{
  "best_metric": 0.9945604801177979,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.001680366319857729,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.60122106619243e-05,
      "eval_loss": 1.4336460828781128,
      "eval_runtime": 1753.5388,
      "eval_samples_per_second": 8.574,
      "eval_steps_per_second": 2.144,
      "step": 1
    },
    {
      "epoch": 0.0001680366319857729,
      "grad_norm": 0.266056090593338,
      "learning_rate": 0.00012,
      "loss": 1.0415,
      "step": 3
    },
    {
      "epoch": 0.0002800610533096215,
      "eval_loss": 1.2916927337646484,
      "eval_runtime": 1766.1911,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 2.128,
      "step": 5
    },
    {
      "epoch": 0.0003360732639715458,
      "grad_norm": 0.27385246753692627,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.0691,
      "step": 6
    },
    {
      "epoch": 0.0005041098959573187,
      "grad_norm": 0.2463141828775406,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.9389,
      "step": 9
    },
    {
      "epoch": 0.000560122106619243,
      "eval_loss": 1.1044895648956299,
      "eval_runtime": 1760.9403,
      "eval_samples_per_second": 8.538,
      "eval_steps_per_second": 2.135,
      "step": 10
    },
    {
      "epoch": 0.0006721465279430916,
      "grad_norm": 0.24110695719718933,
      "learning_rate": 0.000163742398974869,
      "loss": 0.8667,
      "step": 12
    },
    {
      "epoch": 0.0008401831599288645,
      "grad_norm": 0.2110568881034851,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.8972,
      "step": 15
    },
    {
      "epoch": 0.0008401831599288645,
      "eval_loss": 1.0320571660995483,
      "eval_runtime": 1759.5308,
      "eval_samples_per_second": 8.545,
      "eval_steps_per_second": 2.136,
      "step": 15
    },
    {
      "epoch": 0.0010082197919146375,
      "grad_norm": 0.20842613279819489,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8877,
      "step": 18
    },
    {
      "epoch": 0.001120244213238486,
      "eval_loss": 1.008935570716858,
      "eval_runtime": 1767.2628,
      "eval_samples_per_second": 8.508,
      "eval_steps_per_second": 2.127,
      "step": 20
    },
    {
      "epoch": 0.0011762564239004103,
      "grad_norm": 0.23792214691638947,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.9618,
      "step": 21
    },
    {
      "epoch": 0.0013442930558861831,
      "grad_norm": 0.36009231209754944,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.9181,
      "step": 24
    },
    {
      "epoch": 0.0014003052665481075,
      "eval_loss": 0.9974409341812134,
      "eval_runtime": 1758.6928,
      "eval_samples_per_second": 8.549,
      "eval_steps_per_second": 2.137,
      "step": 25
    },
    {
      "epoch": 0.001512329687871956,
      "grad_norm": 0.3084743022918701,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.9566,
      "step": 27
    },
    {
      "epoch": 0.001680366319857729,
      "grad_norm": 0.2365425080060959,
      "learning_rate": 0.0,
      "loss": 0.9478,
      "step": 30
    },
    {
      "epoch": 0.001680366319857729,
      "eval_loss": 0.9945604801177979,
      "eval_runtime": 1766.1165,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 2.128,
      "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": 2.114592047313715e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}