{
  "best_metric": 2.4877736568450928,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.11461318051575932,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038204393505253103,
      "eval_loss": 2.926515817642212,
      "eval_runtime": 54.4104,
      "eval_samples_per_second": 4.062,
      "eval_steps_per_second": 1.029,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 1.1782021522521973,
      "learning_rate": 0.00012,
      "loss": 2.8327,
      "step": 3
    },
    {
      "epoch": 0.019102196752626553,
      "eval_loss": 2.790332078933716,
      "eval_runtime": 54.9649,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 1.019,
      "step": 5
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 1.7630680799484253,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.748,
      "step": 6
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 0.5621840357780457,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.6568,
      "step": 9
    },
    {
      "epoch": 0.038204393505253106,
      "eval_loss": 2.610966920852661,
      "eval_runtime": 55.0066,
      "eval_samples_per_second": 4.018,
      "eval_steps_per_second": 1.018,
      "step": 10
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 0.31229570508003235,
      "learning_rate": 0.000163742398974869,
      "loss": 2.5721,
      "step": 12
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 0.5381006598472595,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.5459,
      "step": 15
    },
    {
      "epoch": 0.05730659025787966,
      "eval_loss": 2.543789863586426,
      "eval_runtime": 55.0984,
      "eval_samples_per_second": 4.011,
      "eval_steps_per_second": 1.016,
      "step": 15
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 0.31377890706062317,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.4588,
      "step": 18
    },
    {
      "epoch": 0.07640878701050621,
      "eval_loss": 2.507934093475342,
      "eval_runtime": 55.2267,
      "eval_samples_per_second": 4.002,
      "eval_steps_per_second": 1.014,
      "step": 20
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 0.3289887607097626,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.5418,
      "step": 21
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 0.3244362771511078,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.4964,
      "step": 24
    },
    {
      "epoch": 0.09551098376313276,
      "eval_loss": 2.4908852577209473,
      "eval_runtime": 55.1682,
      "eval_samples_per_second": 4.006,
      "eval_steps_per_second": 1.015,
      "step": 25
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 0.28559231758117676,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.4793,
      "step": 27
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 0.29243090748786926,
      "learning_rate": 0.0,
      "loss": 2.4764,
      "step": 30
    },
    {
      "epoch": 0.11461318051575932,
      "eval_loss": 2.4877736568450928,
      "eval_runtime": 55.2145,
      "eval_samples_per_second": 4.003,
      "eval_steps_per_second": 1.014,
      "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": 4.451323701362688e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}