{
  "best_metric": 1.362160563468933,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.04230565838180857,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021152829190904283,
      "eval_loss": 2.7000086307525635,
      "eval_runtime": 6.1387,
      "eval_samples_per_second": 32.417,
      "eval_steps_per_second": 16.29,
      "step": 1
    },
    {
      "epoch": 0.006345848757271285,
      "grad_norm": 5.318497180938721,
      "learning_rate": 0.00012,
      "loss": 2.5873,
      "step": 3
    },
    {
      "epoch": 0.010576414595452142,
      "eval_loss": 2.2884433269500732,
      "eval_runtime": 5.8237,
      "eval_samples_per_second": 34.171,
      "eval_steps_per_second": 17.171,
      "step": 5
    },
    {
      "epoch": 0.01269169751454257,
      "grad_norm": 2.5810461044311523,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.5829,
      "step": 6
    },
    {
      "epoch": 0.019037546271813855,
      "grad_norm": 3.1680948734283447,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0144,
      "step": 9
    },
    {
      "epoch": 0.021152829190904283,
      "eval_loss": 1.6477967500686646,
      "eval_runtime": 5.8873,
      "eval_samples_per_second": 33.801,
      "eval_steps_per_second": 16.986,
      "step": 10
    },
    {
      "epoch": 0.02538339502908514,
      "grad_norm": 4.1059041023254395,
      "learning_rate": 0.000163742398974869,
      "loss": 1.7207,
      "step": 12
    },
    {
      "epoch": 0.03172924378635643,
      "grad_norm": 1.7723767757415771,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4975,
      "step": 15
    },
    {
      "epoch": 0.03172924378635643,
      "eval_loss": 1.4309803247451782,
      "eval_runtime": 5.9816,
      "eval_samples_per_second": 33.268,
      "eval_steps_per_second": 16.718,
      "step": 15
    },
    {
      "epoch": 0.03807509254362771,
      "grad_norm": 1.3478217124938965,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.4421,
      "step": 18
    },
    {
      "epoch": 0.04230565838180857,
      "eval_loss": 1.362160563468933,
      "eval_runtime": 6.0179,
      "eval_samples_per_second": 33.068,
      "eval_steps_per_second": 16.617,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1029368772034560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}