{
  "best_metric": 0.8657696843147278,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.007209805335255948,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003604902667627974,
      "grad_norm": 0.45584237575531006,
      "learning_rate": 2e-05,
      "loss": 3.1068,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 0.8963788151741028,
      "eval_runtime": 234.2242,
      "eval_samples_per_second": 4.991,
      "eval_steps_per_second": 2.498,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 0.34380054473876953,
      "learning_rate": 4e-05,
      "loss": 3.1023,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 0.325403094291687,
      "learning_rate": 6e-05,
      "loss": 4.0382,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 0.3634743392467499,
      "learning_rate": 8e-05,
      "loss": 3.5371,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 0.4651695787906647,
      "learning_rate": 0.0001,
      "loss": 3.4133,
      "step": 5
    },
    {
      "epoch": 0.001802451333813987,
      "eval_loss": 0.8960704207420349,
      "eval_runtime": 234.1442,
      "eval_samples_per_second": 4.993,
      "eval_steps_per_second": 2.498,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 0.5198221206665039,
      "learning_rate": 0.00012,
      "loss": 3.1946,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 0.41471022367477417,
      "learning_rate": 0.00014,
      "loss": 3.0104,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 0.3969924747943878,
      "learning_rate": 0.00016,
      "loss": 3.8138,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 0.39321085810661316,
      "learning_rate": 0.00018,
      "loss": 3.8824,
      "step": 9
    },
    {
      "epoch": 0.003604902667627974,
      "grad_norm": 0.3689773976802826,
      "learning_rate": 0.0002,
      "loss": 3.2554,
      "step": 10
    },
    {
      "epoch": 0.003604902667627974,
      "eval_loss": 0.889240562915802,
      "eval_runtime": 234.1712,
      "eval_samples_per_second": 4.992,
      "eval_steps_per_second": 2.498,
      "step": 10
    },
    {
      "epoch": 0.003965392934390771,
      "grad_norm": 0.9040248990058899,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.1139,
      "step": 11
    },
    {
      "epoch": 0.004325883201153569,
      "grad_norm": 0.5644927024841309,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.7057,
      "step": 12
    },
    {
      "epoch": 0.004686373467916366,
      "grad_norm": 1.0138068199157715,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.6704,
      "step": 13
    },
    {
      "epoch": 0.005046863734679163,
      "grad_norm": 0.4622229337692261,
      "learning_rate": 0.00016691306063588583,
      "loss": 3.3469,
      "step": 14
    },
    {
      "epoch": 0.005407354001441961,
      "grad_norm": 0.5623894929885864,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.6863,
      "step": 15
    },
    {
      "epoch": 0.005407354001441961,
      "eval_loss": 0.8727303743362427,
      "eval_runtime": 231.1288,
      "eval_samples_per_second": 5.058,
      "eval_steps_per_second": 2.531,
      "step": 15
    },
    {
      "epoch": 0.005767844268204758,
      "grad_norm": 0.486777663230896,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.4783,
      "step": 16
    },
    {
      "epoch": 0.0061283345349675555,
      "grad_norm": 0.6631057858467102,
      "learning_rate": 0.00011045284632676536,
      "loss": 3.2112,
      "step": 17
    },
    {
      "epoch": 0.006488824801730353,
      "grad_norm": 0.6003482341766357,
      "learning_rate": 8.954715367323468e-05,
      "loss": 4.0095,
      "step": 18
    },
    {
      "epoch": 0.00684931506849315,
      "grad_norm": 0.5666629672050476,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.2599,
      "step": 19
    },
    {
      "epoch": 0.007209805335255948,
      "grad_norm": 0.7612733244895935,
      "learning_rate": 5.000000000000002e-05,
      "loss": 4.1332,
      "step": 20
    },
    {
      "epoch": 0.007209805335255948,
      "eval_loss": 0.8657696843147278,
      "eval_runtime": 231.5309,
      "eval_samples_per_second": 5.049,
      "eval_steps_per_second": 2.527,
      "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": 6474278237110272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}