{
  "best_metric": 1.7647069692611694,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0022853486299334964,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.141394519733986e-05,
      "grad_norm": 0.5803880095481873,
      "learning_rate": 2e-05,
      "loss": 2.1591,
      "step": 1
    },
    {
      "epoch": 9.141394519733986e-05,
      "eval_loss": 2.0811927318573,
      "eval_runtime": 761.9914,
      "eval_samples_per_second": 6.046,
      "eval_steps_per_second": 3.024,
      "step": 1
    },
    {
      "epoch": 0.00018282789039467972,
      "grad_norm": 0.6075868010520935,
      "learning_rate": 4e-05,
      "loss": 2.0175,
      "step": 2
    },
    {
      "epoch": 0.00027424183559201956,
      "grad_norm": 0.5318930149078369,
      "learning_rate": 6e-05,
      "loss": 2.0423,
      "step": 3
    },
    {
      "epoch": 0.00036565578078935943,
      "grad_norm": 0.5478139519691467,
      "learning_rate": 8e-05,
      "loss": 1.9214,
      "step": 4
    },
    {
      "epoch": 0.00045706972598669925,
      "grad_norm": 0.6103643178939819,
      "learning_rate": 0.0001,
      "loss": 1.8813,
      "step": 5
    },
    {
      "epoch": 0.00045706972598669925,
      "eval_loss": 2.0554721355438232,
      "eval_runtime": 762.1192,
      "eval_samples_per_second": 6.045,
      "eval_steps_per_second": 3.023,
      "step": 5
    },
    {
      "epoch": 0.0005484836711840391,
      "grad_norm": 0.588008463382721,
      "learning_rate": 0.00012,
      "loss": 1.9793,
      "step": 6
    },
    {
      "epoch": 0.0006398976163813789,
      "grad_norm": 0.5743737816810608,
      "learning_rate": 0.00014,
      "loss": 1.9886,
      "step": 7
    },
    {
      "epoch": 0.0007313115615787189,
      "grad_norm": 0.6633493900299072,
      "learning_rate": 0.00016,
      "loss": 2.0246,
      "step": 8
    },
    {
      "epoch": 0.0008227255067760587,
      "grad_norm": 0.6772180795669556,
      "learning_rate": 0.00018,
      "loss": 2.0035,
      "step": 9
    },
    {
      "epoch": 0.0009141394519733985,
      "grad_norm": 0.6537415981292725,
      "learning_rate": 0.0002,
      "loss": 1.9742,
      "step": 10
    },
    {
      "epoch": 0.0009141394519733985,
      "eval_loss": 1.9079514741897583,
      "eval_runtime": 767.7738,
      "eval_samples_per_second": 6.0,
      "eval_steps_per_second": 3.001,
      "step": 10
    },
    {
      "epoch": 0.0010055533971707383,
      "grad_norm": 0.7699624300003052,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.7672,
      "step": 11
    },
    {
      "epoch": 0.0010969673423680782,
      "grad_norm": 0.6934915781021118,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.8934,
      "step": 12
    },
    {
      "epoch": 0.0011883812875654182,
      "grad_norm": 0.6601593494415283,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.7728,
      "step": 13
    },
    {
      "epoch": 0.0012797952327627579,
      "grad_norm": 0.6147029399871826,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.9247,
      "step": 14
    },
    {
      "epoch": 0.0013712091779600978,
      "grad_norm": 0.667289137840271,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9045,
      "step": 15
    },
    {
      "epoch": 0.0013712091779600978,
      "eval_loss": 1.822645902633667,
      "eval_runtime": 759.4505,
      "eval_samples_per_second": 6.066,
      "eval_steps_per_second": 3.034,
      "step": 15
    },
    {
      "epoch": 0.0014626231231574377,
      "grad_norm": 0.6415672898292542,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7777,
      "step": 16
    },
    {
      "epoch": 0.0015540370683547774,
      "grad_norm": 0.6061315536499023,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.8845,
      "step": 17
    },
    {
      "epoch": 0.0016454510135521174,
      "grad_norm": 0.5643168091773987,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.7153,
      "step": 18
    },
    {
      "epoch": 0.0017368649587494573,
      "grad_norm": 0.566535234451294,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.7568,
      "step": 19
    },
    {
      "epoch": 0.001828278903946797,
      "grad_norm": 0.5283828973770142,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.6512,
      "step": 20
    },
    {
      "epoch": 0.001828278903946797,
      "eval_loss": 1.7753185033798218,
      "eval_runtime": 765.7992,
      "eval_samples_per_second": 6.016,
      "eval_steps_per_second": 3.009,
      "step": 20
    },
    {
      "epoch": 0.001919692849144137,
      "grad_norm": 0.5753809809684753,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.8469,
      "step": 21
    },
    {
      "epoch": 0.0020111067943414766,
      "grad_norm": 0.5540127158164978,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.8076,
      "step": 22
    },
    {
      "epoch": 0.0021025207395388166,
      "grad_norm": 0.5540910363197327,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.849,
      "step": 23
    },
    {
      "epoch": 0.0021939346847361565,
      "grad_norm": 0.500247061252594,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.6616,
      "step": 24
    },
    {
      "epoch": 0.0022853486299334964,
      "grad_norm": 0.487179160118103,
      "learning_rate": 0.0,
      "loss": 1.8192,
      "step": 25
    },
    {
      "epoch": 0.0022853486299334964,
      "eval_loss": 1.7647069692611694,
      "eval_runtime": 770.7116,
      "eval_samples_per_second": 5.978,
      "eval_steps_per_second": 2.989,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 4100243324928000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}