{
  "best_metric": 2.0622153282165527,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0009663314033547805,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.221104677849269e-05,
      "eval_loss": 2.376251697540283,
      "eval_runtime": 589.8143,
      "eval_samples_per_second": 22.163,
      "eval_steps_per_second": 11.081,
      "step": 1
    },
    {
      "epoch": 9.663314033547806e-05,
      "grad_norm": 0.48275649547576904,
      "learning_rate": 6e-05,
      "loss": 2.4765,
      "step": 3
    },
    {
      "epoch": 0.00016105523389246343,
      "eval_loss": 2.34928297996521,
      "eval_runtime": 597.6544,
      "eval_samples_per_second": 21.872,
      "eval_steps_per_second": 10.936,
      "step": 5
    },
    {
      "epoch": 0.0001932662806709561,
      "grad_norm": 0.4056912064552307,
      "learning_rate": 0.00012,
      "loss": 2.403,
      "step": 6
    },
    {
      "epoch": 0.0002898994210064342,
      "grad_norm": 0.4705870449542999,
      "learning_rate": 0.00018,
      "loss": 2.2731,
      "step": 9
    },
    {
      "epoch": 0.00032211046778492686,
      "eval_loss": 2.2104227542877197,
      "eval_runtime": 588.7424,
      "eval_samples_per_second": 22.203,
      "eval_steps_per_second": 11.102,
      "step": 10
    },
    {
      "epoch": 0.0003865325613419122,
      "grad_norm": 0.48776328563690186,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.2889,
      "step": 12
    },
    {
      "epoch": 0.00048316570167739026,
      "grad_norm": 0.5405465960502625,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.0378,
      "step": 15
    },
    {
      "epoch": 0.00048316570167739026,
      "eval_loss": 2.1149909496307373,
      "eval_runtime": 592.0405,
      "eval_samples_per_second": 22.08,
      "eval_steps_per_second": 11.04,
      "step": 15
    },
    {
      "epoch": 0.0005797988420128684,
      "grad_norm": 0.45608529448509216,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0422,
      "step": 18
    },
    {
      "epoch": 0.0006442209355698537,
      "eval_loss": 2.077925443649292,
      "eval_runtime": 596.284,
      "eval_samples_per_second": 21.922,
      "eval_steps_per_second": 10.961,
      "step": 20
    },
    {
      "epoch": 0.0006764319823483463,
      "grad_norm": 0.41135507822036743,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.9462,
      "step": 21
    },
    {
      "epoch": 0.0007730651226838244,
      "grad_norm": 0.38372039794921875,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.9378,
      "step": 24
    },
    {
      "epoch": 0.0008052761694623171,
      "eval_loss": 2.0651965141296387,
      "eval_runtime": 590.8792,
      "eval_samples_per_second": 22.123,
      "eval_steps_per_second": 11.061,
      "step": 25
    },
    {
      "epoch": 0.0008696982630193024,
      "grad_norm": 0.42051398754119873,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.0133,
      "step": 27
    },
    {
      "epoch": 0.0009663314033547805,
      "grad_norm": 0.40871503949165344,
      "learning_rate": 0.0,
      "loss": 2.0912,
      "step": 30
    },
    {
      "epoch": 0.0009663314033547805,
      "eval_loss": 2.0622153282165527,
      "eval_runtime": 592.6925,
      "eval_samples_per_second": 22.055,
      "eval_steps_per_second": 11.028,
      "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": 1959403255234560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}