{
  "best_metric": 11.034719467163086,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.011211809772960851,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003737269924320284,
      "eval_loss": 11.11019515991211,
      "eval_runtime": 6.5951,
      "eval_samples_per_second": 170.885,
      "eval_steps_per_second": 85.518,
      "step": 1
    },
    {
      "epoch": 0.0011211809772960853,
      "grad_norm": 1.0661489963531494,
      "learning_rate": 0.00012,
      "loss": 44.4724,
      "step": 3
    },
    {
      "epoch": 0.001868634962160142,
      "eval_loss": 11.102643966674805,
      "eval_runtime": 5.892,
      "eval_samples_per_second": 191.277,
      "eval_steps_per_second": 95.724,
      "step": 5
    },
    {
      "epoch": 0.0022423619545921705,
      "grad_norm": 1.1860142946243286,
      "learning_rate": 0.0001992114701314478,
      "loss": 44.4161,
      "step": 6
    },
    {
      "epoch": 0.0033635429318882555,
      "grad_norm": 1.1881811618804932,
      "learning_rate": 0.00018763066800438636,
      "loss": 44.3998,
      "step": 9
    },
    {
      "epoch": 0.003737269924320284,
      "eval_loss": 11.081565856933594,
      "eval_runtime": 5.9097,
      "eval_samples_per_second": 190.704,
      "eval_steps_per_second": 95.437,
      "step": 10
    },
    {
      "epoch": 0.004484723909184341,
      "grad_norm": 1.2235581874847412,
      "learning_rate": 0.000163742398974869,
      "loss": 44.3337,
      "step": 12
    },
    {
      "epoch": 0.005605904886480426,
      "grad_norm": 1.2298794984817505,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.284,
      "step": 15
    },
    {
      "epoch": 0.005605904886480426,
      "eval_loss": 11.060151100158691,
      "eval_runtime": 6.0065,
      "eval_samples_per_second": 187.631,
      "eval_steps_per_second": 93.899,
      "step": 15
    },
    {
      "epoch": 0.006727085863776511,
      "grad_norm": 1.3735557794570923,
      "learning_rate": 9.372094804706867e-05,
      "loss": 44.2111,
      "step": 18
    },
    {
      "epoch": 0.007474539848640568,
      "eval_loss": 11.044090270996094,
      "eval_runtime": 5.9024,
      "eval_samples_per_second": 190.938,
      "eval_steps_per_second": 95.554,
      "step": 20
    },
    {
      "epoch": 0.007848266841072597,
      "grad_norm": 1.3862786293029785,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 44.1421,
      "step": 21
    },
    {
      "epoch": 0.008969447818368682,
      "grad_norm": 1.3453408479690552,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 44.173,
      "step": 24
    },
    {
      "epoch": 0.00934317481080071,
      "eval_loss": 11.036252975463867,
      "eval_runtime": 5.9901,
      "eval_samples_per_second": 188.143,
      "eval_steps_per_second": 94.155,
      "step": 25
    },
    {
      "epoch": 0.010090628795664768,
      "grad_norm": 1.2414804697036743,
      "learning_rate": 7.022351411174866e-06,
      "loss": 44.1607,
      "step": 27
    },
    {
      "epoch": 0.011211809772960851,
      "grad_norm": 1.4629985094070435,
      "learning_rate": 0.0,
      "loss": 44.1362,
      "step": 30
    },
    {
      "epoch": 0.011211809772960851,
      "eval_loss": 11.034719467163086,
      "eval_runtime": 5.941,
      "eval_samples_per_second": 189.7,
      "eval_steps_per_second": 94.934,
      "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": 655185936384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}