{
  "best_metric": 0.09427446126937866,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.5827505827505828,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011655011655011655,
      "eval_loss": 0.741592526435852,
      "eval_runtime": 297.9811,
      "eval_samples_per_second": 4.849,
      "eval_steps_per_second": 1.215,
      "step": 1
    },
    {
      "epoch": 0.05827505827505827,
      "grad_norm": 0.10792286694049835,
      "learning_rate": 0.0001015,
      "loss": 0.3563,
      "step": 50
    },
    {
      "epoch": 0.11655011655011654,
      "grad_norm": 0.10931839793920517,
      "learning_rate": 0.000203,
      "loss": 0.1276,
      "step": 100
    },
    {
      "epoch": 0.17482517482517482,
      "grad_norm": 0.08734647929668427,
      "learning_rate": 0.0001952737725498956,
      "loss": 0.114,
      "step": 150
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 0.08177594095468521,
      "learning_rate": 0.00017327133829043458,
      "loss": 0.1094,
      "step": 200
    },
    {
      "epoch": 0.2913752913752914,
      "grad_norm": 0.07702960073947906,
      "learning_rate": 0.00014034236838505662,
      "loss": 0.1038,
      "step": 250
    },
    {
      "epoch": 0.34965034965034963,
      "grad_norm": 0.06751956045627594,
      "learning_rate": 0.0001015,
      "loss": 0.1017,
      "step": 300
    },
    {
      "epoch": 0.40792540792540793,
      "grad_norm": 0.08754152804613113,
      "learning_rate": 6.265763161494339e-05,
      "loss": 0.0974,
      "step": 350
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 0.07237119227647781,
      "learning_rate": 2.972866170956543e-05,
      "loss": 0.0956,
      "step": 400
    },
    {
      "epoch": 0.5244755244755245,
      "grad_norm": 0.074247345328331,
      "learning_rate": 7.726227450104397e-06,
      "loss": 0.0929,
      "step": 450
    },
    {
      "epoch": 0.5827505827505828,
      "grad_norm": 0.07363295555114746,
      "learning_rate": 0.0,
      "loss": 0.0937,
      "step": 500
    },
    {
      "epoch": 0.5827505827505828,
      "eval_loss": 0.09427446126937866,
      "eval_runtime": 299.3865,
      "eval_samples_per_second": 4.827,
      "eval_steps_per_second": 1.209,
      "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": 1.330508659163136e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}