epoch": 0.010012515644555695,
      "grad_norm": 24.95964241027832,
      "learning_rate": 0.0001913545457642601,
      "loss": 16.4059,
      "step": 12
    },
    {
      "epoch": 0.01084689194826867,
      "grad_norm": 22.137861251831055,
      "learning_rate": 0.00018090169943749476,
      "loss": 15.0218,
      "step": 13
    },
    {
      "epoch": 0.011681268251981644,
      "grad_norm": 20.20884895324707,
      "learning_rate": 0.00016691306063588583,
      "loss": 16.2653,
      "step": 14
    },
    {
      "epoch": 0.012515644555694618,
      "grad_norm": 26.685359954833984,
      "learning_rate": 0.00015000000000000001,
      "loss": 11.843,
      "step": 15
    },
    {
      "epoch": 0.012515644555694618,
      "eval_loss": 3.342318534851074,
      "eval_runtime": 58.0024,
      "eval_samples_per_second": 8.707,
      "eval_steps_per_second": 4.362,
      "step": 15
    },
    {
      "epoch": 0.013350020859407593,
      "grad_norm": 24.334922790527344,
      "learning_rate": 0.00013090169943749476,
      "loss": 12.9716,
      "step": 16
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 28.592124938964844,
      "learning_rate": 0.00011045284632676536,
      "loss": 14.8966,
      "step": 17
    },
    {
      "epoch": 0.015018773466833541,
      "grad_norm": 28.8742733001709,
      "learning_rate": 8.954715367323468e-05,
      "loss": 14.9197,
      "step": 18
    },
    {
      "epoch": 0.015853149770546516,
      "grad_norm": 23.675039291381836,
      "learning_rate": 6.909830056250527e-05,
      "loss": 11.3489,
      "step": 19
    },
    {
      "epoch": 0.016687526074259492,
      "grad_norm": 27.08548927307129,
      "learning_rate": 5.000000000000002e-05,
      "loss": 13.8079,
      "step": 20
    },
    {
      "epoch": 0.016687526074259492,
      "eval_loss": 2.962515354156494,
      "eval_runtime": 58.0866,
      "eval_samples_per_second": 8.694,
      "eval_steps_per_second": 4.356,
      "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": 150858041917440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}