{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0028107652308340947,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014053826154170472,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 1.1959,
      "step": 1
    },
    {
      "epoch": 0.00014053826154170472,
      "eval_loss": NaN,
      "eval_runtime": 271.2595,
      "eval_samples_per_second": 11.048,
      "eval_steps_per_second": 5.526,
      "step": 1
    },
    {
      "epoch": 0.00028107652308340944,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004216147846251142,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005621530461668189,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0007026913077085237,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0007026913077085237,
      "eval_loss": NaN,
      "eval_runtime": 261.1277,
      "eval_samples_per_second": 11.477,
      "eval_steps_per_second": 5.74,
      "step": 5
    },
    {
      "epoch": 0.0008432295692502284,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.000983767830791933,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0011243060923336377,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0012648443538753427,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0014053826154170473,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0014053826154170473,
      "eval_loss": NaN,
      "eval_runtime": 282.2971,
      "eval_samples_per_second": 10.616,
      "eval_steps_per_second": 5.31,
      "step": 10
    },
    {
      "epoch": 0.001545920876958752,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0016864591385004567,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0018269974000421614,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.001967535661583866,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.002108073923125571,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.002108073923125571,
      "eval_loss": NaN,
      "eval_runtime": 262.5314,
      "eval_samples_per_second": 11.416,
      "eval_steps_per_second": 5.71,
      "step": 15
    },
    {
      "epoch": 0.0022486121846672755,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0023891504462089804,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0025296887077506853,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0026702269692923898,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0028107652308340947,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0028107652308340947,
      "eval_loss": NaN,
      "eval_runtime": 285.8451,
      "eval_samples_per_second": 10.485,
      "eval_steps_per_second": 5.244,
      "step": 20
    }
  ],
  "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1297193034055680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}