{
  "best_metric": 1.3705416917800903,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.003274662300450266,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010915541001500886,
      "eval_loss": 3.5515098571777344,
      "eval_runtime": 1069.192,
      "eval_samples_per_second": 7.216,
      "eval_steps_per_second": 1.804,
      "step": 1
    },
    {
      "epoch": 0.0003274662300450266,
      "grad_norm": 21.812204360961914,
      "learning_rate": 0.00012,
      "loss": 11.4709,
      "step": 3
    },
    {
      "epoch": 0.0005457770500750444,
      "eval_loss": 2.626392364501953,
      "eval_runtime": 1073.9859,
      "eval_samples_per_second": 7.184,
      "eval_steps_per_second": 1.796,
      "step": 5
    },
    {
      "epoch": 0.0006549324600900532,
      "grad_norm": 18.207117080688477,
      "learning_rate": 0.0001992114701314478,
      "loss": 9.8075,
      "step": 6
    },
    {
      "epoch": 0.0009823986901350797,
      "grad_norm": 15.498631477355957,
      "learning_rate": 0.00018763066800438636,
      "loss": 7.7707,
      "step": 9
    },
    {
      "epoch": 0.0010915541001500887,
      "eval_loss": 1.7839173078536987,
      "eval_runtime": 1076.0695,
      "eval_samples_per_second": 7.17,
      "eval_steps_per_second": 1.793,
      "step": 10
    },
    {
      "epoch": 0.0013098649201801064,
      "grad_norm": 10.780076026916504,
      "learning_rate": 0.000163742398974869,
      "loss": 6.8201,
      "step": 12
    },
    {
      "epoch": 0.001637331150225133,
      "grad_norm": 9.651141166687012,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.3769,
      "step": 15
    },
    {
      "epoch": 0.001637331150225133,
      "eval_loss": 1.5862396955490112,
      "eval_runtime": 1075.836,
      "eval_samples_per_second": 7.171,
      "eval_steps_per_second": 1.793,
      "step": 15
    },
    {
      "epoch": 0.0019647973802701594,
      "grad_norm": 10.259759902954102,
      "learning_rate": 9.372094804706867e-05,
      "loss": 6.0802,
      "step": 18
    },
    {
      "epoch": 0.0021831082003001775,
      "eval_loss": 1.4430060386657715,
      "eval_runtime": 1075.7185,
      "eval_samples_per_second": 7.172,
      "eval_steps_per_second": 1.793,
      "step": 20
    },
    {
      "epoch": 0.002292263610315186,
      "grad_norm": 8.80397891998291,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 5.7287,
      "step": 21
    },
    {
      "epoch": 0.0026197298403602127,
      "grad_norm": 9.108375549316406,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 5.637,
      "step": 24
    },
    {
      "epoch": 0.0027288852503752218,
      "eval_loss": 1.3819360733032227,
      "eval_runtime": 1076.1061,
      "eval_samples_per_second": 7.169,
      "eval_steps_per_second": 1.793,
      "step": 25
    },
    {
      "epoch": 0.0029471960704052394,
      "grad_norm": 9.284589767456055,
      "learning_rate": 7.022351411174866e-06,
      "loss": 5.4122,
      "step": 27
    },
    {
      "epoch": 0.003274662300450266,
      "grad_norm": 9.895240783691406,
      "learning_rate": 0.0,
      "loss": 5.2954,
      "step": 30
    },
    {
      "epoch": 0.003274662300450266,
      "eval_loss": 1.3705416917800903,
      "eval_runtime": 1075.5476,
      "eval_samples_per_second": 7.173,
      "eval_steps_per_second": 1.794,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.109388496044032e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}