{
  "best_metric": 0.4230361878871918,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0005743206863132201,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8716034315661008e-05,
      "grad_norm": 8.671835899353027,
      "learning_rate": 2e-05,
      "loss": 1.4187,
      "step": 1
    },
    {
      "epoch": 2.8716034315661008e-05,
      "eval_loss": 0.5256153345108032,
      "eval_runtime": 3174.6735,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 2.31,
      "step": 1
    },
    {
      "epoch": 5.7432068631322015e-05,
      "grad_norm": 8.46462345123291,
      "learning_rate": 4e-05,
      "loss": 1.9288,
      "step": 2
    },
    {
      "epoch": 8.614810294698303e-05,
      "grad_norm": 8.922672271728516,
      "learning_rate": 6e-05,
      "loss": 2.189,
      "step": 3
    },
    {
      "epoch": 0.00011486413726264403,
      "grad_norm": 3.155928134918213,
      "learning_rate": 8e-05,
      "loss": 1.9052,
      "step": 4
    },
    {
      "epoch": 0.00014358017157830503,
      "grad_norm": 2.5399258136749268,
      "learning_rate": 0.0001,
      "loss": 1.5594,
      "step": 5
    },
    {
      "epoch": 0.00014358017157830503,
      "eval_loss": 0.4700046479701996,
      "eval_runtime": 3056.9868,
      "eval_samples_per_second": 4.797,
      "eval_steps_per_second": 2.398,
      "step": 5
    },
    {
      "epoch": 0.00017229620589396605,
      "grad_norm": 4.760073661804199,
      "learning_rate": 0.00012,
      "loss": 1.92,
      "step": 6
    },
    {
      "epoch": 0.00020101224020962704,
      "grad_norm": 2.369114637374878,
      "learning_rate": 0.00014,
      "loss": 1.6082,
      "step": 7
    },
    {
      "epoch": 0.00022972827452528806,
      "grad_norm": 1.7142950296401978,
      "learning_rate": 0.00016,
      "loss": 1.6912,
      "step": 8
    },
    {
      "epoch": 0.00025844430884094905,
      "grad_norm": 1.7321504354476929,
      "learning_rate": 0.00018,
      "loss": 1.7757,
      "step": 9
    },
    {
      "epoch": 0.00028716034315661007,
      "grad_norm": 2.134897470474243,
      "learning_rate": 0.0002,
      "loss": 1.8594,
      "step": 10
    },
    {
      "epoch": 0.00028716034315661007,
      "eval_loss": 0.4394129514694214,
      "eval_runtime": 3067.1184,
      "eval_samples_per_second": 4.781,
      "eval_steps_per_second": 2.391,
      "step": 10
    },
    {
      "epoch": 0.0003158763774722711,
      "grad_norm": 1.524711012840271,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.5585,
      "step": 11
    },
    {
      "epoch": 0.0003445924117879321,
      "grad_norm": 1.4126205444335938,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.2898,
      "step": 12
    },
    {
      "epoch": 0.00037330844610359307,
      "grad_norm": 1.89143967628479,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.7331,
      "step": 13
    },
    {
      "epoch": 0.0004020244804192541,
      "grad_norm": 1.7866116762161255,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.384,
      "step": 14
    },
    {
      "epoch": 0.0004307405147349151,
      "grad_norm": 2.72021484375,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.2272,
      "step": 15
    },
    {
      "epoch": 0.0004307405147349151,
      "eval_loss": 0.42954686284065247,
      "eval_runtime": 3093.5186,
      "eval_samples_per_second": 4.74,
      "eval_steps_per_second": 2.37,
      "step": 15
    },
    {
      "epoch": 0.0004594565490505761,
      "grad_norm": 1.447580099105835,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5618,
      "step": 16
    },
    {
      "epoch": 0.00048817258336623714,
      "grad_norm": 1.823649287223816,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.2623,
      "step": 17
    },
    {
      "epoch": 0.0005168886176818981,
      "grad_norm": 2.1619272232055664,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.9625,
      "step": 18
    },
    {
      "epoch": 0.0005456046519975591,
      "grad_norm": 2.0479583740234375,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.052,
      "step": 19
    },
    {
      "epoch": 0.0005743206863132201,
      "grad_norm": 1.1087257862091064,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.7707,
      "step": 20
    },
    {
      "epoch": 0.0005743206863132201,
      "eval_loss": 0.4230361878871918,
      "eval_runtime": 3099.0418,
      "eval_samples_per_second": 4.731,
      "eval_steps_per_second": 2.366,
      "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": 3505339571896320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}