{
  "best_metric": 0.9566317796707153,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0017191361340926185,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.595680670463093e-05,
      "grad_norm": 14.428430557250977,
      "learning_rate": 2e-05,
      "loss": 16.2145,
      "step": 1
    },
    {
      "epoch": 8.595680670463093e-05,
      "eval_loss": 4.0965118408203125,
      "eval_runtime": 930.5107,
      "eval_samples_per_second": 5.265,
      "eval_steps_per_second": 2.633,
      "step": 1
    },
    {
      "epoch": 0.00017191361340926185,
      "grad_norm": 15.419923782348633,
      "learning_rate": 4e-05,
      "loss": 16.5943,
      "step": 2
    },
    {
      "epoch": 0.0002578704201138928,
      "grad_norm": 14.638813972473145,
      "learning_rate": 6e-05,
      "loss": 15.6648,
      "step": 3
    },
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 16.37404441833496,
      "learning_rate": 8e-05,
      "loss": 17.9738,
      "step": 4
    },
    {
      "epoch": 0.00042978403352315463,
      "grad_norm": 15.420063972473145,
      "learning_rate": 0.0001,
      "loss": 16.0729,
      "step": 5
    },
    {
      "epoch": 0.00042978403352315463,
      "eval_loss": 3.745323896408081,
      "eval_runtime": 893.8333,
      "eval_samples_per_second": 5.481,
      "eval_steps_per_second": 2.741,
      "step": 5
    },
    {
      "epoch": 0.0005157408402277856,
      "grad_norm": 17.25224494934082,
      "learning_rate": 0.00012,
      "loss": 16.9417,
      "step": 6
    },
    {
      "epoch": 0.0006016976469324165,
      "grad_norm": 16.47061538696289,
      "learning_rate": 0.00014,
      "loss": 14.1699,
      "step": 7
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 18.41427993774414,
      "learning_rate": 0.00016,
      "loss": 13.86,
      "step": 8
    },
    {
      "epoch": 0.0007736112603416783,
      "grad_norm": 15.801340103149414,
      "learning_rate": 0.00018,
      "loss": 11.0289,
      "step": 9
    },
    {
      "epoch": 0.0008595680670463093,
      "grad_norm": 23.948348999023438,
      "learning_rate": 0.0002,
      "loss": 11.3058,
      "step": 10
    },
    {
      "epoch": 0.0008595680670463093,
      "eval_loss": 2.1212799549102783,
      "eval_runtime": 886.8924,
      "eval_samples_per_second": 5.524,
      "eval_steps_per_second": 2.762,
      "step": 10
    },
    {
      "epoch": 0.0009455248737509402,
      "grad_norm": 17.285173416137695,
      "learning_rate": 0.00019781476007338058,
      "loss": 9.1643,
      "step": 11
    },
    {
      "epoch": 0.0010314816804555711,
      "grad_norm": 20.7039852142334,
      "learning_rate": 0.0001913545457642601,
      "loss": 7.2011,
      "step": 12
    },
    {
      "epoch": 0.001117438487160202,
      "grad_norm": 15.796852111816406,
      "learning_rate": 0.00018090169943749476,
      "loss": 6.0756,
      "step": 13
    },
    {
      "epoch": 0.001203395293864833,
      "grad_norm": 13.192728042602539,
      "learning_rate": 0.00016691306063588583,
      "loss": 5.4776,
      "step": 14
    },
    {
      "epoch": 0.001289352100569464,
      "grad_norm": 16.307395935058594,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.4935,
      "step": 15
    },
    {
      "epoch": 0.001289352100569464,
      "eval_loss": 1.2589789628982544,
      "eval_runtime": 919.1048,
      "eval_samples_per_second": 5.33,
      "eval_steps_per_second": 2.666,
      "step": 15
    },
    {
      "epoch": 0.0013753089072740948,
      "grad_norm": 23.68831443786621,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.7626,
      "step": 16
    },
    {
      "epoch": 0.0014612657139787258,
      "grad_norm": 12.60560417175293,
      "learning_rate": 0.00011045284632676536,
      "loss": 4.5314,
      "step": 17
    },
    {
      "epoch": 0.0015472225206833567,
      "grad_norm": 16.297088623046875,
      "learning_rate": 8.954715367323468e-05,
      "loss": 5.5915,
      "step": 18
    },
    {
      "epoch": 0.0016331793273879876,
      "grad_norm": 11.184680938720703,
      "learning_rate": 6.909830056250527e-05,
      "loss": 4.0509,
      "step": 19
    },
    {
      "epoch": 0.0017191361340926185,
      "grad_norm": 16.991424560546875,
      "learning_rate": 5.000000000000002e-05,
      "loss": 4.8412,
      "step": 20
    },
    {
      "epoch": 0.0017191361340926185,
      "eval_loss": 0.9566317796707153,
      "eval_runtime": 913.3504,
      "eval_samples_per_second": 5.364,
      "eval_steps_per_second": 2.682,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 597531285258240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}