{
  "best_metric": 0.607528030872345,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.009253547193090685,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030845157310302283,
      "eval_loss": 0.8441849946975708,
      "eval_runtime": 64.7567,
      "eval_samples_per_second": 21.079,
      "eval_steps_per_second": 10.547,
      "step": 1
    },
    {
      "epoch": 0.0009253547193090684,
      "grad_norm": 0.08122389763593674,
      "learning_rate": 0.00012,
      "loss": 0.5338,
      "step": 3
    },
    {
      "epoch": 0.0015422578655151142,
      "eval_loss": 0.8161515593528748,
      "eval_runtime": 68.3304,
      "eval_samples_per_second": 19.976,
      "eval_steps_per_second": 9.996,
      "step": 5
    },
    {
      "epoch": 0.001850709438618137,
      "grad_norm": 0.10917606204748154,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.5386,
      "step": 6
    },
    {
      "epoch": 0.0027760641579272056,
      "grad_norm": 0.13072222471237183,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.5337,
      "step": 9
    },
    {
      "epoch": 0.0030845157310302285,
      "eval_loss": 0.7031258940696716,
      "eval_runtime": 69.8286,
      "eval_samples_per_second": 19.548,
      "eval_steps_per_second": 9.781,
      "step": 10
    },
    {
      "epoch": 0.003701418877236274,
      "grad_norm": 0.17671124637126923,
      "learning_rate": 0.000163742398974869,
      "loss": 0.5097,
      "step": 12
    },
    {
      "epoch": 0.0046267735965453425,
      "grad_norm": 0.215486541390419,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5113,
      "step": 15
    },
    {
      "epoch": 0.0046267735965453425,
      "eval_loss": 0.6584131121635437,
      "eval_runtime": 70.0635,
      "eval_samples_per_second": 19.482,
      "eval_steps_per_second": 9.748,
      "step": 15
    },
    {
      "epoch": 0.005552128315854411,
      "grad_norm": 0.27064475417137146,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.5853,
      "step": 18
    },
    {
      "epoch": 0.006169031462060457,
      "eval_loss": 0.6288348436355591,
      "eval_runtime": 70.2349,
      "eval_samples_per_second": 19.435,
      "eval_steps_per_second": 9.725,
      "step": 20
    },
    {
      "epoch": 0.006477483035163479,
      "grad_norm": 0.27787524461746216,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.4794,
      "step": 21
    },
    {
      "epoch": 0.007402837754472548,
      "grad_norm": 0.3034648597240448,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.5732,
      "step": 24
    },
    {
      "epoch": 0.0077112893275755705,
      "eval_loss": 0.6111285090446472,
      "eval_runtime": 70.2828,
      "eval_samples_per_second": 19.422,
      "eval_steps_per_second": 9.718,
      "step": 25
    },
    {
      "epoch": 0.008328192473781616,
      "grad_norm": 0.2949819564819336,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.5781,
      "step": 27
    },
    {
      "epoch": 0.009253547193090685,
      "grad_norm": 0.3319774270057678,
      "learning_rate": 0.0,
      "loss": 0.6198,
      "step": 30
    },
    {
      "epoch": 0.009253547193090685,
      "eval_loss": 0.607528030872345,
      "eval_runtime": 70.2908,
      "eval_samples_per_second": 19.419,
      "eval_steps_per_second": 9.717,
      "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": 1973893157879808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}