{
  "best_metric": 1.5464701652526855,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.28153153153153154,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005630630630630631,
      "eval_loss": 3.8860297203063965,
      "eval_runtime": 410.3629,
      "eval_samples_per_second": 7.291,
      "eval_steps_per_second": 1.823,
      "step": 1
    },
    {
      "epoch": 0.028153153153153154,
      "grad_norm": 1.2904592752456665,
      "learning_rate": 0.0001005,
      "loss": 3.0054,
      "step": 50
    },
    {
      "epoch": 0.05630630630630631,
      "grad_norm": 1.0581908226013184,
      "learning_rate": 0.000201,
      "loss": 2.0279,
      "step": 100
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.1564744710922241,
      "learning_rate": 0.00019334989301738432,
      "loss": 1.924,
      "step": 150
    },
    {
      "epoch": 0.11261261261261261,
      "grad_norm": 1.2207306623458862,
      "learning_rate": 0.00017156423150924802,
      "loss": 1.8801,
      "step": 200
    },
    {
      "epoch": 0.14076576576576577,
      "grad_norm": 0.981479287147522,
      "learning_rate": 0.00013895968495269154,
      "loss": 1.8058,
      "step": 250
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 1.1009485721588135,
      "learning_rate": 0.0001005,
      "loss": 1.7601,
      "step": 300
    },
    {
      "epoch": 0.19707207207207209,
      "grad_norm": 1.5496914386749268,
      "learning_rate": 6.204031504730848e-05,
      "loss": 1.6338,
      "step": 350
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 0.9261886477470398,
      "learning_rate": 2.943576849075198e-05,
      "loss": 1.6326,
      "step": 400
    },
    {
      "epoch": 0.2533783783783784,
      "grad_norm": 1.1784789562225342,
      "learning_rate": 7.650106982615683e-06,
      "loss": 1.5803,
      "step": 450
    },
    {
      "epoch": 0.28153153153153154,
      "grad_norm": 1.4792702198028564,
      "learning_rate": 0.0,
      "loss": 1.5398,
      "step": 500
    },
    {
      "epoch": 0.28153153153153154,
      "eval_loss": 1.5464701652526855,
      "eval_runtime": 410.1054,
      "eval_samples_per_second": 7.296,
      "eval_steps_per_second": 1.824,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 8.914408016393011e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}