{
  "best_metric": 2.541001081466675,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.017185821697099892,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.6087660789489746,
      "eval_runtime": 26.5872,
      "eval_samples_per_second": 18.43,
      "eval_steps_per_second": 9.215,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 2.643887758255005,
      "learning_rate": 0.00012,
      "loss": 10.5781,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 2.5878348350524902,
      "eval_runtime": 28.2222,
      "eval_samples_per_second": 17.362,
      "eval_steps_per_second": 8.681,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 3.242163896560669,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.2267,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 3.1395814418792725,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.9019,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 2.561180591583252,
      "eval_runtime": 29.3943,
      "eval_samples_per_second": 16.67,
      "eval_steps_per_second": 8.335,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 3.0960826873779297,
      "learning_rate": 0.000163742398974869,
      "loss": 10.8453,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 3.197446346282959,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.4302,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 2.5496432781219482,
      "eval_runtime": 30.0494,
      "eval_samples_per_second": 16.306,
      "eval_steps_per_second": 8.153,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 2.3374435901641846,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.3418,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 2.541001081466675,
      "eval_runtime": 30.3384,
      "eval_samples_per_second": 16.151,
      "eval_steps_per_second": 8.076,
      "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": 1893182157619200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}