{
  "best_metric": 1.5369007587432861,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.7658433850277618,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015316867700555237,
      "eval_loss": 3.2061047554016113,
      "eval_runtime": 25.8137,
      "eval_samples_per_second": 42.613,
      "eval_steps_per_second": 10.653,
      "step": 1
    },
    {
      "epoch": 0.07658433850277618,
      "grad_norm": 1.5110907554626465,
      "learning_rate": 0.0001015,
      "loss": 2.3406,
      "step": 50
    },
    {
      "epoch": 0.15316867700555237,
      "grad_norm": 1.2404429912567139,
      "learning_rate": 0.000203,
      "loss": 1.7922,
      "step": 100
    },
    {
      "epoch": 0.22975301550832855,
      "grad_norm": 0.9525713920593262,
      "learning_rate": 0.0001952737725498956,
      "loss": 1.6946,
      "step": 150
    },
    {
      "epoch": 0.30633735401110473,
      "grad_norm": 0.9197774529457092,
      "learning_rate": 0.00017327133829043458,
      "loss": 1.652,
      "step": 200
    },
    {
      "epoch": 0.3829216925138809,
      "grad_norm": 1.0582269430160522,
      "learning_rate": 0.00014034236838505662,
      "loss": 1.61,
      "step": 250
    },
    {
      "epoch": 0.4595060310166571,
      "grad_norm": 0.9777085185050964,
      "learning_rate": 0.0001015,
      "loss": 1.5777,
      "step": 300
    },
    {
      "epoch": 0.5360903695194332,
      "grad_norm": 1.0337378978729248,
      "learning_rate": 6.265763161494339e-05,
      "loss": 1.5685,
      "step": 350
    },
    {
      "epoch": 0.6126747080222095,
      "grad_norm": 1.0152058601379395,
      "learning_rate": 2.972866170956543e-05,
      "loss": 1.5596,
      "step": 400
    },
    {
      "epoch": 0.6892590465249856,
      "grad_norm": 1.2468204498291016,
      "learning_rate": 7.726227450104397e-06,
      "loss": 1.5478,
      "step": 450
    },
    {
      "epoch": 0.7658433850277618,
      "grad_norm": 1.0304168462753296,
      "learning_rate": 0.0,
      "loss": 1.5297,
      "step": 500
    },
    {
      "epoch": 0.7658433850277618,
      "eval_loss": 1.5369007587432861,
      "eval_runtime": 25.8665,
      "eval_samples_per_second": 42.526,
      "eval_steps_per_second": 10.631,
      "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": 3.329388183552e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}