{
  "best_metric": 1.1455615758895874,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02577873254564984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.5069729089736938,
      "eval_runtime": 40.8177,
      "eval_samples_per_second": 12.005,
      "eval_steps_per_second": 6.002,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.5732300281524658,
      "learning_rate": 0.00012,
      "loss": 1.3787,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 1.3689213991165161,
      "eval_runtime": 40.8673,
      "eval_samples_per_second": 11.99,
      "eval_steps_per_second": 5.995,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.6091071963310242,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.4081,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.5341973304748535,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.3382,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 1.2347180843353271,
      "eval_runtime": 40.8649,
      "eval_samples_per_second": 11.991,
      "eval_steps_per_second": 5.995,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 0.38722068071365356,
      "learning_rate": 0.000163742398974869,
      "loss": 1.207,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.4613712728023529,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1689,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 1.184698462486267,
      "eval_runtime": 40.9051,
      "eval_samples_per_second": 11.979,
      "eval_steps_per_second": 5.989,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 0.4428097605705261,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.2282,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 1.1592237949371338,
      "eval_runtime": 40.9161,
      "eval_samples_per_second": 11.976,
      "eval_steps_per_second": 5.988,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 0.4648377299308777,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.2069,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.38540998101234436,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.2756,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 1.1481420993804932,
      "eval_runtime": 40.8896,
      "eval_samples_per_second": 11.983,
      "eval_steps_per_second": 5.992,
      "step": 25
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 0.3698107600212097,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.1622,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.3534325659275055,
      "learning_rate": 0.0,
      "loss": 1.1373,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 1.1455615758895874,
      "eval_runtime": 40.8906,
      "eval_samples_per_second": 11.983,
      "eval_steps_per_second": 5.992,
      "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": 1.6599727969665024e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}