{
  "best_metric": 1.8213965892791748,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.13083867591259976,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026167735182519954,
      "eval_loss": 2.884338617324829,
      "eval_runtime": 711.1328,
      "eval_samples_per_second": 9.052,
      "eval_steps_per_second": 2.264,
      "step": 1
    },
    {
      "epoch": 0.013083867591259976,
      "grad_norm": 1.4948066473007202,
      "learning_rate": 0.000106,
      "loss": 2.1167,
      "step": 50
    },
    {
      "epoch": 0.02616773518251995,
      "grad_norm": 1.645493507385254,
      "learning_rate": 0.000212,
      "loss": 1.8784,
      "step": 100
    },
    {
      "epoch": 0.03925160277377993,
      "grad_norm": 1.3755465745925903,
      "learning_rate": 0.0002039312304461964,
      "loss": 1.8797,
      "step": 150
    },
    {
      "epoch": 0.0523354703650399,
      "grad_norm": 3.6685054302215576,
      "learning_rate": 0.00018095331880577404,
      "loss": 1.891,
      "step": 200
    },
    {
      "epoch": 0.06541933795629988,
      "grad_norm": 1.4065568447113037,
      "learning_rate": 0.00014656444383069953,
      "loss": 1.8882,
      "step": 250
    },
    {
      "epoch": 0.07850320554755987,
      "grad_norm": 1.3157413005828857,
      "learning_rate": 0.000106,
      "loss": 1.8365,
      "step": 300
    },
    {
      "epoch": 0.09158707313881984,
      "grad_norm": 1.2989448308944702,
      "learning_rate": 6.543555616930049e-05,
      "loss": 1.8363,
      "step": 350
    },
    {
      "epoch": 0.1046709407300798,
      "grad_norm": 1.3002171516418457,
      "learning_rate": 3.104668119422597e-05,
      "loss": 1.8237,
      "step": 400
    },
    {
      "epoch": 0.11775480832133979,
      "grad_norm": 1.2948780059814453,
      "learning_rate": 8.068769553803605e-06,
      "loss": 1.8233,
      "step": 450
    },
    {
      "epoch": 0.13083867591259976,
      "grad_norm": 1.357683539390564,
      "learning_rate": 0.0,
      "loss": 1.8182,
      "step": 500
    },
    {
      "epoch": 0.13083867591259976,
      "eval_loss": 1.8213965892791748,
      "eval_runtime": 711.9984,
      "eval_samples_per_second": 9.041,
      "eval_steps_per_second": 2.261,
      "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": 7.544453535702712e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}